See also the list of my publications in Google scholar.
@inproceedings{li24learning, author = {Zizhang Li and Dor Litvak and Ruining Li and Yunzhi Zhang and Tomas Jakab and Christian Rupprecht and Shangzhe Wu and Andrea Vedaldi and Jiajun Wu}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {Learning the {3D} Fauna of the {Web}}, year = {2024} }
@inproceedings{chen24shap-editor:, author = {Minghao Chen and Junyu Xie and Iro Laina and Andrea Vedaldi}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {{SHAP-EDITOR}: Instruction-guided Latent {3D} Editing in Seconds}, year = {2024} }
@inproceedings{hamdi24ges:, author = {Abdullah Hamdi and Luke Melas-Kyriazi and Guocheng Qian and Jinjie Mai and Ruoshi Liu and Carl Vondrick and Bernard Ghanem and Andrea Vedaldi}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {{GES}: Generalized Exponential Splatting for Efficient Radiance Field Rendering}, year = {2024} }
@inproceedings{zheng2023free3d, author = {Chuanxia Zheng and Andrea Vedaldi}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {{Free3D}: Consistent Novel View Synthesis without {3D} Representation}, year = {2024} }
@inproceedings{szymanowicz24splatter, author = {Stanislaw Szymanowicz and Christian Rupprecht and Andrea Vedaldi}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {{Splatter Image}: Ultra-Fast Single-View {3D} Reconstruction}, year = {2024} }
@inproceedings{jakab24farm3d:, author = {Tomas Jakab and Ruining Li and Shangzhe Wu and Christian Rupprecht and Andrea Vedaldi}, booktitle = {Proceedings of the International Conference on {3D} Vision (3DV)}, title = {{Farm3D}: Learning Articulated {3D} Animals by Distilling {2D} Diffusion}, year = {2024} }
@inproceedings{chen24training-free, author = {Minghao Chen and Iro Laina and Andrea Vedaldi}, booktitle = {Proceedings of the {IEEE} Winter Conference on Applications of Computer Vision (WACV)}, title = {Training-Free Layout Control with Cross-Attention Guidance}, year = {2024} }
@article{melas-kyriazi24im-3d, author = {Luke Melas-Kyriazi and Iro Laina and Christian Rupprecht and Natalia Neverova and Andrea Vedaldi and Oran Gafni and Filippos Kokkinos}, journal = {arXiv preprint}, number = {abs/2402.08682}, title = {{IM-3D}: Iterative Multiview Diffusion and Reconstruction for High-Quality {3D} Generation}, year = {2024} }
@inproceedings{shtedritski23learning, author = {Aleksandar Shtedritski and Christian Rupprecht and Andrea Vedaldi}, booktitle = {Proc. IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, title = {Learning Universal Semantic Correspondences with No Supervision and Automatic Data Curation}, year = {2023} }
@inproceedings{vaze23no-representation, author = {Sagar Vaze and Andrea Vedaldi and Andrew Zisserman}, booktitle = {Proceedings of Advances in Neural Information Processing Systems (NeurIPS)}, title = {No Representation Rules Them All in Category Discovery}, year = {2023} }
@inproceedings{bhalgat23contrastive, author = {Yash Sanjay Bhalgat and Iro Laina and Joao F. Henriques and Andrea Vedaldi and Andrew Zisserman}, booktitle = {Proceedings of Advances in Neural Information Processing Systems (NeurIPS)}, title = {Contrastive Lift: 3D Object Instance Segmentation by Slow-Fast Contrastive Fusion}, year = {2023} }
@inproceedings{rocco23replay, author = {Ignacio Rocco and Iurii Makarov and Filippos Kokkinos and David Novotny and Ben Graham and Natalia Neverova and Andrea Vedaldi}, booktitle = {Proceedings of the International Conference on Computer Vision ({ICCV})}, title = {Replay: Multi-modal Multi-view Acted Videos for Casual Holography}, year = {2023} }
@inproceedings{szymanowicz23viewset, author = {Stanislaw Szymanowicz and Christian Rupprecht and Andrea Vedaldi}, booktitle = {Proceedings of the International Conference on Computer Vision ({ICCV})}, title = {Viewset Diffusion: (0-)Image-Conditioned {3D} Generative Models from {2D} Data}, year = {2023} }
@inproceedings{zheng23online, author = {Chuanxia Zheng and Andrea Vedaldi}, booktitle = {Proceedings of the International Conference on Computer Vision ({ICCV})}, title = {Online Clustered Codebook}, year = {2023} }
@inproceedings{karnewar23holofusion, author = {Animesh Karnewar and Andrea Vedaldi and Niloy Mitra and David Novotny}, booktitle = {Proceedings of the International Conference on Computer Vision ({ICCV})}, title = {HoloFusion: Towards Photo-realistic 3D Generative Modeling}, year = {2023} }
@inproceedings{tschernezki23epic, author = {Vadim Tschernezki and Ahmad Darkhalil and Zhifan Zhu and David Fouhey and Iro Laina and Diane Larlus and Dima Damen and Andrea Vedaldi}, booktitle = {Proceedings of Advances in Neural Information Processing Systems (NeurIPS): Track on Datasets and Benchmarks}, title = {{EPIC Fields}: Marrying {3D} Geometry and Video Understanding}, year = {2023} }
@inproceedings{shtedritski23what, author = {Aleksandar Shtedritski and Christian Rupprecht and Andrea Vedaldi}, booktitle = {Proceedings of the International Conference on Computer Vision ({ICCV})}, title = {What does {CLIP} know about a red circle? Visual prompt engineering for {VLMs}}, year = {2023} }
@inproceedings{singer23text-to-4d, author = {Uriel Singer and Shelly Sheynin and Adam Polyak and Oron Ashual and Iurii Makarov and Filippos Kokkinos and Naman Goyal and Andrea Vedaldi and Devi Parikh and Justin Johnson and Yaniv Taigman}, booktitle = {Proceedings of the International Conference on Machine Learning ({ICML})}, title = {Text-To-{4D} Dynamic Scene Generation}, year = {2023} }
@inproceedings{wimbauer23behind, author = {Felix Wimbauer and Nan Yang and Christian Rupprecht and Daniel Cremers}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {Behind the Scenes: Density Fields for Single View Reconstruction}, year = {2023} }
@inproceedings{chen23novel-view, author = {Changan Chen and Alexander Richard and Roman Shapovalov and Vamsi Ithapu and Natalia Neverova and Kristen Grauman and Andrea Vedaldi}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {Novel-view Acoustic Synthesis}, year = {2023} }
@inproceedings{karnewar23holo-diffusion, author = {Animesh Karnewar and Andrea Vedaldi and David Novotny and Niloy Mitra}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {{HoloDiffusion}: training a {3D} diffusion model using {2D} Images}, year = {2023} }
@inproceedings{karaev23dynamicstereo, author = {Nikita Karaev and Ignacio Rocco and Benjamin Graham and Natalia Neverova and Andrea Vedaldi and Christian Rupprecht}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {{DynamicStereo}: Consistent Dynamic Depth from Stereo Videos}, year = {2023} }
@inproceedings{sinha22common, author = {Samarth Sinha and Roman Shapovalov and Jeremy Reizenstein and Ignacio Rocco and Natalia Neverova and Andrea Vedaldi and David Novotn{\'{y}}}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {Common Pets in {3D}: Dynamic New-View Synthesis of Real-Life Deformable Categories}, year = {2023} }
@inproceedings{liu23continual, author = {Yaoyao Liu and Bernt Schiele and Andrea Vedaldi and Christian Rupprecht}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {Continual Detection Transformer for Incremental Object Detection}, year = {2023} }
@inproceedings{wu23magicpony, author = {Shangzhe Wu and Ruining Li and Tomas Jakab and Christian Rupprecht and Andrea Vedaldi}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {{MagicPony}: Learning Articulated {3D} Animals in the Wild}, year = {2023} }
@inproceedings{melas-kyriazi23pc2, author = {Luke Melas{-}Kyriazi and Christian Rupprecht and Andrea Vedaldi}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {{PC2}: Projection-Conditioned Point Cloud Diffusion for Single-Image 3D Reconstruction}, year = {2023} }
@inproceedings{melas-kyriazi23realfusion, author = {Luke Melas{-}Kyriazi and Christian Rupprecht and Iro Laina and Andrea Vedaldi}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {{RealFusion}: 360 Reconstruction of Any Object from a Single Image}, year = {2023} }
@article{rocco23real-time, author = {Ignacio Rocco and Iurii Makarov and Filippos Kokkinos and David Novotn{\'{y}} and Benjamin Graham and Natalia Neverova and Andrea Vedaldi}, journal = {arXiv preprint}, title = {Real-time volumetric rendering of dynamic humans}, volume = {abs/2303.11898}, year = {2023} }
@inproceedings{ji22test, author = {Xu Ji and Razvan Pascanu and R. Devon Hjelm and Balaji Lakshminarayanan and Andrea Vedaldi}, booktitle = {Proceedings of Conference on Lifelong Learning Agents (CoLLA)}, title = {Test Sample Accuracy Scales with Training Sample Density in Neural Networks}, year = {2022} }
@inproceedings{mccraith22lifting, author = {Robert McCraith and Eldar Insafutdinov and Luk{\'{a}}s Neumann and Andrea Vedaldi}, booktitle = {Proceedings of the {IEEE} Conference on Robotics and Automation ({ICRA})}, title = {Lifting {2D} Object Locations to {3D} by Discounting {LiDAR} Outliers across Objects and Views}, year = {2022} }
@inproceedings{brown22end-to-end, author = {Andrew Brown and Cheng{-}Yang Fu and Omkar M. Parkhi and Tamara L. Berg and Andrea Vedaldi}, booktitle = {Proceedings of the European Conference on Computer Vision ({ECCV})}, title = {End-to-End Visual Editing with a Generatively Pre-Trained Artist}, year = {2022} }
@inproceedings{insafutdinov22snes, author = {Eldar Insafutdinov and Dylan Campbell and Jo{\~{a}}o F. Henriques and Andrea Vedaldi}, booktitle = {Proceedings of the European Conference on Computer Vision ({ECCV})}, title = {{SNeS}: Learning Probably Symmetric Neural Surfaces from Incomplete Data}, year = {2022} }
@inproceedings{karazija22guess, author = {Laurynas Karazija and Subhabrata Choudhury and Iro Laina and Andrea Vedaldi and Christian Rupprecht}, booktitle = {Proceedings of the British Machine Vision Conference ({BMVC})}, title = {Guess What Moves: Unsupervised Video and Image Segmentation by Anticipating Motion}, year = {2022} }
@inproceedings{karazija22unsupervised, author = {Laurynas Karazija and Subhabrata Choudhury and Iro Laina and Christian Rupprecht and Andrea Vedaldi}, booktitle = {Proceedings of Advances in Neural Information Processing Systems (NeurIPS)}, title = {Unsupervised Multi-object Segmentation by Predicting Probable Motion Patterns}, year = {2022} }
@inproceedings{mccraith02direct, author = {Robert McCraith and Eldar Insafutdinov and Lukas Neumann and Andrea Vedaldi}, booktitle = {Proceedings of NeurIPS Machine Learning for the Developing World Workshop}, title = {Direct LiDAR-based object detector training from automated 2D detections}, year = {2022} }
@inproceedings{tschernezki22neural, author = {Vadim Tschernezki and Iro Laina and Diane Larlus and Andrea Vedaldi}, booktitle = {Proceedings of the International Conference on {3D} Vision (3DV)}, title = {{Neural Feature Fusion Fields}: {3D} Distillation of Self-Supervised {2D} Image Representation}, year = {2022} }
@inproceedings{yang22banmo, author = {Gengshan Yang and Minh Vo and Natalia Neverova and Deva Ramanan and Andrea Vedaldi and Hanbyul Joo}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {{BANMo}: Building Animatable 3D Neural Models from Many Casual Videos}, year = {2022} }(Media coverage)
@inproceedings{melas-kyriazi22deep, author = {Luke Melas-Kyriazi and Christian Rupprecht and Iro Laina and Andrea Vedaldi}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localization}, year = {2022} }
@inproceedings{melas-kyriazi22finding, author = {Luke Melas-Kyriazi and Christian Rupprecht and Iro Laina and Andrea Vedaldi}, booktitle = {Proceedings of the International Conference on Learning Representations ({ICLR})}, title = {Finding an Unsupervised Image Segmenter in each of your Deep Generative Models}, year = {2022} }
@inproceedings{vaze22generalized, author = {Sagar Vaze and Kai Han and Andrea Vedaldi and Andrew Zisserman}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {Generalized Category Discovery}, year = {2022} }
@inproceedings{novotny22keypoint, author = {David Novotny and Ignacio Rocco and Samrath Sinha and Alexandre Carlier and Gael Kerchenbaum and Roman Shapovalov and Nikita Smetanin and Natalia Neverova and Andrea Vedaldi}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {Keypoint Transporter for Reconstructing Non-rigid 3D Shapes in Videos}, year = {2022} }
@inproceedings{laina22measuring, author = {Iro Laina and Yuki M. Asano and Andrea Vedaldi}, booktitle = {Proceedings of the International Conference on Learning Representations ({ICLR})}, title = {Measuring the Interpretability of Unsupervised Representations via Quantized Reversed Probing}, year = {2022} }
@inproceedings{vaze22open-set, author = {Sagar Vaze and Kai Han and Andrea Vedaldi and Andrew Zisserman}, booktitle = {Proceedings of the International Conference on Learning Representations ({ICLR})}, title = {Open-Set Recognition: A Good Closed-Set Classifier is All You Need}, year = {2022} }
@inproceedings{afouras22self-supervised, author = {Triantafyllos Afouras and Yuki Asano and Francois Fagan and Andrea Vedaldi and Florian Metze}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {Self-supervised object detection from audio-visual correspondence}, year = {2022} }
@article{han21autonovel, author = {Kai Han and Sylvestre{-}Alvise Rebuffi and S{\'{e}}bastien Ehrhardt and Andrea Vedaldi and Andrew Zisserman}, journal = {{IEEE} Transactions on Pattern Analysis and Machine Intelligence}, title = {AutoNovel: Automatically Discovering and Learning Novel Visual Categories}, year = {2021} }
@inproceedings{chen21audio-visual, author = {Honglie Chen and Weidi Xie and Triantafyllos Afouras and Arsha Nagrani and Andrea Vedaldi and Andrew Zisserman}, booktitle = {Proceedings of the British Machine Vision Conference ({BMVC})}, title = {Audio-Visual Synchronisation in the Wild}, year = {2021} }
@inproceedings{choudhury21the-curious, author = {Subhabrata Choudhury and Iro Laina and Christian Rupprecht and Andrea Vedaldi}, booktitle = {Proceedings of the British Machine Vision Conference ({BMVC})}, title = {The Curious Layperson: Fine-Grained Image Recognition without Expert Labels}, year = {2021} }(Best student paper award)
@inproceedings{choudhury21unsupervised, author = {Subhabrata Choudhury and Iro Laina and Christian Rupprecht and Andrea Vedaldi}, booktitle = {Proceedings of Advances in Neural Information Processing Systems (NeurIPS)}, title = {Unsupervised Part Discovery from Contrastive Reconstruction}, year = {2021} }
@inproceedings{patrick21keeping, author = {Mandela Patrick and Dylan Campbell and Yuki Markus Asano and Ishan Misra and Florian Metze and Christoph Feichtenhofer and Andrea Vedaldi and Jo{\~{a}}o F. Henriques}, booktitle = {Proceedings of Advances in Neural Information Processing Systems (NeurIPS)}, title = {Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers}, year = {2021} }
@article{asano21pass:, author = {Yuki M. Asano and Christian Rupprecht and Andrew Zisserman and Andrea Vedaldi}, journal = {Proceedings of Advances in Neural Information Processing Systems (NeurIPS): Track on Datasets and Benchmarks}, title = {{PASS}: An {ImageNet} replacement for self-supervised pretraining without human}, year = {2021} }
@inproceedings{tschernezki21neuraldiff, author = {Vadim Tschernezki and Diane Larlus and Andrea Vedaldi}, booktitle = {Proceedings of the International Conference on {3D} Vision (3DV)}, title = {{NeuralDiff}: Segmenting {3D} objects that move in egocentric videos}, year = {2021} }
@inproceedings{xu21moving, author = {Dan Xu and Andrea Vedaldi and Jo{\~{a}}o F. Henriques}, booktitle = {Proc. IEEE Intl. Conf. on Intelligent Robots an Systems (IROS)}, title = {Moving {SLAM}: Fully Unsupervised Deep Learning in Non-Rigid Scenes}, year = {2021} }
@inproceedings{groth21goal-conditioned, author = {Oliver Groth and Chia-Man Hung and Andrea Vedaldi and Ingmar Posner}, booktitle = {Proceedings of the {IEEE} Conference on Robotics and Automation ({ICRA})}, title = {Goal-Conditioned End-to-End Visuomotor Control for Versatile Skill Primitives}, year = {2021} }
@inproceedings{mccraith21real, author = {Robert McCraith and Lukas Neumann and Andrea Vedaldi}, booktitle = {Proc. IEEE Intelligent Vehicles Symposium}, title = {Real Time Monocular Vehicle Velocity Estimation Using Synthetic Data}, year = {2021} }
@inproceedings{patrick21on-compositions, author = {Mandela Patrick and Yuki M. Asano and Polina Kuznetsova and Ruth Fong and Jo{\~{a}}o F. Henriques and Geoffrey Zweig and Andrea Vedaldi}, booktitle = {Proceedings of the International Conference on Computer Vision ({ICCV})}, title = {On Compositions of Transformations in Contrastive Self-Supervised Learning}, year = {2021} }
@inproceedings{patrick21space-time, author = {Mandela Patrick and Yuki M. Asano and Bernie Huang and Ishan Misra and Florian Metze and Jo{\~{a}}o F. Henriques and Andrea Vedaldi}, booktitle = {Proceedings of the International Conference on Computer Vision ({ICCV})}, title = {Space-time crop and Attend: Improving cross-modal video representation learning}, year = {2021} }
@inproceedings{shapovalov21densepose, author = {Roman Shapovalov and David Novotny and Benjamin Graham and Patrick Labatut and Andrea Vedaldi}, booktitle = {Proceedings of the International Conference on Computer Vision ({ICCV})}, title = {{DensePose} {3D}: Lifting Canonical Surface Maps of Articulated Objects to the Third Dimension}, year = {2021} }
@inproceedings{eisenberger21neuromorph, author = {Marvin Eisenberger and David Novotny and Gael Kerchenbaum and Patrick Labatut and Natalia Neverova and Daniel Cremers and Andrea Vedaldi}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {{NeuroMorph}: Unsupervised Shape Interpolation and Correspondence in One Go}, year = {2021} }
@inproceedings{henzler21unsupervised, author = {Philipp Henzler and Jeremy Reizenstein and Patrick Labatut and Shapovalov, Roman and Tobias Ritschel and Andrea Vedaldi and David Novotny}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {Unsupervised Learning of 3D Object Categories from Videos in the Wild}, year = {2021} }
@inproceedings{neverova21discovering, author = {Natalia Neverova and Artsiom Sanakoyeu and Patrick Labatut and David Novotny and Andrea Vedaldi}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {Discovering Relationships between Object Categories via Universal Canonical Maps}, year = {2021} }
@inproceedings{patrick21support-set, author = {Mandela Patrick and Po{-}Yao Huang and Yuki Markus Asano and Florian Metze and Alexander G. Hauptmann and Jo{\~{a}}o F. Henriques and Andrea Vedaldi}, booktitle = {iclr}, title = {Support-set bottlenecks for video-text representation learning}, year = {2021} }
@article{gong21optimising, author = {Weikang Gong and Christian F. Beckmann and Andrea Vedaldi and Stephen M. Smith and Han Peng}, journal = {Front. Psychiatry}, title = {Optimising a Simple Fully Convolutional Network (SFCN) for accurate brain age prediction in the PAC 2019 challenge}, volume = {12}, year = {2021} }
@inproceedings{ehrhardt20relate, author = {S{\'{e}}bastien Ehrhardt and Oliver Groth and Aron Monszpart and Martin Engelcke and Ingmar Posner and Niloy J. Mitra and Andrea Vedaldi}, booktitle = {Proceedings of Advances in Neural Information Processing Systems (NeurIPS)}, title = {{RELATE:} Physically Plausible Multi-Object Scene Synthesis Using Structured Latent Spaces}, year = {2020} }
@inproceedings{laina20quantifying, author = {Iro Laina and Ruth C. Fong and Andrea Vedaldi}, booktitle = {Proceedings of Advances in Neural Information Processing Systems (NeurIPS)}, title = {Quantifying Learnability and Describability of Visual Concepts Emerging in Representation Learning}, year = {2020} }
@inproceedings{asano20labelling, author = {Yuki M. Asano and Mandela Patrick and Christian Rupprecht and Andrea Vedaldi}, booktitle = {Proceedings of Advances in Neural Information Processing Systems (NeurIPS)}, title = {Labelling unlabelled videos from scratch with multi-modal self-supervision}, year = {2020} }
@inproceedings{biggs203d-multi-bodies, author = {Benjamin Biggs and Andrea Vedaldi and David Novotn{\'{y}}}, booktitle = {Proceedings of Advances in Neural Information Processing Systems (NeurIPS)}, title = {{3D} Multi-bodies: Fitting Sets of Plausible {3D} Human Models to Ambiguous Image Data}, year = {2020} }
@inproceedings{novotny20canonical, author = {David Novotn{\'{y}} and Roman Shapovalov and Andrea Vedaldi}, booktitle = {Proceedings of Advances in Neural Information Processing Systems (NeurIPS)}, title = {Canonical {3D} Deformer Maps: Unifying parametric and non-parametric methods for dense weakly-supervised category reconstruction}, year = {2020} }
@inproceedings{neverova20continuous, author = {Natalia Neverova and David Novotn{\'{y}} and Andrea Vedaldi}, booktitle = {Proceedings of Advances in Neural Information Processing Systems (NeurIPS)}, title = {Continuous Surface Embeddings}, year = {2020} }
@article{ulyanov20deep, author = {Dmitry Ulyanov and Andrea Vedaldi and Victor S. Lempitsky}, journal = {International Journal of Computer Vision ({IJCV})}, number = {7}, pages = {1867--1888}, title = {Deep Image Prior}, volume = {128}, year = {2020} }
@inproceedings{chen20vggsound, author = {Honglie Chen and Weidi Xie and Andrea Vedaldi and Andrew Zisserman}, booktitle = {International Conference on Acoustics, Speech, and Signal Processing (ICASS)}, title = {{VGGSound}: A Large-scale Audio-Visual Dataset}, year = {2020} }
@inproceedings{sanakoyeu20transferring, author = {Artsiom Sanakoyeu and Vasil Khalidov and Maureen S. McCarthy and Andrea Vedaldi and Natalia Neverova}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {Transferring Dense Pose to Proximal Animal Classes}, year = {2020} }
@inproceedings{jakab20self-supervised, author = {Tomas Jakab and Ankush Gupta and Hakan Bilen and Andrea Vedaldi}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {Self-supervised Learning of Interpretable Keypoints from Unlabelled Videos}, year = {2020} }
@inproceedings{wu20unsupervised, author = {Shangzhe Wu and Christian Rupprecht and Andrea Vedaldi}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {Unsupervised Learning of Probably Symmetric Deformable {3D} Objects from Images in the Wild}, year = {2020} }(Best paper award)
@inproceedings{rebuffi20there, author = {Sylvestre-Alvise Rebuffi and Ruth C. Fong and Xu Ji and Andrea Vedaldi}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {There and Back Again: Revisiting Backpropagation Saliency Methods}, year = {2020} }
@inproceedings{han20automatically, author = {Kai Han and Sylvestre-Alvise Rebuffi and Sebastien Ehrhardt and Andrea Vedaldi and Andrew Zisserman}, booktitle = {Proceedings of the International Conference on Learning Representations ({ICLR})}, title = {Automatically Discovering and Learning New Visual Categories with Ranking Statistics}, year = {2020} }
@inproceedings{asano20a-critical, author = {Yuki M. Asano and Christian Rupprecht and Andrea Vedaldi}, booktitle = {Proceedings of the International Conference on Learning Representations ({ICLR})}, title = {A critical analysis of self-supervision, or what we can learn from a single image}, year = {2020} }
@inproceedings{asano20self-labelling, author = {Yuki M. Asano and Christian Rupprecht and Andrea Vedaldi}, booktitle = {Proceedings of the International Conference on Learning Representations ({ICLR})}, title = {Self-labelling via simultaneous clustering and representation learning}, year = {2020} }
@inproceedings{neumann19future, author = {Luk{\'{a}}s Neumann and Andrew Zisserman and Andrea Vedaldi}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition Workshops ({CVPRW})}, title = {Future Event Prediction: If and When}, year = {2019} }
@book{19explainable, editor = {Wojciech Samek and Gr{\'{e}}goire Montavon and Andrea Vedaldi and Lars Kai Hansen and Klaus{-}Robert M{\"{u}}ller}, publisher = {Springer}, title = {Explainable {AI:} Interpreting, Explaining and Visualizing Deep Learning}, year = {2019} }
@inproceedings{touvron19fixing, author = {Hugo Touvron and Andrea Vedaldi and Matthijs Douze and Herv{\'{e}} J{\'{e}}gou}, booktitle = {Proceedings of Advances in Neural Information Processing Systems (NeurIPS)}, title = {Fixing the train-test resolution discrepancy}, year = {2019} }
@inproceedings{chen19autocorrect, author = {Honglie Chen and Weidi Xie and Andrea Vedaldi and Andrew Zisserman}, booktitle = {Proceedings of the British Machine Vision Conference ({BMVC})}, title = {{AutoCorrect}: Deep Inductive Alignment of Noisy Geometric Annotations}, year = {2019} }
@inproceedings{fuchs19scrutinizing, author = {Fabian B. Fuchs and Oliver Groth and Adam R. Kosiorek and Alex Bewley and Markus Wulfmeier and Andrea Vedaldi and Ingmar Posner}, booktitle = {Proceedings of the British Machine Vision Conference ({BMVC})}, title = {Scrutinizing and De-Biasing Intuitive Physics with Neural Stethoscopes}, year = {2019} }
@inproceedings{novotny19c3dpo, author = {David Novotn{\'{y}} and Nikhila Ravi and Benjamin Graham and Natalia Neverova and Andrea Vedaldi}, booktitle = {Proceedings of the International Conference on Computer Vision ({ICCV})}, title = {{C3DPO}: Canonical 3D Pose Networks for Non-Rigid Structure From Motion}, year = {2019} }
@inproceedings{henriques19small, author = {Jo{\~{a}}o F. Henriques and S{\'{e}}bastien Ehrhardt and Samuel Albanie and Andrea Vedaldi}, booktitle = {Proceedings of the International Conference on Computer Vision ({ICCV})}, title = {Small step and giant leaps: Minimal {Netwon} solvers for Deep Learning}, year = {2019} }
@inproceedings{thewlis19unsupervised, author = {James Thewlis and Samuel Albanie and Hakan Bilen and Andrea Vedaldi}, booktitle = {Proceedings of the International Conference on Computer Vision ({ICCV})}, title = {Unsupervised learning of landmarks by descriptor vector exchange}, year = {2019} }
@inproceedings{fong19understanding, author = {Ruth Fong and Mandela Patrick and Andrea Vedaldi}, booktitle = {Proceedings of the International Conference on Computer Vision ({ICCV})}, title = {Understanding Deep Networks via Extremal Perturbations and Smooth Masks}, year = {2019} }
@inproceedings{ji19invariant, author = {Xu Ji and Jo{\~{a}}o F. Henriques and Andrea Vedaldi}, booktitle = {Proceedings of the International Conference on Computer Vision ({ICCV})}, title = {Invariant Information Clustering for Unsupervised Image Classification and Segmentation}, year = {2019} }
@inproceedings{han19learning, author = {Kai Han and Andrea Vedaldi and Andrew Zisserman}, booktitle = {Proceedings of the International Conference on Computer Vision ({ICCV})}, title = {Learning to Discover Novel Visual Categories via Deep Transfer Clustering}, year = {2019} }
@article{balntas19hpatches, author = {Vassileios Balntas and Karel Lenc and Andrea Vedaldi and Tinne Tuytelaars and Jiri Matas and Krystian Mikolajczyk}, journal = {{IEEE} Transactions on Pattern Analysis and Machine Intelligence}, title = {{HPatches}: A benchmark and evaluation of handcrafted and learned local descriptors}, year = {2019} }
@article{ehrhardt19taking, author = {S{\'{e}}bastien Ehrhardt and Aron Monszpart and Niloy J. Mitra and Andrea Vedaldi}, journal = {Computer Vision and Image Understanding}, title = {Taking visual motion prediction to new heightfields}, year = {2019} }
@inproceedings{bertinetto19meta-learning, author = {Luca Bertinetto and Jo{\~{a}}o F. Henriques and Philip H. S. Torr and Andrea Vedaldi}, booktitle = {Proceedings of the International Conference on Learning Representations ({ICLR})}, title = {Meta-learning with differentiable closed-form solvers}, year = {2019} }
@inproceedings{neverova19slim, author = {Natalia Neverova and James Thewlis and Riza Alp G{\"{u}}ler and Iasonas Kokkinos and Andrea Vedaldi}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {Slim {DensePose}: Thrifty Learning From Sparse Annotations and Motion Cues}, year = {2019} }
@article{lenc18understanding, author = {Karel Lenc and Andrea Vedaldi}, journal = {International Journal of Computer Vision ({IJCV})}, number = {5}, title = {Understanding Image Representations by Measuring Their Equivariance and Equivalence}, volume = {127}, year = {2019} }
@inproceedings{neumann18relaxed, author = {Luk{\'{a}}s Neumann and Andrew Zisserman and Andrea Vedaldi}, booktitle = {{NeurIPS} Workshop on Machine Learning for Intelligent Transportation Systems}, title = {Relaxed Softmax: Efficient Confidence Auto-Calibration for Safe Pedestrian Detection}, year = {2018} }
@inproceedings{gupta18learning, author = {Ankush Gupta and Andrea Vedaldi and Andrew Zisserman}, booktitle = {Proceedings of the {Indian Conference on Computer Vision, Graphics and Image Processing}}, title = {Learning to read by spelling: Towards unsupervised text recognition}, year = {2018} }
@article{novotny18capturing, author = {David Novotn{\'{y}} and Diane Larlus and Andrea Vedaldi}, journal = {{IEEE} Transactions on Pattern Analysis and Machine Intelligence}, title = {Capturing the Geometry of Object Categories from Video Supervision}, year = {2018} }
@inproceedings{ehrhardt18unsupervised, author = {S{\'{e}}bastien Ehrhardt and Aron Monszpart and Niloy J. Mitra and Andrea Vedaldi}, booktitle = {Proceedings of the {Asian Conference on Computer Vision} ({ACCV})}, title = {Unsupervised Intuitive Physics from Visual Observations}, year = {2018} }
@inproceedings{neumann18nightowls, author = {Luk{\'{a}}s Neumann and Michelle Karg and Shanshan Zhang and Christian Scharfenberger and Eric Piegert and Sarah Mistr and Olga Prokofyeva and Robert Thiel and Andrea Vedaldi and Andrew Zisserman and Bernt Schiele}, booktitle = {Proceedings of the {Asian Conference on Computer Vision} ({ACCV})}, title = {{NightOwls}: {A} Pedestrians at Night Dataset}, year = {2018} }
@inproceedings{neumann18tiny, author = {Luk{\'{a}}s Neumann and Andrea Vedaldi}, booktitle = {Proceedings of the {Asian Conference on Computer Vision} ({ACCV})}, title = {Tiny People Pose}, year = {2018} }
@inproceedings{mahendran18cross, author = {Aravindh Mahendran and James Thewlis and Andrea Vedaldi}, booktitle = {Proceedings of the {Asian Conference on Computer Vision} ({ACCV})}, title = {Cross Pixel Optical-Flow Similarity for Self-supervised Learning}, year = {2018} }(oral presentation)
@inproceedings{albanie18emotion, author = {Samuel Albanie and Arsha Nagrani and Andrea Vedaldi and Andrew Zisserman}, booktitle = {Proceedings of the 26th annual {ACM} international conference on Multimedia}, title = {Emotion Recognition in Speech using Cross-Modal Transfer in the Wild}, year = {2018} }
@inproceedings{jakab18unsupervised, author = {Tomas Jakab and Ankush Gupta and Hakan Bilen and Andrea Vedaldi}, booktitle = {Proceedings of Advances in Neural Information Processing Systems (NeurIPS)}, title = {Unsupervised Learning of Object Landmarks through Conditional Image Generation}, year = {2018} }
@inproceedings{thewlis18modelling, author = {James Thewlis and Hakan Bilen and Andrea Vedaldi}, booktitle = {Proceedings of Advances in Neural Information Processing Systems (NeurIPS)}, title = {Modelling and unsupervised learning of symmetric deformable object categories}, year = {2018} }
@inproceedings{hu18gather, author = {Jie Hu and Li Shen and Samuel Albanie and Gang Sun and Andrea Vedaldi}, booktitle = {Proceedings of Advances in Neural Information Processing Systems (NeurIPS)}, title = {Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks}, year = {2018} }
@inproceedings{gupta18inductive, author = {Ankush Gupta and Andrea Vedaldi and Andrew Zisserman}, booktitle = {Proceedings of the British Machine Vision Conference ({BMVC})}, title = {Inductive Visual Localisation: Factorised Training for Superior Generalisation}, year = {2018} }
@inproceedings{valmadre18long-term, author = {Jack Valmadre and Luca Bertinetto and Jo{\~{a}}o F. Henriques and Ran Tao and Andrea Vedaldi and Arnold W. M. Smeulders and Philip H. S. Torr and Efstratios Gavves}, booktitle = {Proceedings of the European Conference on Computer Vision ({ECCV})}, title = {Long-Term Tracking in the Wild: {A} Benchmark}, year = {2018} }
@inproceedings{klodt18supervising, author = {Maria Klodt and Andrea Vedaldi}, booktitle = {Proceedings of the European Conference on Computer Vision ({ECCV})}, title = {Supervising the New with the Old: Learning {SFM} from {SFM}}, year = {2018} }
@inproceedings{lenc18large, author = {Karel Lenc and Andrea Vedaldi}, booktitle = {Proceedings of the British Machine Vision Conference ({BMVC})}, title = {Large scale evaluation of local image feature detectors on homography datasets}, year = {2018} }
@inproceedings{groth18shapestacks, author = {Oliver Groth and Fabian B. Fuchs and Ingmar Posner and Andrea Vedaldi}, booktitle = {Proceedings of the European Conference on Computer Vision ({ECCV})}, title = {{ShapeStacks}: Learning Vision-Based Physical Intuition for Generalised Object Stacking}, year = {2018} }
@inproceedings{novotny18semi-convolutional, author = {David Novotn{\'{y}} and Samuel Albanie and Diane Larlus and Andrea Vedaldi}, booktitle = {Proceedings of the European Conference on Computer Vision ({ECCV})}, title = {Semi-convolutional Operators for Instance Segmentation}, year = {2018} }
@inproceedings{fong18net2vec, author = {Ruth Fong and Andrea Vedaldi}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {{Net2Vec}: Quantifying and Explaining How Concepts Are Encoded by Filters in Deep Neural Networks}, year = {2018} }
@inproceedings{henriques18mapnet, author = {Jo{\~{a}}o F. Henriques and Andrea Vedaldi}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {{MapNet}: An Allocentric Spatial Memory for Mapping Environments}, year = {2018} }
@inproceedings{rebuffi18efficient, author = {Sylvestre{-}Alvise Rebuffi and Hakan Bilen and Andrea Vedaldi}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {Efficient Parametrization of Multi-Domain Deep Neural Networks}, year = {2018} }
@inproceedings{novotny18self-supervised, author = {David Novotn{\'{y}} and Samuel Albanie and Diane Larlus and Andrea Vedaldi}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {Self-Supervised Learning of Geometrically Stable Features Through Probabilistic Introspection}, year = {2018} }
@inproceedings{ulyanov18deep, author = {Dmitry Ulyanov and Andrea Vedaldi and Victor S. Lempitsky}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {Deep Image Prior}, year = {2018} }
@inproceedings{ulyanov18takes, author = {Dmitry Ulyanov and Andrea Vedaldi and Victor S. Lempitsky}, booktitle = {Proceedings of the Association for the Advancement of Artificial Intelligence ({AAAI})}, title = {It Takes {(Only)} Two: Adversarial Generator-Encoder Networks}, year = {2018} }
@article{bilen18action, author = {Hakan Bilen and Basura Fernando and Efstratios Gavves and Andrea Vedaldi}, journal = {{IEEE} Transactions on Pattern Analysis and Machine Intelligence}, number = {12}, title = {Action Recognition with Dynamic Image Networks}, volume = {40}, year = {2018} }
@incollection{novotny17generalizing, author = {David Novotn{\'{y}} and Diane Larlus and Andrea Vedaldi}, booktitle = {Domain Adaptation in Computer Vision Applications}, pages = {259--273}, publisher = {Springer, Cham}, title = {Generalizing Semantic Part Detectors Across Domains}, year = {2017} }
@inproceedings{thewlis17dense, author = {James Thewlis and Hakan Bilen and Andrea Vedaldi}, booktitle = {Proceedings of Advances in Neural Information Processing Systems (NeurIPS)}, title = {Unsupervised learning of object frames by dense equivariant image labelling}, year = {2017} }(oral presentation)
@inproceedings{rebuffi17learning, author = {Sylvestre{-}Alvise Rebuffi and Hakan Bilen and Andrea Vedaldi}, booktitle = {Proceedings of Advances in Neural Information Processing Systems (NeurIPS)}, title = {Learning multiple visual domains with residual adapters}, year = {2017} }
@inproceedings{novotny17learning, author = {David Novotn{\'{y}} and Diane Larlus and Andrea Vedaldi}, booktitle = {Proceedings of the International Conference on Computer Vision ({ICCV})}, title = {Learning {3D} Object Categories by Looking Around Them}, year = {2017} }(oral presentation)
@inproceedings{fong17interpretable, author = {Ruth C. Fong and Andrea Vedaldi}, booktitle = {Proceedings of the International Conference on Computer Vision ({ICCV})}, title = {Interpretable Explanations of Black Boxes by Meaningful Perturbation}, year = {2017} }
@inproceedings{thewlis17unsupervised, author = {James Thewlis and Hakan Bilen and Andrea Vedaldi}, booktitle = {Proceedings of the International Conference on Computer Vision ({ICCV})}, title = {Unsupervised Learning of Object Landmarks by Factorized Spatial Embeddings}, year = {2017} }(oral presentation)
@inproceedings{henriques17warped, author = {Jo{\~{a}}o F. Henriques and Andrea Vedaldi}, booktitle = {Proceedings of the International Conference on Machine Learning ({ICML})}, title = {Warped Convolutions: Efficient Invariance to Spatial Transformations}, year = {2017} }
@inproceedings{bertinetto17end-to-end, author = {Jack Valmadre and Luca Bertinetto and Jo{\~{a}}o F. Henriques and Andrea Vedaldi and Philip H. S. Torr}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {End-to-End Representation Learning for Correlation Filter Based Tracking}, year = {2017} }
@inproceedings{ulyanov17improved, author = {Dmitry Ulyanov and Andrea Vedaldi and Victor S. Lempitsky}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {Improved Texture Networks: Maximizing Quality and Diversity in Feed-Forward Stylization and Texture Synthesis}, year = {2017} }
@inproceedings{novotny17anchornet, author = {David Novotn{\'{y}} and Diane Larlus and Andrea Vedaldi}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {{AnchorNet}: {A} Weakly Supervised Network to Learn Geometry-Sensitive Features for Semantic Matching}, year = {2017} }
@inproceedings{balntas17hpatch, author = {Vassileios Balntas and Karel Lenc and Andrea Vedaldi and Krystian Mikolajczyk}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {{HPatches}: {A} Benchmark and Evaluation of Handcrafted and Learned Local Descriptors}, year = {2017} }
@inproceedings{bertinetto16fully, author = {Luca Bertinetto and Jack Valmadre and Jo{\~{a}}o F. Henriques and Andrea Vedaldi and Philip H. S. Torr}, booktitle = {{ECCV} Workshop on Computer Vision on Visual Object Tracking}, title = {Fully-Convolutional Siamese Networks for Object Tracking}, year = {2016} }
@inproceedings{lenc16learning, author = {Karel Lenc and Andrea Vedaldi}, booktitle = {Proceedings of the {ECCV} workshop on {Geometry Meets Deep Learning}}, title = {Learning Covariant Feature Detectors}, year = {2016} }
@inproceedings{novotny16learning, author = {David Novotn{\'{y}} and Diane Larlus and Andrea Vedaldi}, booktitle = {Proceedings of the {ECCV} workshop on {Geometry Meets Deep Learning}}, title = {Learning the semantic structure of objects from Web supervision}, year = {2016} }
@inproceedings{bertinetto16learning, author = {Luca Bertinetto and Jo{\~{a}}o F. Henriques and Jack Valmadre and Philip H. S. Torr and Andrea Vedaldi}, booktitle = {Proceedings of Advances in Neural Information Processing Systems (NeurIPS)}, title = {Learning feed-forward one-shot learners}, year = {2016} }
@inproceedings{bilen16integrated, author = {Hakan Bilen and Andrea Vedaldi}, booktitle = {Proceedings of Advances in Neural Information Processing Systems (NeurIPS)}, title = {Integrated perception with recurrent multi-task neural networks}, year = {2016} }
@inproceedings{mahendran16salient, author = {Aravindh Mahendran and Andrea Vedaldi}, booktitle = {Proceedings of the European Conference on Computer Vision ({ECCV})}, title = {Salient Deconvolutional Networks}, year = {2016} }
@inproceedings{novotny16i-have, author = {David Novotn{\'{y}} and Diane Larlus and Andrea Vedaldi}, booktitle = {Proceedings of the British Machine Vision Conference ({BMVC})}, title = {I Have Seen Enough: Transferring Parts Across Categories}, year = {2016} }
@inproceedings{thewlis16fully-trainable, author = {James Thewlis and Shuai Zheng and Philip H. S. Torr and Andrea Vedaldi}, booktitle = {Proceedings of the British Machine Vision Conference ({BMVC})}, title = {Fully-trainable deep matching}, year = {2016} }(oral presentation)
@inproceedings{albanie16learning, author = {Samuel Albanie and Andrea Vedaldi}, booktitle = {Proceedings of the British Machine Vision Conference ({BMVC})}, title = {Learning Grimaces by Watching {TV}}, year = {2016} }
@article{mahendran16visualizing, author = {Aravindh Mahendran and Andrea Vedaldi}, journal = {International Journal of Computer Vision ({IJCV})}, number = {3}, title = {Visualizing Deep Convolutional Neural Networks Using Natural Pre-images}, volume = {120}, year = {2016} }
@inproceedings{ulyanov16texture, author = {Dmitry Ulyanov and Vadim Lebedev and Andrea Vedaldi and Victor S. Lempitsky}, booktitle = {Proceedings of the International Conference on Machine Learning ({ICML})}, title = {Texture Networks: Feed-forward Synthesis of Textures and Stylized Images}, year = {2016} }
@inproceedings{gupta16synthetic, author = {Ankush Gupta and Andrea Vedaldi and Andrew Zisserman}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {Synthetic Data for Text Localisation in Natural Images}, year = {2016} }
@inproceedings{bilen16dynamic, author = {Hakan Bilen and Basura Fernando and Efstratios Gavves and Andrea Vedaldi and Stephen Gould}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {Dynamic Image Networks for Action Recognition}, year = {2016} }(oral presentation)
@inproceedings{bilen16weakly, author = {Hakan Bilen and Andrea Vedaldi}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {Weakly Supervised Deep Detection Networks}, year = {2016} }
@article{cimpoi16deep, author = {Mircea Cimpoi and Subhransu Maji and Iasonas Kokkinos and Andrea Vedaldi}, journal = {International Journal of Computer Vision ({IJCV})}, number = {1}, title = {Deep Filter Banks for Texture Recognition, Description, and Segmentation}, volume = {118}, year = {2016} }
@article{jaderberg15reading, author = {Max Jaderberg and Karen Simonyan and Andrea Vedaldi and Andrew Zisserman}, journal = {International Journal of Computer Vision ({IJCV})}, number = {1}, title = {Reading Text in the Wild with Convolutional Neural Networks}, volume = {116}, year = {2016} }
@article{gonfaus15factorized, author = {Josep M. Gonfaus and Marco Pedersoli and Jordi Gonz{\`{a}}lez and Andrea Vedaldi and F. Xavier Roca}, journal = {Computer Vision and Image Understanding}, pages = {92--101}, title = {Factorized appearances for object detection}, volume = {138}, year = {2015} }
@inproceedings{parkhi15deep, author = {Omkar M. Parkhi and Andrea Vedaldi and Andrew Zisserman}, booktitle = {Proceedings of the British Machine Vision Conference ({BMVC})}, title = {Deep Face Recognition}, year = {2015} }
@inproceedings{vedaldi15matconvnet, author = {Andrea Vedaldi and Karel Lenc}, booktitle = {Proceedings of the 25th annual {ACM} international conference on Multimedia}, title = {{MatConvNet}: Convolutional Neural Networks for {MATLAB}}, year = {2015} }
@inproceedings{lenc15rcnn, author = {Karel Lenc and Andrea Vedaldi}, booktitle = {Proceedings of the British Machine Vision Conference ({BMVC})}, title = {{R-CNN} minus {R}}, year = {2015} }(oral presentation)
@inproceedings{parizi15automatic, author = {Sobhan Naderi Parizi and Andrea Vedaldi and Andrew Zisserman and Pedro F. Felzenszwalb}, booktitle = {Proceedings of the International Conference on Learning Representations ({ICLR})}, title = {Automatic Discovery and Optimization of Parts for Image Classification}, year = {2015} }
@inproceedings{cimpoi15deep, author = {Mircea Cimpoi and Subhransu Maji and Andrea Vedaldi}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {Deep filter banks for texture recognition and segmentation}, year = {2015} }(oral presentation)
@inproceedings{lenc15understanding, author = {Karel Lenc and Andrea Vedaldi}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {Understanding image representations by measuring their equivariance and equivalence}, year = {2015} }(oral presentation)
@inproceedings{mahendran15understanding, author = {Aravindh Mahendran and Andrea Vedaldi}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {Understanding deep image representations by inverting them}, year = {2015} }(oral presentation)
@article{pedersoli14coarse, author = {Marco Pedersoli and Andrea Vedaldi and Jordi Gonz{\`{a}}lez and F. Xavier Roca}, journal = {Pattern Recognition}, title = {A coarse-to-fine approach for fast deformable object detection}, year = {2014} }
@inproceedings{jaderberg14synthetic, author = {M. Jaderberg and K. Simonyan and Andrea Vedaldi and A. Zisserman}, booktitle = {{NeurIPS} Deep Learning Workshop}, title = {Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition}, year = {2014} }
@inproceedings{jaderberg14deep, author = {Max Jaderberg and Andrea Vedaldi and Andrew Zisserman}, booktitle = {Proceedings of the European Conference on Computer Vision ({ECCV})}, title = {Deep Features for Text Spotting}, year = {2014} }
@inproceedings{chatfield14return, author = {Ken Chatfield and Karen Simonyan and Andrea Vedaldi and Andrew Zisserman}, booktitle = {Proceedings of the British Machine Vision Conference ({BMVC})}, title = {Return of the Devil in the Details: Delving Deep into Convolutional Nets}, year = {2014} }(best paper award, oral presentation)
@inproceedings{jaderberg14speeding, author = {Max Jaderberg and Andrea Vedaldi and Andrew Zisserman}, booktitle = {Proceedings of the British Machine Vision Conference ({BMVC})}, title = {Speeding up Convolutional Neural Networks with Low Rank Expansions}, year = {2014} }
@inproceedings{vedaldi14understanding, author = {Andrea Vedaldi and Siddharth Mahendran and Stavros Tsogkas and Subhransu Maji and Ross B. Girshick and Juho Kannala and Esa Rahtu and Iasonas Kokkinos and Matthew B. Blaschko and David J. Weiss and Ben Taskar and Karen Simonyan and Naomi Saphra and Sammy Mohamed}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {Understanding Objects in Detail with Fine-Grained Attributes}, year = {2014} }
@inproceedings{cimpoi14describing, author = {Mircea Cimpoi and Subhransu Maji and Iasonas Kokkinos and Sammy Mohamed and Andrea Vedaldi}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {Describing Textures in the Wild}, year = {2014} }
@inproceedings{parkhi14compact, author = {Omkar M. Parkhi and Karen Simonyan and Andrea Vedaldi and Andrew Zisserman}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {A Compact and Discriminative Face Track Descriptor}, year = {2014} }(oral presentation)
@inproceedings{simonyan14deep, author = {Karen Simonyan and Andrea Vedaldi and Andrew Zisserman}, booktitle = {Proceedings of the International Conference on Learning Representations ({ICLR})}, title = {Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps}, year = {2014} }
@article{simonyan14learning, author = {Karen Simonyan and Andrea Vedaldi and Andrew Zisserman}, journal = {{IEEE} Transactions on Pattern Analysis and Machine Intelligence}, number = {8}, title = {Learning Local Feature Descriptors Using Convex Optimisation}, volume = {36}, year = {2014} }
@inproceedings{simonyan13deep, author = {Karen Simonyan and Andrea Vedaldi and Andrew Zisserman}, booktitle = {Proceedings of Advances in Neural Information Processing Systems (NeurIPS)}, title = {Deep Fisher Networks for Large-Scale Image Classification}, year = {2013} }(NeurIPS spotlight)
@inproceedings{simonyan13fisher, author = {Karen Simonyan and Omkar M. Parkhi and Andrea Vedaldi and Andrew Zisserman}, booktitle = {Proceedings of the British Machine Vision Conference ({BMVC})}, title = {Fisher Vector Faces in the Wild}, year = {2013} }(oral presentation)
@inproceedings{juneja13blocks, author = {Mayank Juneja and Andrea Vedaldi and C. V. Jawahar and Andrew Zisserman}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {Blocks That Shout: Distinctive Parts for Scene Classification}, year = {2013} }
@inproceedings{vedaldi12self, author = {Andrea Vedaldi and Andrew Zisserman}, booktitle = {Proceedings of the European Conference on Computer Vision ({ECCV})}, title = {Self-similar Sketch}, year = {2012} }
@inproceedings{simonyan12descriptor, author = {Karen Simonyan and Andrea Vedaldi and Andrew Zisserman}, booktitle = {Proceedings of the European Conference on Computer Vision ({ECCV})}, title = {Descriptor Learning Using Convex Optimisation}, year = {2012} }
@inproceedings{parkhi12spotting, author = {Omkar M. Parkhi and Andrea Vedaldi and Andrew Zisserman}, booktitle = {Proceedings of the Int. Workshop on Image Analysis for Multimedia Interactive Services}, title = {On-the-fly specific person retrieval}, year = {2012} }
@inproceedings{vedaldi12sparse, author = {Andrea Vedaldi and Andrew Zisserman}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {Sparse kernel approximations for efficient classification and detection}, year = {2012} }
@inproceedings{parkhi12cat, author = {Omkar M. Parkhi and Andrea Vedaldi and Andrew Zisserman and C. V. Jawahar}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {Cats and dogs}, year = {2012} }
@article{vedaldi11efficient, author = {Andrea Vedaldi and Andrew Zisserman}, journal = {{IEEE} Transactions on Pattern Analysis and Machine Intelligence}, number = {3}, title = {Efficient Additive Kernels via Explicit Feature Maps}, volume = {34}, year = {2012} }
@inproceedings{lempitsky11pylon, author = {Victor S. Lempitsky and Andrea Vedaldi and Andrew Zisserman}, booktitle = {Proceedings of Advances in Neural Information Processing Systems (NeurIPS)}, title = {Pylon Model for Semantic Segmentation}, year = {2011} }
@inproceedings{chatfield11devil, author = {Ken Chatfield and Victor S. Lempitsky and Andrea Vedaldi and Andrew Zisserman}, booktitle = {Proceedings of the British Machine Vision Conference ({BMVC})}, title = {The devil is in the details: an evaluation of recent feature encoding methods}, year = {2011} }
@inproceedings{parkhi11truth, author = {Omkar M. Parkhi and Andrea Vedaldi and C. V. Jawahar and Andrew Zisserman}, booktitle = {Proceedings of the International Conference on Computer Vision ({ICCV})}, title = {The truth about cats and dogs}, year = {2011} }
@inproceedings{vedaldi11learning, author = {Andrea Vedaldi and Matthew B. Blaschko and Andrew Zisserman}, booktitle = {Proceedings of the International Conference on Computer Vision ({ICCV})}, title = {Learning equivariant structured output {SVM} regressors}, year = {2011} }
@inproceedings{pedersoli11coarse, author = {Marco Pedersoli and Andrea Vedaldi and Jordi Gonz{\`{a}}lez}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {A coarse-to-fine approach for fast deformable object detection}, year = {2011} }(oral presentation)
@incollection{vedaldi10knowing, author = {Andrea Vedaldi and Haibin Ling and Stefano Soatto}, booktitle = {Computer Vision: Detection, Recognition and Reconstruction}, pages = {27-49}, publisher = {Springer}, title = {Knowing a Good Feature When You See It: Ground Truth and Methodology to Evaluate Local Features for Recognition}, volume = {285}, year = {2010} }
@inproceedings{vedaldi10vlfeat, author = {Andrea Vedaldi and Brian Fulkerson}, booktitle = {Proceedings of the 18th annual {ACM} international conference on Multimedia}, title = {{VLFeat}: an open and portable library of computer vision algorithms}, year = {2010} }(Winner of the ACM Open Source Software Competition 2010)
@inproceedings{blaschko10simultaneous, author = {Matthew B. Blaschko and Andrea Vedaldi and Andrew Zisserman}, booktitle = {Proceedings of Advances in Neural Information Processing Systems (NeurIPS)}, title = {Simultaneous Object Detection and Ranking with Weak Supervision}, year = {2010} }
@inproceedings{vempati10generalized, author = {Sreekanth Vempati and Andrea Vedaldi and Andrew Zisserman and C. V. Jawahar}, booktitle = {Proceedings of the British Machine Vision Conference ({BMVC})}, title = {Generalized {RBF} feature maps for Efficient Detection}, year = {2010} }
@inproceedings{vedaldi10efficient, author = {Andrea Vedaldi and Andrew Zisserman}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {Efficient additive kernels via explicit feature maps}, year = {2010} }
@inproceedings{vedaldi09structured, author = {Andrea Vedaldi and A. Zisserman}, booktitle = {Proceedings of Advances in Neural Information Processing Systems (NeurIPS)}, title = {Structured output regression for detection with partial occulsion}, year = {2009} }
@inproceedings{vedaldi09multiple, author = {Andrea Vedaldi and Varun Gulshan and Manik Varma and Andrew Zisserman}, booktitle = {Proceedings of the International Conference on Computer Vision ({ICCV})}, title = {Multiple kernels for object detection}, year = {2009} }(Winner of the PASCAL Visual Object Classification challenge 2009)
@inproceedings{fulkerson09class, author = {Brian Fulkerson and Andrea Vedaldi and Stefano Soatto}, booktitle = {Proceedings of the International Conference on Computer Vision ({ICCV})}, title = {Class segmentation and object localization with superpixel neighborhoods}, year = {2009} }
@inproceedings{fulkerson08localizing, author = {Brian Fulkerson and Andrea Vedaldi and Stefano Soatto}, booktitle = {Proceedings of the European Conference on Computer Vision ({ECCV})}, title = {Localizing Objects with Smart Dictionaries}, year = {2008} }
@inproceedings{vedaldi08quick, author = {Andrea Vedaldi and Stefano Soatto}, booktitle = {Proceedings of the European Conference on Computer Vision ({ECCV})}, title = {Quick Shift and Kernel Methods for Mode Seeking}, year = {2008} }
@inproceedings{vedaldi08relaxed, author = {Andrea Vedaldi and Stefano Soatto}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {Relaxed Matching Kernels for Object Recognition}, year = {2008} }
@inproceedings{vedaldi08joint, author = {Andrea Vedaldi and Gregorio Guidi and Stefano Soatto}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {Joint data alignment up to (lossy) transformations}, year = {2008} }
@phdthesis{vedaldi08invariant, author = {Andrea Vedaldi}, school = {University of California at Los Angeles}, title = {Invariant Representations and Learning for Computer Vision}, year = {2008} }
@inproceedings{rabinovich07objects, author = {Andrew Rabinovich and Andrea Vedaldi and Carolina Galleguillos and Eric Wiewiora and Serge J. Belongie}, booktitle = {Proceedings of the International Conference on Computer Vision ({ICCV})}, title = {Objects in Context}, year = {2007} }(oral presentation)
@inproceedings{vedaldi07boosting, author = {Andrea Vedaldi and Paolo Favaro and Enrico Grisan}, booktitle = {Proceedings of the International Conference on Computer Vision ({ICCV})}, title = {Boosting Invariance and Efficiency in Supervised Learning}, year = {2007} }(oral presentation)
@inproceedings{vedaldi07moving, author = {Andrea Vedaldi and Gregorio Guidi and Stefano Soatto}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {Moving Forward in Structure From Motion}, year = {2007} }
@inproceedings{jones07inertial, author = {Eagle Jones and Andrea Vedaldi and Stefano Soatto}, booktitle = {Proceedings of {ICCV} Workshop on Dynamical Vision}, title = {Inertial structure from motion with autocalibration}, year = {2007} }
@inproceedings{vedaldi07complexity, author = {Andrea Vedaldi and Stefano Soatto}, booktitle = {Proceedings of Advances in Neural Information Processing Systems ({NeurIPS})}, title = {A Complexity-Distrotion Approach to Joint Pattern Alignment}, year = {2007} }
@techreport{vedaldi07open, author = {Andrea Vedaldi}, institution = {{UCLA CSD}}, number = {070012}, title = {An open implementation of the {SIFT} detector and descriptor}, year = {2007} }
@inproceedings{vedaldi06local, author = {Andrea Vedaldi and Stefano Soatto}, booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})}, title = {Local Features, All Grown Up}, year = {2006} }(oral presentation)
@inproceedings{vedaldi06viewpoint, author = {Andrea Vedaldi and Stefano Soatto}, booktitle = {Proceedings of the European Conference on Computer Vision ({ECCV})}, pages = {374}, title = {Viewpoint Induced Deformation Statistics and the Design of Viewpoint Invariant Features: Singularities and Occlusions}, year = {2006} }
@inproceedings{vedaldi05features, author = {Andrea Vedaldi and Stefano Soatto}, booktitle = {Proceedings of the International Conference on Computer Vision ({ICCV})}, title = {Features for Recognition: Viewpoint Invariance for Non-Planar Scenes}, year = {2005} }(oral presentation)
@inproceedings{vedaldi05kalmansac, author = {Andrea Vedaldi and Hailin Jin and Paolo Favaro and Stefano Soatto}, booktitle = {Proceedings of the International Conference on Computer Vision ({ICCV})}, title = {{KALMANSAC:} Robust Filtering by Consensus}, year = {2005} }
@techreport{vedaldiTR05viewpoint, author = {Andrea Vedaldi and Stefano Soatto}, institution = {{UCLA} {CSD}}, number = {050012}, title = {On Viewpoint Invariance for Non-Planar Scenes}, year = {2005} }