---
title: "Andrea Vedaldi — all works — Elamur Research"
description: "All 76 works of Andrea Vedaldi in the Elamur Research library, the most cited first: our summaries where we have them, else the original."
canonical: "https://research.elamur.ai/free/en/authors/andrea-vedaldi/works/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/andrea-vedaldi/works/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / [Andrea Vedaldi](https://md.research.elamur.ai/free/en/authors/andrea-vedaldi/) / all works

# Andrea Vedaldi — all works

76 works · [← Andrea Vedaldi](https://md.research.elamur.ai/free/en/authors/andrea-vedaldi/)

1. **[Deep Face Recognition ↗](https://doi.org/10.5244/c.29.41) British Machine Vision Conference (BMVC) · no summary yet**Omkar Parkhi, Andrea Vedaldi, Andrew Zisserman*2015 · 4,994 citations*
2. **[Return of the Devil in the Details: Delving Deep into Convolutional Nets ↗](https://doi.org/10.5244/c.28.6) British Machine Vision Conference (BMVC) · no summary yet**Ken Chatfield et al.*2014 · 3,379 citations*
3. **[Understanding deep image representations by inverting them ↗](https://doi.org/10.1109/cvpr.2015.7299155) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Aravindh Mahendran, Andrea Vedaldi*2015 · 1,825 citations*
4. **[Cats and dogs ↗](https://doi.org/10.1109/cvpr.2012.6248092) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Omkar Parkhi et al.*2012 · 1,656 citations*
5. **[Speeding up Convolutional Neural Networks with Low Rank Expansions ↗](https://doi.org/10.5244/c.28.88) British Machine Vision Conference (BMVC) · no summary yet**Max Jaderberg, Andrea Vedaldi, Andrew Zisserman*2014 · 1,210 citations*
6. [**Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps arXiv:1312.6034**Karen Simonyan, Andrea Vedaldi, Andrew Zisserman*2013 · 1,210 citations*](https://md.research.elamur.ai/free/en/papers/simonyan-2013-deep-inside-convolutional-networks-visualising/)
7. **[Reading Text in the Wild with Convolutional Neural Networks ↗](https://doi.org/10.1007/s11263-015-0823-z) International Journal of Computer Vision · no summary yet**Max Jaderberg et al.*2015 · 1,208 citations*
8. **[The devil is in the details: an evaluation of recent feature encoding methods ↗](https://doi.org/10.5244/c.25.76) British Machine Vision Conference (BMVC) · no summary yet**Ken Chatfield et al.*2011 · 848 citations*
9. **[Improved Texture Networks: Maximizing Quality and Diversity in Feed-Forward Stylization and Texture Synthesis ↗](https://doi.org/10.1109/cvpr.2017.437) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Dmitry Ulyanov, Andrea Vedaldi, Victor Lempitsky*2017 · 832 citations*
10. **[Multiple kernels for object detection ↗](https://doi.org/10.1109/iccv.2009.5459183) IEEE International Conference on Computer Vision (ICCV) · no summary yet**Andrea Vedaldi et al.*2009 · 760 citations*
11. **[Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition ↗](https://arxiv.org/abs/1406.2227) arXiv (Cornell University) · no summary yet**Max Jaderberg et al.*2014 · 757 citations*
12. **[Efficient Additive Kernels via Explicit Feature Maps ↗](https://doi.org/10.1109/tpami.2011.153) IEEE Transactions on Pattern Analysis and Machine Intelligence · no summary yet**Andrea Vedaldi, Andrew Zisserman*2011 · 701 citations*
13. [**Learning multiple visual domains with residual adapters arXiv:1705.08045**Sylvestre-Alvise Rebuffi, Hakan Bilen, Andrea Vedaldi*2017 · 694 citations*](https://md.research.elamur.ai/free/en/papers/rebuffi-2017-learning-multiple-visual-domains-residual/)
14. **[Deep filter banks for texture recognition and segmentation ↗](https://doi.org/10.1109/cvpr.2015.7299007) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Mircea Cimpoi, Subhransu Maji, Andrea Vedaldi*2015 · 655 citations*
15. **[Deep Features for Text Spotting ↗](https://doi.org/10.1007/978-3-319-10593-2_34) Lecture notes in computer science · no summary yet**Max Jaderberg, Andrea Vedaldi, Andrew Zisserman*2014 · 653 citations*
16. **[Dynamic Image Networks for Action Recognition ↗](https://doi.org/10.1109/cvpr.2016.331) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Hakan Bilen et al.*2016 · 584 citations*
17. **[Vggsound: A Large-Scale Audio-Visual Dataset ↗](https://doi.org/10.1109/icassp40776.2020.9053174) IEEE International Conference on Acoustics Speech and Signal Processing · no summary yet**Honglie Chen et al.*2020 · 486 citations*
18. **[Fisher Vector Faces in the Wild ↗](https://doi.org/10.5244/c.27.8) British Machine Vision Conference (BMVC) · no summary yet**Karen Simonyan et al.*2013 · 448 citations*
19. **[Understanding image representations by measuring their equivariance and equivalence ↗](https://doi.org/10.1109/cvpr.2015.7298701) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Karel Lenc, Andrea Vedaldi*2015 · 378 citations*
20. **[Blocks That Shout: Distinctive Parts for Scene Classification ↗](https://doi.org/10.1109/cvpr.2013.124) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Mayank Juneja et al.*2013 · 374 citations*
21. **[Learning Local Feature Descriptors Using Convex Optimisation ↗](https://doi.org/10.1109/tpami.2014.2301163) IEEE Transactions on Pattern Analysis and Machine Intelligence · no summary yet**Karen Simonyan, Andrea Vedaldi, Andrew Zisserman*2014 · 359 citations*
22. **[Learning to Discover Novel Visual Categories via Deep Transfer Clustering ↗](https://doi.org/10.1109/iccv.2019.00849) IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yet**Kai Han, Andrea Vedaldi, Andrew Zisserman*2019 · 326 citations*
23. **[Generalized Category Discovery ↗](https://doi.org/10.1109/cvpr52688.2022.00734) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Sagar Vaze et al.*2022 · 261 citations*
24. **[Learning feed-forward one-shot learners ↗](https://openalex.org/W2962810352) neural information processing systems · no summary yet**Luca Bertinetto et al.*2016 · 256 citations*
25. **[Deep Structured Output Learning for Unconstrained Text Recognition ↗](https://arxiv.org/abs/1412.5903) arXiv (Cornell University) · no summary yet**Max Jaderberg et al.*2014 · 210 citations*
26. **[RealFusion 360° Reconstruction of Any Object from a Single Image ↗](https://doi.org/10.1109/cvpr52729.2023.00816) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Luke Melas-Kyriazi et al.*2023 · 205 citations*
27. **[Splatter Image: Ultra-Fast Single-View 3D Reconstruction ↗](https://arxiv.org/abs/2312.13150) arXiv:2312.13150 · no summary yet**Stanislaw Szymanowicz, Christian Rupprecht, Andrea Vedaldi*2023 · 199 citations*
28. **[End-to-End Representation Learning for Correlation Filter Based Tracking ↗](https://doi.org/10.1109/cvpr.2017.531) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Jack Valmadre et al.*2017 · 198 citations*
29. **[Localizing Visual Sounds the Hard Way ↗](https://doi.org/10.1109/cvpr46437.2021.01659) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Honglie Chen et al.*2021 · 182 citations*
30. **[Synthetic Data for Text Localisation in Natural Images ↗](https://arxiv.org/abs/1604.06646) arXiv:1604.06646 · no summary yet**Ankush Gupta, Andrea Vedaldi, Andrew Zisserman*2016 · 164 citations*
31. **[AutoNovel: Automatically Discovering and Learning Novel Visual Categories ↗](https://doi.org/10.1109/tpami.2021.3091944) IEEE Transactions on Pattern Analysis and Machine Intelligence · no summary yet**Kai Han et al.*2021 · 160 citations*
32. **[Deep Fisher Networks for Large-Scale Image Classification ↗](https://openalex.org/W2165146474) neural information processing systems · no summary yet**Karen Simonyan, Andrea Vedaldi, Andrew Zisserman*2013 · 147 citations*
33. **[Pylon Model for Semantic Segmentation ↗](https://openalex.org/W2150609397) no summary yet**Victor Lempitsky, Andrea Vedaldi, Andrew Zisserman*2011 · 126 citations*
34. **[A Compact and Discriminative Face Track Descriptor ↗](https://doi.org/10.1109/cvpr.2014.219) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Omkar Parkhi et al.*2014 · 121 citations*
35. **[The truth about cats and dogs ↗](https://doi.org/10.1109/iccv.2011.6126398) International Conference on Computer Vision · no summary yet**Omkar Parkhi et al.*2011 · 113 citations*
36. **[NightOwls: A Pedestrians at Night Dataset ↗](https://doi.org/10.1007/978-3-030-20887-5_43) Lecture notes in computer science · no summary yet**Lukáš Neumann et al.*2019 · 100 citations*
37. **[PC2: Projection-Conditioned Point Cloud Diffusion for Single-Image 3D Reconstruction ↗](https://doi.org/10.1109/cvpr52729.2023.01242) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Luke Melas-Kyriazi, Christian Rupprecht, Andrea Vedaldi*2023 · 96 citations*
38. **[Understanding Objects in Detail with Fine-Grained Attributes ↗](https://doi.org/10.1109/cvpr.2014.463) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Andrea Vedaldi et al.*2014 · 92 citations*
39. **[Sparse kernel approximations for efficient classification and detection ↗](https://doi.org/10.1109/cvpr.2012.6247943) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Andrea Vedaldi, Andrew Zisserman*2012 · 82 citations*
40. **[Generalized RBF feature maps for Efficient Detection ↗](https://doi.org/10.5244/c.24.2) British Machine Vision Conference (BMVC) · no summary yet**Sreekanth Vempati et al.*2010 · 78 citations*
41. **[Simultaneous Object Detection and Ranking with Weak Supervision ↗](https://openalex.org/W2137023887) no summary yet**Matthew B. Blaschko, Andrea Vedaldi, Andrew Zisserman*2010 · 63 citations*
42. **[Structured output regression for detection with partial truncation ↗](https://openalex.org/W2135578030) no summary yet**Andrea Vedaldi, Andrew Zisserman*2009 · 61 citations*
43. **[Descriptor Learning Using Convex Optimisation ↗](https://doi.org/10.1007/978-3-642-33718-5_18) Lecture notes in computer science · no summary yet**Karen Simonyan, Andrea Vedaldi, Andrew Zisserman*2012 · 60 citations*
44. **[Relaxed Softmax: Efficient Confidence Auto-Calibration for Safe Pedestrian Detection ↗](https://openalex.org/W2908048420) no summary yet**Lukáš Neumann, Andrew Zisserman, Andrea Vedaldi*2018 · 50 citations*
45. **[Open-Set Recognition: a Good Closed-Set Classifier is All You Need? ↗](https://arxiv.org/abs/2110.06207) arXiv (Cornell University) · no summary yet**Sagar Vaze et al.*2021 · 48 citations*
46. **[Automatically Discovering and Learning New Visual Categories with Ranking Statistics ↗](https://arxiv.org/abs/2002.05714) arXiv (Cornell University) · no summary yet**Kai Han et al.*2020 · 39 citations*
47. **[On-the-fly specific person retrieval ↗](https://doi.org/10.1109/wiamis.2012.6226775) International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS) · no summary yet**Omkar Parkhi, Andrea Vedaldi, Andrew Zisserman*2012 · 36 citations*
48. **[Future Event Prediction: If and When ↗](https://doi.org/10.1109/cvprw.2019.00354) IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · no summary yet**Lukáš Neumann, Andrew Zisserman, Andrea Vedaldi*2019 · 32 citations*
49. **[Text-To-4D Dynamic Scene Generation ↗](https://arxiv.org/abs/2301.11280) arXiv (Cornell University) · no summary yet**Uriel Singer et al.*2023 · 31 citations*
50. **[Automatic Discovery and Optimization of Parts for Image Classification ↗](https://arxiv.org/abs/1412.6598) arXiv (Cornell University) · no summary yet**Sobhan Naderi Parizi et al.*2014 · 28 citations*
51. **[Learning equivariant structured output SVM regressors ↗](https://doi.org/10.1109/iccv.2011.6126339) International Conference on Computer Vision · no summary yet**Andrea Vedaldi, Matthew B. Blaschko, Andrew Zisserman*2011 · 28 citations*
52. **[Contrastive Lift: 3D Object Instance Segmentation by Slow-Fast Contrastive Fusion ↗](https://doi.org/10.52202/075280-0399) neural information processing systems · no summary yet**Yash Sanjay Bhalgat et al.*2023 · 26 citations*
53. **[No Representation Rules Them All in Category Discovery ↗](https://doi.org/10.52202/075280-0876) neural information processing systems · no summary yet**Sagar Vaze, Andrea Vedaldi, Andrew Zisserman*2023 · 21 citations*
54. **[Self-similar Sketch ↗](https://doi.org/10.1007/978-3-642-33709-3_7) Lecture notes in computer science · no summary yet**Andrea Vedaldi, Andrew Zisserman*2012 · 20 citations*
55. **[Monocular Depth Estimation with Self-supervised Instance Adaptation ↗](https://arxiv.org/abs/2004.05821) arXiv (Cornell University) · no summary yet**Robert McCraith et al.*2020 · 19 citations*
56. **[Learning to Read by Spelling ↗](https://doi.org/10.1145/3293353.3293386) Indian Conference on Computer Vision, Graphics and Image Processing · no summary yet**Ankush Gupta, Andrea Vedaldi, Andrew Zisserman*2018 · 16 citations*
57. **[PASS: An ImageNet replacement for self-supervised pretraining without humans ↗](https://arxiv.org/abs/2109.13228) arXiv (Cornell University) · no summary yet**Yuki M. Asano et al.*2021 · 14 citations*
58. **[N2F2: Hierarchical Scene Understanding with Nested Neural Feature Fields ↗](https://doi.org/10.1007/978-3-031-73202-7_12) Lecture notes in computer science · no summary yet**Yash Sanjay Bhalgat et al.*2024 · 13 citations*
59. **[LSD-C: Linearly Separable Deep Clusters ↗](https://doi.org/10.1109/iccvw54120.2021.00121) IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) · no summary yet**Sylvestre-Alvise Rebuffi et al.*2021 · 10 citations*
60. **[Semi-Supervised Learning with Scarce Annotations ↗](https://doi.org/10.1109/cvprw50498.2020.00389) IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · no summary yet**Sylvestre-Alvise Rebuffi et al.*2020 · 8 citations*
61. **[AutoCorrect: Deep Inductive Alignment of Noisy Geometric Annotations ↗](https://arxiv.org/abs/1908.05263) arXiv (Cornell University) · no summary yet**Honglie Chen et al.*2019 · 8 citations*
62. **[3D-Aware Instance Segmentation and Tracking in Egocentric Videos ↗](https://doi.org/10.1007/978-981-96-0908-6_20) Lecture notes in computer science · no summary yet**Yash Sanjay Bhalgat et al.*2024 · 5 citations*
63. **[Learning to Read by Spelling: Towards Unsupervised Text Recognition ↗](https://arxiv.org/abs/1809.08675) arXiv (Cornell University) · no summary yet**Ankush Gupta, Andrea Vedaldi, Andrew Zisserman*2018 · 5 citations*
64. **[Audio-Visual Synchronisation in the wild ↗](https://arxiv.org/abs/2112.04432) arXiv (Cornell University) · no summary yet**Honglie Chen et al.*2021 · 4 citations*
65. **[Inductive Visual Localisation: Factorised Training for Superior Generalisation ↗](https://arxiv.org/abs/1807.08179) arXiv (Cornell University) · no summary yet**Ankush Gupta, Andrea Vedaldi, Andrew Zisserman*2018 · 3 citations*
66. **[Oxford-IIIT TRECVID 2009 - Notebook Paper ↗](https://openalex.org/W2915409354) no summary yet**Sreekanth Vempati et al.*2009 · 3 citations*
67. **[Towards a detailed understanding of objects and scenes in natural images ↗](https://openalex.org/W2524969449) INRIA a CCSD electronic archive server · no summary yet**Matthew B. Blaschko et al.*2012 · 2 citations*
68. **[Oxford-IIIT TRECVID 2010 - Notebook paper. ↗](https://openalex.org/W2916865123) no summary yet**Mayank Juneja et al.*2010 · 1 citation*
69. **[The University of Oxford response to the UK government consultation on copyright and AI ↗](https://doi.org/10.5287/ora-gogk6kz0d) Oxford University Research Archive (ORA) (University of Oxford) · no summary yet**Chris Morrison, Andrew Zisserman, Andrea Vedaldi*2025*
70. **[JADERBERG, VEDALDI, AND ZISSERMAN: SPEEDING UP CONVOLUTIONAL... 1 Speeding up Convolutional Neural Networks with Low Rank Expansions ↗](https://openalex.org/W7099004956) no summary yet**Max Jaderberg, Andrea Vedaldi, Andrew Zisserman*2016*
71. **[CHATFIELD et al.: THE DEVIL IS IN THE DETAILS 1 The devil is in the details: an evaluation of recent feature encoding methods ↗](https://openalex.org/W7099142701) no summary yet**Ken Chatfield et al.*2014*
72. **[Synthetic data and artificial neural networks for natural scene text recognition." arXiv preprint arXiv:1406.2227 ↗](https://openalex.org/W7098536107) no summary yet**Max Jaderberg et al.*2014*
73. **[4. Kernel reconstruction K(x, x0) ⇡ (x)> KZZ (x 0) ↗](https://openalex.org/W7098618161) no summary yet**Andrea Vedaldi, Andrew Zisserman, Zz Kzx*2013*
74. **[Overview Formulation Algorithm Results ↗](https://openalex.org/W7096902281) no summary yet**Andrea Vedaldi, Matthew B. Blaschko, Andrew Zisserman*2013*
75. **[SREEKANTH.V et al.: GENERALIZED RBF FEATURE MAPS 1 Generalized RBF feature maps for Efficient Detection ↗](https://openalex.org/W7096805241) no summary yet**Sreekanth Vempati et al.*2013*
76. **[Structured output regression for detection with partial occulsion ↗](https://openalex.org/W7097112811) no summary yet**Andrea Vedaldi, Andrew Zisserman*2009*