Bibliography

Publications of the year

Doctoral Dissertations and Habilitation Theses

• 1V. Kalogeiton.
  Localizing spatially and temporally objects and actions in videos, University of Edinburgh ; Inria Grenoble, September 2017.
  https://hal.inria.fr/tel-01674504
• 2J. Mairal.
  Large-Scale Machine Learning and Applications, UGA - Université Grenoble Alpes, October 2017, Habilitation à diriger des recherches.
  https://hal.inria.fr/tel-01629997
• 3M. Paulin.
  Of Learning Visual Representations Robust to Invariances for Image Classification and Retrieval, Université Grenoble Alpes, February 2017.
  https://hal.inria.fr/tel-01677852

Articles in International Peer-Reviewed Journals

• 4N. Chesneau, K. Alahari, C. Schmid.
  Learning from Web Videos for Event Classification, in: IEEE Transactions on Circuits and Systems for Video Technology, 2017. [ DOI : 10.1109/TCSVT.2017.2764624 ]
  https://hal.inria.fr/hal-01618400
• 5R. G. Cinbis, J. Verbeek, C. Schmid.
  Weakly Supervised Object Localization with Multi-fold Multiple Instance Learning, in: IEEE Transactions on Pattern Analysis and Machine Intelligence, January 2017, vol. 39, n^o 1, pp. 189-203, https://arxiv.org/abs/1503.00949. [ DOI : 10.1109/TPAMI.2016.2535231 ]
  https://hal.inria.fr/hal-01123482
• 6G. Durif, L. Modolo, J. Michaelsson, J. E. Mold, S. Lambert-Lacroix, F. Picard.
  High Dimensional Classification with combined Adaptive Sparse PLS and Logistic Regression, in: Bioinformatics, 2017, https://arxiv.org/abs/1502.05933. [ DOI : 10.1093/bioinformatics/btx571 ]
  https://hal.archives-ouvertes.fr/hal-01587360
• 7B. Ham, M. Cho, C. Schmid, J. Ponce.
  Proposal Flow: Semantic Correspondences from Object Proposals, in: IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, forthcoming.
  https://hal.inria.fr/hal-01644132
• 8G. Hu, X. Peng, Y. Yang, T. Hospedales, J. Verbeek.
  Frankenstein: Learning Deep Face Representations using Small Data, in: IEEE Transactions on Image Processing, January 2018, vol. 27, n^o 1, pp. 293-303, https://arxiv.org/abs/1603.06470. [ DOI : 10.1109/TIP.2017.2756450 ]
  https://hal.inria.fr/hal-01306168
• 9A. Mensch, J. Mairal, B. Thirion, G. Varoquaux.
  Stochastic Subsampling for Factorizing Huge Matrices, in: IEEE Transactions on Signal Processing, January 2018, vol. 66, n^o 1, pp. 113-128, https://arxiv.org/abs/1701.05363. [ DOI : 10.1109/TSP.2017.2752697 ]
  https://hal.archives-ouvertes.fr/hal-01431618
• 10A. Mishra, K. Alahari, C. Jawahar.
  Unsupervised refinement of color and stroke features for text binarization, in: International Journal on Document Analysis and Recognition, June 2017, vol. 20, n^o 2, pp. 105–121. [ DOI : 10.1007/s10032-017-0283-9 ]
  https://hal.inria.fr/hal-01490176
• 11M. Paulin, J. Mairal, M. Douze, Z. Harchaoui, F. Perronnin, C. Schmid.
  Convolutional Patch Representations for Image Retrieval: an Unsupervised Approach, in: International Journal of Computer Vision, January 2017, vol. 121, n^o 1, pp. 149–168. [ DOI : 10.1007/s11263-016-0924-3 ]
  https://hal.inria.fr/hal-01277109
• 12G. Varol, I. Laptev, C. Schmid.
  Long-term Temporal Convolutions for Action Recognition, in: IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, https://arxiv.org/abs/1604.04494, forthcoming. [ DOI : 10.1109/TPAMI.2017.2712608 ]
  https://hal.inria.fr/hal-01241518

International Conferences with Proceedings

• 13A. Bietti, J. Mairal.
  Invariance and Stability of Deep Convolutional Representations, in: NIPS 2017 - 31st Conference on Advances in Neural Information Processing Systems, Los Angeles, CA, United States, December 2017.
  https://hal.inria.fr/hal-01630265
• 14A. Bietti, J. Mairal.
  Stochastic Optimization with Variance Reduction for Infinite Datasets with Finite-Sum Structure, in: NIPS 2017 - Advances in Neural Information Processing Systems, Long Beach, CA, United States, December 2017, pp. 1-21, https://arxiv.org/abs/1610.00970.
  https://hal.inria.fr/hal-01375816
• 15N. Chesneau, G. Rogez, K. Alahari, C. Schmid.
  Detecting Parts for Action Localization, in: BMVC - British Machine Vision Conference, London, United Kingdom, September 2017, https://arxiv.org/abs/1707.06005.
  https://hal.inria.fr/hal-01573629
• 16N. Dvornik, K. Shmelkov, J. Mairal, C. Schmid.
  BlitzNet: A Real-Time Deep Network for Scene Understanding, in: ICCV 2017 - International Conference on Computer Vision, Venise, Italy, October 2017, 11 p.
  https://hal.archives-ouvertes.fr/hal-01573361
• 17K. K. Han, R. S. Rezende, B. Ham, K.-Y. K. Wong, M. Cho, C. S. Schmid, J. S. Ponce.
  SCNet: Learning Semantic Correspondence, in: International Conference on Computer Vision, Venise, Italy, International conference on computer vision, October 2017, https://arxiv.org/abs/1705.04043.
  https://hal.archives-ouvertes.fr/hal-01576117
• 18V. Kalogeiton, P. Weinzaepfel, V. Ferrari, C. Schmid.
  Action Tubelet Detector for Spatio-Temporal Action Localization, in: ICCV - IEEE International Conference on Computer Vision, Venice, Italy, October 2017, https://arxiv.org/abs/1705.01861.
  https://hal.inria.fr/hal-01519812
• 19V. Kalogeiton, P. Weinzaepfel, V. Ferrari, C. Schmid.
  Joint learning of object and action detectors, in: ICCV 2017 - IEEE International Conference on Computer Vision, Venice, Italy, October 2017.
  https://hal.inria.fr/hal-01575804
• 20P. Luc, N. Neverova, C. Couprie, J. Verbeek, Y. Lecun.
  Predicting Deeper into the Future of Semantic Segmentation, in: ICCV 2017 - International Conference on Computer Vision, Venise, Italy, October 2017, 10 p, https://arxiv.org/abs/1703.07684.
  https://hal.inria.fr/hal-01494296
• 21A. Mensch, J. Mairal, D. Bzdok, B. Thirion, G. Varoquaux.
  Learning Neural Representations of Human Cognition across Many fMRI Studies, in: Neural Information Processing Systems, Long Beach, United States, December 2017, https://arxiv.org/abs/1710.11438.
  https://hal.archives-ouvertes.fr/hal-01626823
• 22M. Pedersoli, T. Lucas, C. Schmid, J. Verbeek.
  Areas of Attention for Image Captioning, in: ICCV - International Conference on Computer Vision, Venice, Italy, October 2017.
  https://hal.inria.fr/hal-01428963
• 23J. Peyre, I. Laptev, C. Schmid, J. Sivic.
  Weakly-supervised learning of visual relations, in: ICCV 2017- International Conference on Computer Vision 2017, Venice, Italy, October 2017, https://arxiv.org/abs/1707.09472.
  https://hal.archives-ouvertes.fr/hal-01576035
• 24G. Rogez, P. Weinzaepfel, C. Schmid.
  LCR-Net: Localization-Classification-Regression for Human Pose, in: CVPR 2017 - IEEE Conference on Computer Vision & Pattern Recognition, Honolulu, United States, June 2017.
  https://hal.inria.fr/hal-01505085
• 25K. Shmelkov, C. Schmid, K. Alahari.
  Incremental Learning of Object Detectors without Catastrophic Forgetting, in: ICCV - IEEE International Conference on Computer Vision, Venice, Italy, October 2017.
  https://hal.inria.fr/hal-01573623
• 26P. Tokmakov, K. Alahari, C. Schmid.
  Learning Motion Patterns in Videos, in: CVPR - IEEE Conference on Computer Vision & Pattern Recognition, Honolulu, United States, July 2017, https://arxiv.org/abs/1612.07217.
  https://hal.archives-ouvertes.fr/hal-01427480
• 27P. Tokmakov, K. Alahari, C. Schmid.
  Learning Video Object Segmentation with Visual Memory, in: ICCV - IEEE International Conference on Computer Vision, Venice, Italy, October 2017, https://arxiv.org/abs/1704.05737.
  https://hal.archives-ouvertes.fr/hal-01511145
• 28G. Varol, J. J. Romero, X. Martin, N. Mahmood, M. J. Black, I. Laptev, C. Schmid.
  Learning from Synthetic Humans, in: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017), Honolulu, United States, July 2017, https://arxiv.org/abs/1701.01370. [ DOI : 10.1109/CVPR.2017.492 ]
  https://hal.inria.fr/hal-01505711

Other Publications

• 29A. Bietti, J. Mairal.
  Group Invariance, Stability to Deformations, and Complexity of Deep Convolutional Representations, November 2017, https://arxiv.org/abs/1706.03078 - working paper or preprint.
  https://hal.inria.fr/hal-01536004
• 30D. Chen, L. Jacob, J. Mairal.
  Predicting Transcription Factor Binding Sites with Convolutional Kernel Networks, November 2017, working paper or preprint.
  https://hal.inria.fr/hal-01632912
• 31T. Dias-Alves, J. Mairal, M. Blum.
  Loter: A software package to infer local ancestry for a wide range of species, November 2017, working paper or preprint. [ DOI : 10.1101/213728 ]
  https://hal.inria.fr/hal-01630228
• 32G. Durif, L. Modolo, J. E. Mold, S. Lambert-Lacroix, F. Picard.
  Probabilistic Count Matrix Factorization for Single Cell Expression Data Analysis, November 2017, working paper or preprint.
  https://hal.archives-ouvertes.fr/hal-01649275
• 33T. LUCAS, J. Verbeek.
  Auxiliary Guided Autoregressive Variational Autoencoders, November 2017, working paper or preprint.
  https://hal.inria.fr/hal-01652881
• 34H. Lin, J. Mairal, Z. Harchaoui.
  A Generic Quasi-Newton Algorithm for Faster Gradient-Based Optimization, April 2017, https://arxiv.org/abs/1610.00960 - working paper or preprint.
  https://hal.inria.fr/hal-01376079
• 35H. Lin, J. Mairal, Z. Harchaoui.
  Catalyst Acceleration for First-order Convex Optimization: from Theory to Practice, December 2017, working paper or preprint.
  https://hal.inria.fr/hal-01664934
• 36C. Paquette, H. Lin, D. Drusvyatskiy, J. Mairal, Z. Harchaoui.
  Catalyst Acceleration for Gradient-Based Non-Convex Optimization, June 2017, working paper or preprint.
  https://hal.inria.fr/hal-01536017
• 37P. Tokmakov, C. Schmid, K. Alahari.
  Learning to Segment Moving Objects, December 2017, https://arxiv.org/abs/1712.01127 - working paper or preprint.
  https://hal.archives-ouvertes.fr/hal-01653720
• 38K. Tombre, L. Quan, R. Horaud, P. Gros, C. Schmid, P. Sturm.
  In Memoriam Roger Mohr, Société Informatique de France, September 2017, pp. 91-98, Article qui rappelle la carrière scientifique de Roger Mohr.
  https://hal.inria.fr/hal-01598085
• 39N. Verma, E. Boyer, J. Verbeek.
  Dynamic Filters in Graph Convolutional Networks, June 2017, https://arxiv.org/abs/1706.05206 - working paper or preprint.
  https://hal.inria.fr/hal-01540389
• 40P. Weinzaepfel, X. MARTIN, C. Schmid.
  Human Action Localization with Sparse Spatial Supervision, May 2017, https://arxiv.org/abs/1605.05197 - working paper or preprint.
  https://hal.inria.fr/hal-01317558