ALL PUBLICATIONS
Sorted by: [year] [type]
2023
Pia Bideau, Erik Learned-Miller, Cordelia Schmid, Karteek Alahari
The Right Spin: Learning Object Motion from Rotation-Compensated Flow Fields 
International Journal of Computer Vision (IJCV), 2023 (accepted).
[abstract] [pdf] [bibtex] [DOI] [HAL] [ArXiv]
Zhiqi Kang*, Enrico Fini*, Moin Nabi, Elisa Ricci, Karteek Alahari
A soft nearest-neighbor framework for continual semi-supervised learning
In Proceedings of the International Conference on Computer Vision (ICCV), 2023.
[abstract] [pdf] [bibtex] [HAL] [ArXiv] [supplementary material]
* - joint first authors
Florent Bartoccioni, Eloi Zablocki, Patrick Pérez, Matthieu Cord, Karteek Alahari
LiDARTouch: Monocular metric depth estimation with a few-beam LiDAR
In Computer Vision and Image Understanding (CVIU) Journal, 2023.
[abstract] [pdf] [bibtex] [DOI] [HAL] [ArXiv] [Code]
Enrico Fini*, Pietro Astolfi*, Karteek Alahari, Xavier Alameda-Pineda, Julien Mairal, Moin Nabi, Elisa Ricci
Semi-supervised learning made simple with self-supervised clustering
In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023.
[abstract] [pdf] [bibtex] [HAL] [ArXiv] [supplementary material] [Code]
* - joint first authors
Mert Bulent Sariyildiz, Karteek Alahari, Diane Larlus, Yannis Kalantidis
Fake it till you make it: Learning transferable representations from synthetic ImageNet clones
In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023.
[abstract] [pdf] [bibtex] [HAL] [ArXiv] [supplementary material] [project page] [Models]
Mert Bulent Sariyildiz, Yannis Kalantidis, Karteek Alahari, Diane Larlus
No Reason for No Supervision: Improved Generalization in Supervised Models
In Proceedings of the International Conference on Learning Representations (ICLR), 2023 (spotlight, notable top 25%).
[abstract] [pdf] [bibtex] [HAL] [ArXiv] [project page] [Code, Models]
2022
Hubert Leterme, Kévin Polisano, Valérie Perrier, Karteek Alahari
From CNNs to Shift-Invariant Twin Wavelet Models
Technical report, 2022.
[abstract] [pdf] [bibtex] [HAL] [ArXiv]
Heeseung Kwon, Francisco M. Castro, Manuel J. Marin-Jimenez, Nicolas Guil, Karteek Alahari
Lightweight Structure-Aware Attention for Visual Understanding
Technical report, 2022.
[abstract] [pdf] [bibtex] [HAL] [ArXiv]
Hubert Leterme, Kévin Polisano, Valérie Perrier, Karteek Alahari
On the Shift Invariance of Max Pooling Feature Maps in Convolutional Neural Networks
Technical report, 2022.
[abstract] [pdf] [bibtex] [HAL] [ArXiv]
Lina Mezghani, Sainbayar Sukhbaatar, Piotr Bojanowski, Alessandro Lazaric, Karteek Alahari
Learning Goal-Conditioned Policies Offline with Self-Supervised Reward Shaping
In Proceedings of the Conference on Robot Learning (CoRL), 2022.
[abstract] [pdf] [bibtex] [HAL] [ArXiv] [Code]
Florent Bartoccioni, Eloi Zablocki, Andrei Bursuc, Patrick Pérez, Matthieu Cord, Karteek Alahari
LaRa: Latents and Rays for Multi-Camera Bird's-Eye-View Semantic Segmentation
In Proceedings of the Conference on Robot Learning (CoRL), 2022.
[abstract] [pdf] [bibtex] [HAL] [ArXiv] [Code]
Avijit Dasgupta, C. V. Jawahar, Karteek Alahari
Overcoming Label Noise for Source-free Unsupervised Video Domain Adaptation
In Proceedings of the Indian Conference on Computer Vision, Graphics and Image Processing (ICVGIP), 2022 (Best paper runner-up award).
[abstract] [pdf] [bibtex] [HAL]
Lina Mezghani, Sainbayar Sukhbaatar, Thibaut Lavril, Oleksandr Maksymets, Dhruv Batra, Piotr Bojanowski, Karteek Alahari
Memory-Augmented Reinforcement Learning for Image-Goal Navigation
In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022.
[abstract] [pdf] [bibtex] [HAL] [ArXiv]
Valentin Gabeur, Paul Hongsuck Seo, Arsha Nagrani, Chen Sun, Karteek Alahari, Cordelia Schmid
AVATAR: Unconstrained Audiovisual Speech Recognition
In Proceedings of INTERSPEECH, 2022.
[abstract] [pdf] [bibtex] [HAL] [ArXiv]
Enrico Fini, Victor G. Turrisi da Costa, Xavier Alameda-Pineda, Elisa Ricci, Karteek Alahari, Julien Mairal
Self-Supervised Models are Continual Learners
In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
[abstract] [pdf] [bibtex] [HAL] [ArXiv]
Valentin Gabeur, Arsha Nagrani, Chen Sun, Karteek Alahari, Cordelia Schmid
Masking Modalities for Cross-modal Video Retrieval
In Proceedings of the Winter Conference on Applications of Computer Vision (WACV), 2022.
[abstract] [pdf] [bibtex] [HAL] [ArXiv]
2021
D. Khuê Lê-Huu, Karteek Alahari
Regularized Frank-Wolfe for Dense CRFs: Generalizing Mean Field and Beyond
In Advances in Neural Information Processing Systems (NeurIPS), 2021.
[abstract] [pdf] [bibtex] [HAL] [ArXiv]
Mert Bulent Sariyildiz, Yannis Kalantidis, Diane Larlus, Karteek Alahari
Concept Generalization in Visual Representation Learning
In Proceedings of the International Conference on Computer Vision (ICCV), 2021.
[abstract] [pdf] [bibtex] [HAL] [ArXiv] [project page] [supplementary material] [Code]
Hubert Leterme, Kévin Polisano, Valérie Perrier, Karteek Alahari
Sparsifying Convolutional Layers with Dual-Tree Wavelet Packets
Technical report, presented at Journées francophones des jeunes chercheurs en vision par ordinateur, 2021.
[abstract] [pdf] [bibtex] [HAL]
2020
Avijit Dasgupta, C. V. Jawahar, Karteek Alahari
Context Aware Group Activity Recognition
In Proceedings of the International Conference on Pattern Recognition (ICPR), 2020.
[abstract] [pdf] [bibtex] [HAL]
Samuel Albanie, and other challenge organizers and participants
The End-of-End-to-End: A Video Understanding Pentathlon Challenge (2020)
Workshop technical report, 2020.
[abstract] [pdf] [bibtex] [HAL] [ArXiv]
Valentin Gabeur, Chen Sun, Karteek Alahari, Cordelia Schmid
Multi-modal Transformer for Video Retrieval
In Proceedings of the European Conference on Computer Vision (ECCV), 2020.
[abstract] [pdf] [bibtex] [HAL] [ArXiv] [project page] [supplementary material] [code]
Ekaterina Iakovleva, Jakob Verbeek, Karteek Alahari
Meta-Learning with Shared Amortized Variational Inference
In Proceedings of the International Conference on Machine Learning (ICML), 2020.
[abstract] [pdf] [bibtex] [HAL] [ArXiv] [supplementary material]
Gunnar A. Sigurdsson, Abhinav Gupta, Cordelia Schmid, Karteek Alahari
Beyond the Camera: Neural Networks in World Coordinates
Technical report, 2020.
[abstract] [pdf] [bibtex] [HAL] [ArXiv]
2019
Thomas Lucas, Konstantin Shmelkov, Karteek Alahari, Cordelia Schmid, Jakob Verbeek
Adaptive Density Estimation for Generative Models
In Advances in Neural Information Processing Systems (NeurIPS), 2019 (spotlight).
[abstract] [pdf] [bibtex] [HAL]
Vladyslav Sydorov, Karteek Alahari, Cordelia Schmid
Focused Attention for Action Recognition
In Proceedings of the British Machine Vision Conference (BMVC), 2019.
[abstract] [pdf] [bibtex] [HAL]
Nieves Crasto, Philippe Weinzaepfel, Karteek Alahari, Cordelia Schmid
MARS: Motion-Augmented RGB Stream for Action Recognition
In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
[abstract] [pdf] [bibtex] [HAL] [Code]
Pavel Tokmakov, Cordelia Schmid, Karteek Alahari
Learning to Segment Moving Objects
International Journal of Computer Vision (IJCV), 2019.
[abstract] [pdf] [bibtex] [HAL] [ArXiv] [project page] [code + models (journal version)]
Karteek Alahari
Human, Motion and Other Priors for Partially-Supervised Recognition
Habilitation Manuscript, Université Grenoble Alpes, January 2019.
[abstract] [pdf] [bibtex] [HAL]
2018
Francisco M. Castro, Manuel J. Marin-Jimenez, Nicolas Guil, Cordelia Schmid, Karteek Alahari
End-to-End Incremental Learning
In Proceedings of the European Conference on Computer Vision (ECCV), 2018.
[abstract] [pdf] [bibtex] [HAL] [ArXiv] [project page] [code]
Konstantin Shmelkov, Cordelia Schmid, Karteek Alahari
How good is my GAN?
In Proceedings of the European Conference on Computer Vision (ECCV), 2018.
[abstract] [pdf] [bibtex] [HAL] [ArXiv] [project page] [code]
Gunnar A. Sigurdsson, Abhinav Gupta, Cordelia Schmid, Ali Farhadi, Karteek Alahari
Charades-Ego: A Large-Scale Dataset of Paired Third and First Person Videos
Technical report, 2018.
[abstract] [pdf] [bibtex] [HAL] [ArXiv] [project page]
Gunnar A. Sigurdsson, Abhinav Gupta, Cordelia Schmid, Ali Farhadi, Karteek Alahari
Actor and Observer: Joint Modeling of First and Third-Person Videos
In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.
[abstract] [pdf] [bibtex] [HAL] [ArXiv] [project page (with dataset and code)] [supplementary material]
Nicolas Chesneau, Karteek Alahari, Cordelia Schmid
Learning from Web Videos for Event Classification
In IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2018.
[abstract] [pdf] [bibtex] [DOI] [HAL]
2017
Konstantin Shmelkov, Cordelia Schmid, Karteek Alahari
Incremental Learning of Object Detectors without Catastrophic Forgetting
In Proceedings of the International Conference on Computer Vision (ICCV), 2017.
[abstract] [pdf] [bibtex] [HAL] [project page]
Pavel Tokmakov, Karteek Alahari, Cordelia Schmid
Learning Video Object Segmentation with Visual Memory
In Proceedings of the International Conference on Computer Vision (ICCV), 2017 (oral).
[abstract] [pdf] [bibtex] [HAL] [Tech. rep. - ArXiv] [project page] [code + models]
Nicolas Chesneau, Gregory Rogez, Karteek Alahari, Cordelia Schmid
Detecting Parts for Action Localization
In Proceedings of the British Machine Vision Conference (BMVC), 2017.
[abstract] [pdf] [bibtex] [HAL]
Anand Mishra, Karteek Alahari, C. V. Jawahar
Unsupervised refinement of color and stroke features for text binarization
In International Journal on Document Analysis and Recognition (IJDAR), 2017.
[abstract] [pdf] [bibtex] [DOI] [HAL]
Pavel Tokmakov, Karteek Alahari, Cordelia Schmid
Learning Motion Patterns in Videos
In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.
[abstract] [pdf] [bibtex] [HAL] [ArXiv] [project page] [code + models]
2016
Pavel Tokmakov, Karteek Alahari, Cordelia Schmid
Weakly-Supervised Semantic Segmentation using Motion Cues
In Proceedings of the European Conference on Computer Vision (ECCV), 2016.
[abstract] [pdf] [bibtex] [HAL] [Tech. rep.] [project page] [code + models]
Anand Mishra, Karteek Alahari, C. V. Jawahar
Enhancing Energy Minimization Framework for Scene Text Recognition with Top-Down Cues
In Computer Vision and Image Understanding (CVIU) Journal, 2016.
[abstract] [pdf] [bibtex] [DOI] [HAL] [ArXiV] [project page] [IIIT 5K-Word Dataset] [SVT-CHAR data] [README]
2015
Yang Hua, Karteek Alahari, Cordelia Schmid
Online Object Tracking with Proposal Selection
In Proceedings of the International Conference on Computer Vision (ICCV), 2015.
[abstract] [pdf] [bibtex] [DOI] [HAL] [ArXiv] [project page] [code]
Matej Kristan, and other challenge organizers and participants
The Visual Object Tracking VOT2015 Challenge Results
ICCV Workshop technical report, 2015.
[abstract] [pdf] [bibtex] [HAL]
Michael Felsberg, and other challenge organizers and participants
The Thermal Infrared Visual Object Tracking VOT-TIR2015 Challenge Results
ICCV Workshop technical report, 2015.
[abstract] [pdf] [bibtex] [HAL]
Karteek Alahari, Dhruv Batra, Srikumar Ramalingam, Nikos Paragios, Richard Zemel
Guest Editors' Introduction: Special Section on Higher Order Graphical Models in Computer Vision
In IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2015.
[abstract] [pdf] [html] [bibtex] [DOI]
Guillaume Seguin, Karteek Alahari, Josef Sivic, Ivan Laptev
Pose Estimation and Segmentation of Multiple People in Stereoscopic Movies
In IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2015.
[abstract] [pdf] [bibtex] [DOI] [Copyright] [HAL] [project page] [Inria 3DMovie dataset]
2014
Udit Roy, Anand Mishra, Karteek Alahari, C. V. Jawahar
Scene Text Recognition and Retrieval for Large Lexicons
In Proceedings of the Asian Conference on Computer Vision (ACCV), 2014.
[abstract] [pdf] [bibtex] [DOI] [HAL]
M. Douze, D. Oneata, M. Paulin, C. Leray, N. Chesneau, D. Potapov, J. Verbeek, K. Alahari, Z. Harchaoui, L. Lamel, J.-L. Gauvain, C. A. Schmidt, C. Schmid
The INRIA-LIM-VocR and AXES submissions to Trecvid 2014 Multimedia Event Detection
2014
[pdf] [bibtex] [HAL]
Yang Hua, Karteek Alahari, Cordelia Schmid
Occlusion and Motion Reasoning for Long-term Tracking
In Proceedings of the European Conference on Computer Vision (ECCV), 2014.
[abstract] [pdf] [bibtex] [DOI] [HAL] [project page]
Anoop Cherian, Julien Mairal, Karteek Alahari, Cordelia Schmid
Mixing Body-Part Sequences for Human Pose Estimation
In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014.
[abstract] [pdf] [bibtex] [DOI] [HAL] [project page] [dataset] [code]
2013
Karteek Alahari, Guillaume Seguin, Josef Sivic, Ivan Laptev
Pose Estimation and Segmentation of People in 3D Movies
In Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2013.
[abstract] [pdf] [bibtex] [DOI] [HAL] [project page] [Inria 3DMovie dataset]
Minsu Cho, Karteek Alahari, Jean Ponce
Learning Graphs to Match
In Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2013 (oral).
[abstract] [pdf] [bibtex] [DOI] [HAL] [project page]
Ankit Gandhi, Karteek Alahari, C. V. Jawahar
Decomposing Bag of Words Histograms
In Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2013.
[abstract] [pdf] [bibtex] [DOI] [HAL]
Anand Mishra, Karteek Alahari, C. V. Jawahar
Image Retrieval using Textual Cues
In Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2013.
[abstract] [pdf] [bibtex] [DOI] [HAL] [project page] [datasets: IIIT STR, TV series-1M, Sports-10K]
Vibhor Goel, Anand Mishra, Karteek Alahari, C. V. Jawahar
Whole is Greater than Sum of Parts: Recognizing Scene Text Words
In Proceedings of the International Conference on Document Analysis and Recognition (ICDAR), 2013.
[abstract] [pdf] [bibtex] [DOI] [HAL]
Florent Couzinié-Devy, Jian Sun, Karteek Alahari, Jean Ponce
Learning to Estimate and Remove Non-uniform Image Blur
In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013.
[abstract] [pdf] [bibtex] [DOI] [HAL]
2012
Anand Mishra, Karteek Alahari, C. V. Jawahar
Scene Text Recognition using Higher Order Language Priors
In Proceedings of the British Machine Vision Conference (BMVC), 2012 (oral).
[abstract] [pdf] [bibtex] [DOI] [HAL] [project page] [IIIT 5K-Word Dataset]
Anand Mishra, Karteek Alahari, C. V. Jawahar
Top-Down and Bottom-Up Cues for Scene Text Recognition
In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2012.
[abstract] [pdf] [bibtex] [DOI] [HAL] [project page] [SVT-CHAR data] [README]
2011
Anand Mishra, Karteek Alahari, C. V. Jawahar
An MRF Model for Binarization of Natural Scene Text
In Proceedings of the International Conference on Document Analysis and Recognition (ICDAR), 2011 (oral).
[abstract] [pdf] [bibtex] [DOI] [HAL]
Mark Schmidt, Karteek Alahari
Generalized Fast Approximate Energy Minimization via Graph Cuts: Alpha-Expansion Beta-Shrink Moves
In Proceedings of the 27th Conference on Uncertainty in Artificial Intelligence (UAI), 2011.
[abstract] [pdf] [bibtex] [HAL] [arXiv] [code]
José Lezama, Karteek Alahari, Josef Sivic, Ivan Laptev
Track to the Future: Spatio-temporal Video Segmentation with Long-range Motion Cues
In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011.
[abstract] [pdf] [bibtex] [DOI] [HAL] [poster] [project page]
2010
Karteek Alahari, Pushmeet Kohli, P. H. S. Torr
Dynamic Hybrid Algorithms for MAP Inference in Discrete MRFs
In IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2010.
[abstract] [pdf] [bibtex] [DOI] [Copyright] [code] [README] [data]
Ľubor Ladický, Paul Sturgess, Karteek Alahari, Chris Russell, P. H. S. Torr
What, Where & How Many? Combining Object Detectors and CRFs
In Proceedings of the European Conference on Computer Vision (ECCV), 2010 (oral).
[abstract] [pdf] [bibtex] [DOI] [code]
Karteek Alahari
Efficient Inference and Learning for Computer Vision Labelling Problems
Ph.D. Thesis, Oxford Brookes University, July 2010.
[abstract] [pdf] [bibtex]
Karteek Alahari, Chris Russell, P. H. S. Torr
Efficient Piecewise Learning for Conditional Random Fields
In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2010.
[abstract] [pdf] [bibtex] [DOI]
2009
Paul Sturgess, Karteek Alahari, Ľubor Ladický, P. H. S. Torr
Combining Appearance and Structure from Motion Features for Road Scene Understanding
In Proceedings of the British Machine Vision Conference (BMVC), 2009 (oral).
[abstract] [pdf] [bibtex] [DOI] [code]
2008
Karteek Alahari, Pushmeet Kohli, P. H. S. Torr
Reduce, Reuse & Recycle: Efficiently Solving Multi-Label MRFs
In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2008.
[abstract] [pdf] [bibtex] [DOI] [code] [README]
Srikumar Ramalingam, Pushmeet Kohli, Karteek Alahari, P. H. S. Torr
Exact Inference in Multi-label CRFs with Higher Order Cliques
In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2008.
[abstract] [pdf] [bibtex] [DOI]
2004 - 2006
Karteek Alahari, C. V. Jawahar
Dynamic Events as Mixtures of Spatial and Temporal Features
In Proceedings of the Indian Conference on Computer Vision, Graphics and Image Processing (ICVGIP), 2006.
[pdf][bibtex]
Karteek Alahari, C. V. Jawahar
Discriminative Actions for Recognising Events
In Proceedings of the Indian Conference on Computer Vision, Graphics and Image Processing (ICVGIP), 2006.
[pdf][bibtex]
Karteek Alahari, Satya Lahari Putrevu, C. V. Jawahar
Learning Mixtures of Offline and Online features for Handwritten Stroke Recognition
In Proceedings of the IEEE International Conference on Pattern Recognition (ICPR), 2006.
[pdf][bibtex]
Karteek Alahari
"Modelling and Recognition of Dynamic Events in Video"
MS Thesis, IIIT Hyderabad, July 2005.
[bibtex]
Karteek Alahari, Satya Lahari Putrevu, C. V. Jawahar
Discriminant Substrokes for Online Handwriting Recognition
In Proceedings of the IEEE International Conference on Document Analysis and Recognition (ICDAR), 2005 (oral).
[pdf][bibtex]
Ravi Kiran Sarvadevabhatla, Karteek Alahari, C. V. Jawahar
Recognizing Human Activities from Constituent Actions
In Proceedings of the National Conference on Communications (NCC), 2005 (oral).
[pdf][bibtex]
Karteek Alahari, Sujit Kuthirummal, C. V. Jawahar, P. J. Narayanan
Geometric and Stochastic Error Minimisation in Motion Tracking
In Proceedings of the Asian Conference on Computer Vision (ACCV), 2004.
[pdf][bibtex]