Ishan Misra

			
@inproceedings{emuvideo2023,
title={Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning},
author={Rohit Girdhar and Mannat Singh and Andrew Brown and Quentin Duval and Samaneh Azadi and Sai Saketh Rambhatla and Akbar Shah and Xi Yin and Devi Parikh and Ishan Misra},
inproceedings={ECCV},
year={2024},
}
		

			
@inproceedings{liang2024flowvid,
title={FlowVid: Taming Imperfect Optical Flows for Consistent Video-to-Video Synthesis},
author={Feng Liang and Bichen Wuand Jialiang Wang and Licheng Yu and Kunpeng Li and Yinan Zhao and Ishan Misra and Jia-Bin Huang and Peizhao Zhang and Peter Vajda and Diana Marculescu},
booktitle={CVPR},
year={2024},
}
		

			
@inproceedings{wang2024instance,
title={InstanceDiffusion: Instance-level Control for Image Generation},
author={Xudong Wang and Trevor Darrell and Sai Saketh Rambhatla and Rohit Girdhar and Ishan Misra},
booktitle={CVPR},
year={2024},
}
		

			
@inproceedings{menon2024illustrated,
title={Generating Illustrated Instructions},
author={Sachit Menon and Ishan Misra and Rohit Girdhar},
booktitle={CVPR},
year={2024},
}
		

			
@inproceedings{wang2024vcutler,
title={VideoCutLER: Surprisingly Simple Unsupervised Video Instance Segmentation},
author={Xudong Wang and Ishan Misra and Ziyun Zheng and Rohit Girdhar and Trevor Darrell},
booktitle={CVPR},
year={2024},
}
		

			
@inproceedings{singh2023effectiveness,
title={The effectiveness of MAE pre-pretraining for billion-scale pretraining},
author={Singh, Mannat and Duval, Quentin and Alwala, Kalyan Vasudev and Fan, Haoqi and Aggarwal, Vaibhav and Adcock, Aaron and Joulin, Armand and Doll{\'a}r, Piotr and Feichtenhofer, Christoph and Girshick, Ross and Girdhar, Rohit and Misra, Ishan},
booktitle={ICCV},
year={2023},
}
		

			
@inproceedings{rambhatla2023most,
title={MOST: Multiple Object localization with Self-supervised Transformers for object discovery},
author={Sai Saketh Rambhatla and Ishan Misra and Rama Chellappa and Abhinav Shrivastava},
booktitle={ICCV},
year={2023},
}
		

			
@inproceedings{fu2023mononerf,
title={MonoNeRF: Learning Generalizable NeRFs from Monocular Videos without Camera Poses},
author={Yang Fu and Ishan Misra and Xiaolong Wang},
booktitle={ICML},
year={2023},
}
		

			
@inproceedings{girdhar2023imagebind,
title={ImageBind: One Embedding Space To Bind Them All},
author={Girdhar, Rohit and El-Nouby, Alaaeldin and Liu, Zhuang and Singh, Mannat and Alwala, Kalyan Vasudev and Joulin, Armand and Misra, Ishan},
booktitle={CVPR},
year={2023},
}
		

			
@inproceedings{wang2023cut,
title={Cut and Learn for Unsupervised Object Detection and Instance Segmentation},
author={Wang, Xudong and Girdhar, Rohit and Yu, Stella X and Misra, Ishan},
booktitle={CVPR},
year={2023},
}
		

			
@inproceedings{zhao2022lavila,
title={Learning Video Representations from Large Language Models},
author={Zhao, Yue and Misra, Ishan and Kr{\"a}henb{\"u}hl, Philipp and Girdhar, Rohit},
booktitle=CVPR,
year={2023},
}
		

			
@inproceedings{assran2023hidden,
title={The Hidden Uniform Cluster Prior in Self-Supervised Learning},
author={Mahmoud Assran and Randall Balestriero and Quentin Duval and Florian Bordes and Ishan Misra and Piotr Bojanowski and Pascal Vincent and Michael Rabbat and Nicolas Ballas},
booktitle=ICLR,
year={2023},
}
		

			
@inproceedings{girdhar2022omnimae,
title={OmniMAE: Single Model Masked Pretraining on Images and Videos},
author={Girdhar, Rohit and El-Nouby, Alaaeldin and Singh, Mannat and Alwala, Kalyan Vasudev and Joulin, Armand and Misra, Ishan},
booktitle={CVPR},
year={2023},
}
		

			
@inproceedings{assran2022masked,
title={Masked Siamese Networks for Label-Efficient Learning},
author={Assran, Mahmoud, and Caron, Mathilde, and Misra, Ishan, and Bojanowski, Piotr, and Bordes, Florian and Vincent, Pascal, and Joulin, Armand, and Rabbat, Michael, and Ballas, Nicolas},
booktitle={ECCV},
year={2022},
}
		

			
@inproceedings{zhou2021detecting,
title={Detecting Twenty-thousand Classes using Image-level Supervision},
author={Zhou, Xingyi and Girdhar, Rohit and Joulin, Armand and Kr{\"a}henb{\"u}hl, Philipp and Misra, Ishan},
booktitle={ECCV},
year={2022},
}
		

			
@inproceedings{girdhar2022omnivore,
title={{Omnivore: A Single Model for Many Visual Modalities}},
author={Girdhar, Rohit and Singh, Mannat and Ravi, Nikhila and van der Maaten, Laurens and Joulin, Armand and Misra, Ishan},
booktitle={CVPR},
year={2022},
}
		

			
@inproceedings{cheng2021mask2former,
title={Masked-attention Mask Transformer for Universal Image Segmentation},
author={Bowen Cheng and Ishan Misra and Alexander G. Schwing and Alexander Kirillov and Rohit Girdhar},
booktitle={CVPR},
year={2022},
}
		

			
@inproceedings{misra2021-3detr,
title={{An End-to-End Transformer Model for 3D Object Detection}},
author={Misra, Ishan and Girdhar, Rohit and Joulin, Armand},
booktitle={{ICCV}},
year={2021},
}
		

			
@inproceedings{zhang_depth_contrast,
title={Self-Supervised Pretraining of 3D Features on any Point-Cloud},
author={Zhang, Zaiwei and Girdhar, Rohit and Joulin, Armand and Misra, Ishan},
journal={arXiv preprint arXiv:2101.02691},
year={2021},
}
		

			
@article{morgado2020avid,
title={Audio-Visual Instance Discrimination with Cross-Modal Agreement},
author={Pedro Morgado and Nuno Vasconcelos and Ishan Misra},
year={2020},
journal={https://arxiv.org/abs/2004.12943},
}
		

			
@ InProceedings{morgado2021_robust_xid,
title={Robust Audio-Visual Instance Discrimination},
author={Pedro Morgado, Ishan Misra, Nuno Vasconcelos},
booktitle = {{CVPR}},
year={2021},
}
		

			
@inproceedings{zbontar_barlowtwins,
title={Barlow Twins: Self-Supervised Learning via Redundancy Reduction},
author={Jure Zbontar, Li Jing, Ishan Misra, Yann LeCun, Stephane Deny},
booktitle={ICML},
year={2021},
}
		

			
@inproceedings{caron2020swav,
title={Unsupervised Learning of Visual Features by Contrasting Cluster Assignments},
author={Mathilde Caron, Ishan Misra, Julien Mairal, Priya Goyal, Piotr Bojanowski, Armand Joulin},
year={2020},
booktitle={NeurIPS},
}
		

			
@inproceedings{misra2020pirl,
title={Self-Supervised Learning of Pretext-Invariant Representations},
author={Misra, Ishan and van der Maaten, Laurens},
booktitle={CVPR},
year={2020},
}
		

			
@inproceedings{yan2020cluster,
title={{ClusterFit: Improving Generalization of Visual Representations}},
author={Xueting Yan, Ishan Misra, Abhinav Gupta, Deepti Ghadiyaram, Dhruv Mahajan},
booktitle={CVPR},
year={2020},
}
		

			
@inproceedings{jiang2020grid,
title={In Defense of Grid Features for Visual Question Answering},
author={Huaizu Jiang, Ishan Misra, Marcus Rohrbach, Erik Learned-Miller, Xinlei Chen},
booktitle={CVPR},
year={2020},
}
		

			
@inproceedings{kulkarni20193drel,
title={{3D-RelNet: Joint Object and Relational Network for 3D Prediction}},
author={Nilesh Kulkarni and Ishan Misra and Shubham Tulsiani and Abhinav Gupta},
booktitle={ICCV},
year={2019},
}
		

			
@inproceedings{goyal2019self,
title={{Scaling and Benchmarking Self-Supervised Visual Representation Learning}},
author={Priya Goyal and Dhruv Mahajan and Abhinav Gupta and Ishan Misra},
booktitle={ICCV},
year={2019},
}
		

			
@article{hexiang2018bison,
title={{Binary Image Selection (BISON): Interpretable Evaluation of Visual Grounding}},
author={Hu, Hexiang and Misra, Ishan and van der Maaten, Laurens},
journal={arXiv preprint arXiv:1901.06595},
year={2019},
}
		

			
@inproceedings{devries2019fairness,
title={{Does Object Recognition Work for Everyone?}},
author={Terrance DeVries and Ishan Misra and Changhan Wang and Laurens van der Maaten},
booktitle={CVPR 2019 Workshop on Computer Vision for Global Challenges},
year={2019},
}
		

			
@inproceedings {jiangmainstream18,
title = {Mainstream: Dynamic Stem-Sharing for Multi-Tenant Video Processing},
authors = {Angela Jiang and Daniel L.-K. Wong and Christopher Canel and Ishan Misra and Michael Kaminsky and Michael Kozuch and Padmanabhan Pillai and David G. Andersen and Gregory Ganger},
booktitle = {{USENIX} Annual Technical Conference ({USENIX} {ATC} 18)},
year = {2018},
address = {Boston, MA},
url = {https://www.usenix.org/conference/atc18/presentation/jiang},
publisher = {{USENIX} Association},
}
		

			
@inproceedings{misra2017lba,
Author    = {Ishan Misra and Ross Girshick and Rob Fergus and,
Martial Hebert and Abhinav Gupta and Laurens van der Maaten},
Title     = {{Learning by Asking Questions}},
Booktitle = {{CVPR}},
Year      = {2018},
}
		

			
@inproceedings{debi2017cutpaste,
title={{Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection}},
author={Dwibedi, Debidatta and Misra, Ishan and Hebert, Martial},
booktitle={ICCV},
year={2017},
}
		

			
@inproceedings{misra2017composing,
title={{From Red Wine to Red Tomato: Composition with Context}},
author={Misra, Ishan and Gupta, Abhinav and Hebert, Martial},
booktitle={CVPR},
year={2017},
}
		

			
@inproceedings{misra2016unsupervised,
title={{Shuffle and Learn: Unsupervised Learning using Temporal Order Verification}},
author={Misra, Ishan and Zitnick, C. Lawrence and Hebert, Martial},
booktitle={ECCV},
year={2016},
}
		

			
@inproceedings{MisraNoisy16,
Author =	 {Ishan Misra and C. Lawrence Zitnick and Margaret Mitchell and Ross Girshick},
Booktitle =	 {CVPR},
Title =	 {{Seeing through the Human Reporting Bias:  Visual Classifiers from Noisy Human-Centric Labels}},
Year =	 {2016},
}
,
		

			
@inproceedings{MisraCrossMTL16,
Author =	 {Ishan Misra and Abhinav Shrivastava and Abhinav Gupta and Martial Hebert},
Booktitle =	 {CVPR},
Title =	 {{Cross-stitch Networks for Multi-task Learning}},
Year =	 {2016},
}
,
		

			
@article{mostafazadeh2016generating,
title={Generating Natural Questions About an Image},
author={Mostafazadeh, Nasrin and Misra, Ishan and Devlin, Jacob and Mitchell, Margaret and He, Xiaodong and Vanderwende, Lucy},
journal={arXiv preprint arXiv:1603.06059},
year={2016},
}
,
		

			
@article{ferraro2016visual,
title={Visual storytelling},
author={Ferraro, Francis and Mostafazadeh, Nasrin and Misra, Ishan and Agrawal, Aishwarya and Devlin, Jacob and Girshick, Ross and He, Xiaodong and Kohli, Pushmeet and Batra, Dhruv and Zitnick, C Lawrence and Parikh, Devi and Vanderwende, Lucy and Galley, Michel and Mitchell, Margaret},
journal={arXiv preprint arXiv:1604.03968},
year={2016},
}
		

			
@inproceedings{MisraSSL15,
Author =	 {Ishan Misra and Abhinav Shrivastava and Martial Hebert},
Booktitle =	 {CVPR},
Title =	 {Watch and Learn: Semi-Supervised Learning of Object Detectors from Videos},
Year =	 {2015},
}
,
		

			
@inproceedings{MisraExemplarSelection,
Author =	 {Ishan Misra and Abhinav Shrivastava and Martial Hebert},
Booktitle =	 {IEEE Winter Conference on Applications of Computer Vision (WACV)},
Title =	 {Data-driven Exemplar Model Selection},
Year =	 {2014},
}
,