Bolei Zhou


- I am the 4th-year Ph.D. Candidate in Computer Science and Artificial Intelligence Laboratory (CSAIL) at MIT, advised by Prof. Antonio Torralba. I got the M.Eng. in Information Engineering at CUHK in July 2012 and B.Eng. in Biomedical Engineering at SJTU in June 2010.
- My research is on computer vision and machine learning, particularly I am interested in deep learning and high-level vision & AI tasks like scene understanding and visual intelligence.
- I've had internships at Facebook AI Research, eBay Research Labs, Microsoft Research Asia, and Barclays Capital.


[2016/10/22] MIT CSAIL News covered on the scene parsing and scene classification challenges.
[2016/10/10] I gave a talk titled Challenges in Deep Sceen Understanding at ECCV'16 ILSVRC and COCO workshop, on the overview and the results of the scene classification challenge 2016 and the scene parsing challenge 2016..
[2016/10/06] Places2 paper is online. Details about the dataset construction and the Places365-CNNs are included.
[2016/09/26] Results of the Places2 Scene Classification 2016 and Scene Parsing Challenge 2016 are released. Congratulations to the winners and thanks to all the participants!
[2016/06/23] Scene Parsing Challenge 2016 is online. Data and toolkit are released. Winners will be announced mid September and invited to give presentations at ILSVRC and COCO joint workshop at ECCV'16.
[2016/06/15] I am co-organizing ILSVRC'16 challenge. Come to compete! There are two scene-centric tasks, scene classification and scene parsing, in ILSVRC this year.
[2016/05/12] Places Challenge 2016 is coming at ECCV'16, to be jointly held at ILSVRC and COCO workshop. We release the CNNs trained on Places365 (new Places2 data).
[2016/02/29] Class Activation Mapping is accepted to CVPR'16. CNN models and sample codes are released at project page.
[2016/02/09] I am co-organizing the weekly MIT Vision Seminar. Welcome to visit us and give a talk about your research.
[2015/12/28] I won Facebook Graduate Fellowship. Thank Facebook AI Research for the support!
[2015/12/08] Simple baseline model for visual QA is released on arXiv. Interactive Demo and source code are available.
[2015/09/29] I am Teaching Assistant for MIT course Advances in Computer Vision. In the course we are hosting a Mini-Places Scene Classification Challenge for educational purpose.
[2015/08/31] We are organizing the Places2 Scene Classification Challenge, held in conjunction with ILSVRC at ICCV 2015. There are more than 8 million training images from 401 scene categories! The deadline for submission is November 13, 2015.
[2015/05/07] Our recent work on object detectors emerge in CNNs was featured in Techcrunch and MIT News.

Selected Publications

full list
B. Zhou, A. Khosla, A. Lapedriza, A. Torralba, and A. Oliva.
Places: An Image Database for Deep Scene Understanding.
arXiv:1610.02055, 2016.
[PDF][Places2 Dataset][Challenge Page][Places365 CNN models][Demo]
B. Zhou, H. Zhao, X. Puig, S. Fidler, A. Barriuso and A. Torralba.
Semantic Understanding of Scenes through ADE20K Dataset.
arXiv:1608.05442, 2016.
[PDF][Dataset][Benchmark Page][Challenge Page][Toolkit&Code][Demo]
B. Zhou, A. Khosla, A. Lapedriza, A. Oliva, and A. Torralba
Learning Deep Features for Discriminative Localization.
Computer Vision and Pattern Recognition (CVPR), 2016 (arXiv:1512.04150)
[PDF] [arXiv][Project Page][Video of CNN shifting its attention]
D. Wei, B. Zhou, A. Torralba, W. Freeman
Understanding Intra-Class Knowledge inside CNN.
arXiv:1507.02379, 2015.
B. Zhou, Y. Tian, S. Suhkbaatar, A. Szlam, R. Fergus
Simple Baseline for Visual Question Answering.
arXiv:1512.02167, 2015.
Z. Wang, B. Zhou, S. Jegelka
Optimization as Estimation with Gaussian Processes in Bandit Settings.
Artificial Intelligence and Statistics (AISTATS'16) as oral, 2016. (arXiv:1510.06423)
B. Zhou, A. Khosla, A. Lapedriza, A. Oliva, and A. Torralba
Object Detectors Emerge in Deep Scene CNNs.
International Conference on Learning Representations (ICLR) as oral, 2015.(arXiv:1412.6856)
[PDF][Project Page][More Visualization]
B. Zhou, V. Jagadeesh, and R. Piramuthu
ConceptLearner: Discovering Visual Concepts from Weakly Labeled Image Collections.
Computer Vision and Pattern Recognition (CVPR), 2015.(arXiv:1411.5319)
[PDF][Project Page & Demo]
B. Zhou, A. Lapedriza, J. Xiao, A. Torralba, and A. Oliva
Learning Deep Features for Scene Recognition using Places Database.
Advances in Neural Information Processing Systems 27 (NIPS) spotlight, 2014.
[PDF][Project Page][Demo]
B. Zhou, L. Liu, A. Oliva and A. Torralba
Recognizing City Identity via Attribute Analysis of Geo-tagged Images.
Proceedings of 13th European Conference on Computer Vision (ECCV) , 2014.
[PDF][Project Page]
L.Liu, B. Zhou, J. Zhao, B.D.Ryan
C-IMAGE: City Cognitive Mapping through Geo-tagged Photos
GeoJournal, Springer, 2016.
B. Zhou, X. Tang, H. Zhang and X. Wang
Measuring Crowd Collectiveness.
IEEE transaction on Pattern Analysis and Machine Intelligence (PAMI), 2014.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) oral, 2013.
[PDF(CVPR)][PDF(TPAMI)][Project Page]
B. Zhou, X. Tang and X. Wang.
Learning Collective Crowd Behaviors with Dynamic Pedestrian-Agents.
International Journal of Computer Vision (IJCV), 2014.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) oral, 2012.
[PDF(CVPR)] [PDF(IJCV)][Project Page]
B. Zhou, X. Tang and X. Wang.
Coherent Filtering: Detecting Coherent Motions from Crowd Clutters.
In Proceedings of 12th European Conference on Computer Vision (ECCV), 2012.
[PDF] [Project Page]
B. Zhou, X. Wang and X. Tang.
Random Field Topic Model for Semantic Region Analysis in Crowded Scenes from Tracklets.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011.
[PDF][Project Page]

Other projects and codes


Professional activities


Personal interests