Heng Wang

Research Scientist @ Facebook AI Research
Menlo Park, CA

https://www.semanticscholar.org/author/Heng-Wang/46506697 http://scholar.google.com/citations?user=ghmgyewAAAAJ&hl=en View Heng Wang's profile on LinkedIn

Short Bio [CV]

I am a research scientist at Facebook AI since 2017. I was research scientist at Amazon Seattle, building computer vision systems for the "Just Walk Out" feature of Amazon Go. Before moving to US, I was a postdoc in the LEAR Team, INRIA with Cordelia Schmid. I received my PhD in Computer Vision from Chinese Academy of Sciences in 2012, and B.S. in Electrical Engineering from Harbin Institute of Technology in 2006.

My research interests range from low-level vision to high-level vision with a focus on video understanding. You can find more detailed information in my CV and my old homepage.

Selected Publications [Semantic Scholar] [Google Scholar]

Unidentified Video Objects: A Benchmark for Dense, Open-World Segmentation
Weiyao Wang, Matt Feiszli, Heng Wang, Du Tran
Technical report, (arXiv), 2021
[Paper]

Is Space-Time Attention All You Need for Video Understanding?
Gedas Bertasius, Heng Wang, Lorenzo Torresani
International Conference on Machine Learning (ICML), 2021
[Paper] [Code] [Facebook AI Blog]

Beyond Short Clips: End-to-End Video-Level Learning with Collaborative Memories
Xitong Yang, Haoqi Fan, Lorenzo Torresani, Larry Davis, Heng Wang
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021
[Paper]

Proposal-based Video Completion
Yuan-Ting Hu, Heng Wang, Nicolas Ballas, Kristen Grauman and Alexander G. Schwing
European Conference on Computer Vision (ECCV), 2020
[Paper]

Video Modeling with Correlation Networks
Heng Wang, Du Tran, Lorenzo Torresani and Matt Feiszli
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020
[Paper]

FASTER Recurrent Networks for Efficient Video Classification
Linchao Zhu, Laura Sevilla-Lara, Du Tran, Matt Feiszli, Yi Yang and Heng Wang
AAAI Conference on Artificial Intelligence (AAAI), 2020
[Paper]

Video Classification with Channel-Separated Convolutional Networks
Du Tran, Heng Wang, Lorenzo Torresani and Matt Feiszli
International Conference on Computer Vision (ICCV), 2019
[Paper] [Code]

Large-scale Weakly-Supervised Pre-training for Video Action Recognition
Deepti Ghadiyaram, Matt Feiszli, Du Tran, Xueting Yan, Heng Wang, and Dhruv Mahajan
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019
[Paper]

Scenes-Objects-Actions: A Multi-Task, Multi-Label Video Dataset
Jamie Ray, Heng Wang, Du Tran, Yufei Wang, Matt Feiszli, Lorenzo Torresani, and Manohar Paluri
European Conference on Computer Vision (ECCV), 2018
[Paper]

A Closer Look at Spatiotemporal Convolutions for Action Recognition
Du Tran, Heng Wang, Lorenzo Torresani, Jamie Ray, Yann LeCun, Manohar Paluri
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018
[Paper] [Project page] [Code]

A Robust and Efficient Video Representation for Action Recognition
Heng Wang, Dan Oneata, Jakob Verbeek, Cordelia Schmid
International Journal of Computer Vision (IJCV), 2016
[Paper]

Action Recognition with Improved Trajectories
Heng Wang, Cordelia Schmid
International Conference on Computer Vision (ICCV), 2013
[Paper] [Project page] [Code]

Dense Trajectories and Motion Boundary Descriptors for Action Recognition
Heng Wang, Alexander Klaser, Cordelia Schmid, Cheng-Lin Liu
International Journal of Computer Vision (IJCV), 2013
[Paper]

Action Recognition by Dense Trajectories
Heng Wang, Alexander Klaser, Cordelia Schmid, Cheng-Lin Liu
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011
[Paper] [Project page] [Code]

Evaluation of Local Spatio-temporal Features for Action Recognition
Heng Wang, Muhammad Muneeb Ullah, Alexander Klaser, Ivan Laptev, Cordelia Schmid
British Machine Vision Conference (BMVC), 2009
[Paper]