I am a Ph.D student of computer science, Shanghai Jiao Tong University. I am a member of MVIGLab mentored by Pro. Cewu Lu. My research interests are in computer vision, especially in video understanding and unsupervised learning.

Now, I’m a research intern at institute of media technology of Huawei Technologies Co Ltd.

News

  • 【2021.3】Paper “PGT: A Progressive Method for Training Models on Long Videos” is accepted as an oral paper in CVPR-2021.
  • 【2020.6.30】Paper “Complex sequential understanding through the awareness of spatial and temporal concepts” won the World Artifical Intelligence Conference Youth Outstanding Paper Award.
  • 【2020.5.6】TubeTK, a one-stage system for multi-object tracking is open-sourced here.
  • 【2020.4.29】An article paper is published in Nature Machine Intelligence. The paper is here. And a read-only link is provided.

Publications


Human Pose Regression with Residual Log-likelihood Estimation
Jiefeng Li, Siyuan Bian, Ailing Zeng, Can Wang, Bo Pang, Wentao Liu, Cewu Lu

IEEE International Conference on Computer Vision (ICCV), 2021 (oral)

[paper] [code]


PGT: A Progressive Method for Training Models on Long Videos
Bo Pang, Gao Peng, Yizhuo Li, Cewu Lu

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021 (oral)

[paper] [code]


TDAF: Top-Down Attention Framework for Vision Tasks
Bo Pang, Yizhuo Li, Jiefeng Li, Muchen Li, Hanwen Cao, Cewu Lu

AAAI Conference on Artificial Intelligence (AAAI), 2021

[paper]


Complex sequential understanding through the awareness of spatial and temporal concepts
Bo Pang, Kaiwen Zha, Hanwen Cao, Jiajun Tang, Minghui Yu, Cewu Lu

Nature Machine Intelligence

[paper] [Read-Only Link] [Arxiv]


TubeTK: Adopting Tubes to Track Multi-Object in a One-Step Training Model
Bo Pang, Yizhuo Li, Yifan Zhang, Muchen Li, Cewu Lu

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020 (oral)

[paper] [code]


Further Understanding Videos through Adverbs: A New Video Task
Bo Pang, Kaiwen Zha, Yifan Zhang, Cewu Lu

AAAI Conference on Artificial Intelligence (AAAI), 2020

[paper]


Deep RNN Framework for Visual Sequential Applications
Bo Pang, Kaiwen Zha, Hanwen Cao, Chen Shi, Cewu Lu

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019

[paper] [Code]


Human Action Adverb Recognition: ADHA Dataset and A Three-Stream Hybrid Model
Bo Pang, Kaiwen Zha, Cewu Lu

IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2018

[paper]


Asynchronous Interaction Aggregation for Action Detection
Jiajun Tang, Jin Xia, Xinzhi Mu, Bo Pang, Cewu Lu

European Conference on Computer Vision (ECCV), 2020

[paper] [code]


ASAP-Net: Attention and Structure Aware Point Cloud Sequence Segmentation
Hanwen Cao, Yongyi Lu, Bo Pang, Cewu Lu, Alan Yuille, Gongshen Liu

British Machine Vision Conference 2020 (BMVC), 2020

[paper]


Efficient 3D Video Engine Using Frame Redundancy
Gao Peng, Bo Pang, Cewu Lu

Winter Conference on Applications of Computer Vision 2021 (WACV), 2021

[paper]


Projects


TubeTK: A one-stage MOT system
Bo Pang, Yizhuo Li, yifan Zhang, Muchen Li, Cewu Lu

AlphaVideo: Video models from MVIG
Bo Pang, Jiajun Tang, Cewu Lu