Chen Zhao

Research Scientist

King Abudullah University of Science and Technology

Biography

Chen Zhao is Research Scientist at King Abdullah University of Science and Technology (KAUST), and Leader of the Video Theme in Image and Video Understanding Lab (IVUL) with Prof. Bernard Ghanum. She obtained her Ph.D from Peking University (PKU), advised by Prof. Wen Gao. Her research interests include computer vision, deep learning, image/video understanding, image/video processing.

Interests

Video Action Detection
Computer Vision
Deep Learning
Image/video understanding
Image/video Processing

Education

Ph.D. in Computer Science, 2016
Peking University, Beijing, China
Research Intern, 2016
National Institute of Informatics, Tokyo, Japan
CSC Joint Ph.D. student, 2012
University of Washington, Seattle, USA
B.Eng. in Software Engineering, 2010
Sichuan University, Chengdu, China

News

2022

[2022-07-04] R-DFCIL and EASEE were accepted into ECCV'22!

[2022-06-21] Ego4D got into CVPR'22 Best Paper Finalist!

[2022-04-18] All Ego4D challenges are live now!

[2022-03-29] Ego4D was accepted to CVPR'22 as ORAL presentation!

[2022-03-29] MAD was accepted to CVPR'22!

2021

[2021-10-15] Ego4D was released and paper on arxiv!

[2021-07-23] VSGN was accepted to ICCV'21!

[2021-05-20] I was recognized by CVPR’21 as Outstanding Reviewer.

2020

[2020-10-13] I presented our work ThumbNet on ACM Multimedia 2020.

[2020-07-29] ThumbNet was accepted to ACM MM'20.

[2020-06-07] We won the 2‑nd place in the HACS’20 Weakly‑supervised action detection Challenge.

[2020-02-27] G-TAD was accepted to CVPR'20!

2019

[2019-10-23] Our paper for YouTube-8M challenge got accepted as oral presentation in ICCV'19 Workshop!

[2019-10-12] We missed the gold medal by only 0.0004 in Kaggle’s 3rd YouTube‑8M Video Understanding Challenge; rank 9/11 out of 283 teams in the public/private leaderboards.

Projects

Video Self-Stitching Graph Network for Temporal Action Localization

Short actions are critical and challenging in the task of action localization. We target this problem and propose a video self-stitching graph network (VSGN), which enhances short action by video self-stitching (VSS) and a cross-scale graph pyramid network (xGPN).

Chen Zhao, Ali Thabet, Bernard Ghanem

Video Self-Stitching Graph Network for Temporal Action Localization

G‑TAD: Sub‑Graph Localization for Temporal Action Detection

The first work on snippet-level GCN for video temporal action detection (TAD). Cast TAD as a sub-graph localization problem to aggregate multi-level semantic context, which is important but ignored in previous works. Design a GCNeXt block and an SGAlign layer.

Mengmeng Xu, Chen Zhao, David Rojas Blanco, Ali Thabet, Bernard Ghanem

G‑TAD: Sub‑Graph Localization for Temporal Action Detection

Publications

Qiankun Gao, Chen Zhao, Bernard Ghanem, Jian Zhang (2022). R-DFCIL: Relation-Guided Representation Learning for Data-Free Class Incremental Learning. ECCV'22.

Juan Leon Alcazar, Moritz Cordes, Chen Zhao, Bernard Ghanem (2022). End-to-End Active Speaker Detection. ECCV'22.

Shuming Liu, Mengmeng Xu, Chen Zhao, Xu Zhao, Bernard Ghanem (2022). ETAD: A Unified Framework for Efficient Temporal Action Detection. arxiv'22.

Mattia Soldan, Alejandro Pardo, Juan Leon Alcazar, Fabian Caba Heilbron, Chen Zhao, Silvio Giancola, Bernard Ghanem (2022). MAD: A scalable dataset for language grounding in videos from movie audio descriptions. CVPR'22.

PDF Cite Project

Kristen Grauman, Andrew Westbury, Eugene Byrne*, Zachary Chavis*, Antonino Furnari*, Rohit Girdhar*, Jackson Hamburger*, Hao Jiang*, Miao Liu*, Xingyu Liu*, Miguel Martin*, Tushar Nagarajan*, Ilija Radosavovic*, Santhosh Kumar Ramakrishnan*, Fiona Ryan*, Jayant Sharma*, Michael Wray*, Mengmeng Xu, Eric Zhongcong Xu*, Chen Zhao, Siddhant Bansal, Dhruv Batra, Vincent Cartillier, Sean Crane, Tien Do, Morrie Doulaty, Akshay Erapalli, Christoph Feichtenhofer, Adriano Fragomeni, Qichen Fu, Abrham Gebreselasie, Cristina Gonzalez, James Hillis, Xuhua Huang, Yifei Huang, Wenqi Jia, Weslie Khoo, Jachym Kolar, Satwik Kottur, Anurag Kumar, Federico Landini, Chao Li, Yanghao Li, Zhenqiang Li, Karttikeya Mangalam, Raghava Modhugu, Jonathan Munro, Tullie Murrell, Takumi Nishiyasu, Will Price, Paola Ruiz Puentes, Merey Ramazanova, Leda Sari, Kiran Somasundaram, Audrey Southerland, Yusuke Sugano, Ruijie Tao, Minh Vo, Yuchen Wang, Xindi Wu, Takuma Yagi, Ziwei Zhao, Yunyi Zhu, Pablo Arbelaez+, David Crandall+, Dima Damen+, Giovanni Maria Farinella+, Christian Fuegen+, Bernard Ghanem+, Vamsi Krishna Ithapu+, C. V. Jawahar+, Hanbyul Joo+, Kris Kitani+, Haizhou Li+, Richard Newcombe+, Aude Oliva+, Hyun Soo Park+, James M. Rehg+, Yoichi Sato+, Jianbo Shi+, Mike Zheng Shou+, Antonio Torralba+, Lorenzo Torresani+, Mingfei Yan+, Jitendra Malik (2022). Ego4D: Around the World in 3,000 Hours of Egocentric Video. CVPR'22.

PDF Cite Project

Merey Ramazanova, Victor Escorcia, Fabian Caba Heilbron, Chen Zhao, Bernard Ghanem (2022). Owl (observe, watch, listen): Localizing actions in egocentric video via audiovisual temporal context. arXiv'22.

Chen Zhao, Merey Ramazanova, Mengmeng Xu, Bernard Ghanem (2022). SegTAD: Precise Temporal Action Detection via Semantic Segmentation. arXiv'22.

Guocheng Qian, Xuanyang Zhang, Guohao Li, Chen Zhao, Yukang Chen, Xiangyu Zhang, Bernard Ghanem, Jian Sun (2022). When NAS Meets Trees: An Efficient Algorithm for Neural Architecture Search. arXiv'22.

Chen Zhao, Ali Thabet, Bernard Ghanem (2021). Video Self‑Stitching Graph Network for Temporal Action Localization. ICCV'21.

PDF Cite Code Video

Chen Zhao, Bernard Ghanem (2020). ThumbNet: One Thumbnail Image Contains All You Need for Recognition. ACM MM'20.

Mengmeng Xu, Chen Zhao, Merey Ramazanova, David S. Rojas, Ali Thabet, Bernard Ghanem (2020). Improve Baseline for Temporal Action Detection: HACS Challenge 2020 Solution of IVUL‑KAUST team. CVPRW'20.

Jian Zhang, Chen Zhao, Wen Gao (2020). Optimization‑Inspired Compact Deep Compressive Sensing. JSTSP.

PDF Cite Code Project

Mengmeng Xu, Chen Zhao, David Rojas Blanco, Ali Thabet, Bernard Ghanem (2020). G‑TAD: Sub‑Graph Localization for Temporal Action Detection. CVPR'20.

PDF Cite Code Project Slides Video

Merey Ramazanova, Chen Zhao, Mengmeng Xu, Humam Alwassel, Sara Rojas Martinez, Fabian Caba, Bernard Ghanem (2019). Logistic Regression is Still Alive and Effective: The 3rd YouTube 8M Challenge Solution of the IVUL‑KAUST team. ICCVW'19.

Chen Zhao, Jian Zhang, Ronggang Wang, Wen Gao (2018). CREAM: CNN-REgularized ADMM framework for compressive-sensed image reconstruction. IEEE Access.

Chen Zhao, Jian Zhang, Ronggang Wang, Wen Gao (2018). BoostNet: A Structured Deep Recursive Network to Boost Image Deblocking. VCIP'18.

Chen Zhao, Ronggang Wang, and Wen Gao (2017). Better and Faster, when ADMM Meets CNN: Compressive-sensed Image Reconstruction. PCM'17.

Chen Zhao, Jian Zhang, Siwei Ma, Xiaopeng Fan, Yongbing Zhang, Wen Gao (2017). Reducing Image Compression Artifacts by Structural Sparse Representation and Quantization Constraint Prior. TCSVT.

Chen Zhao, Siwei Ma, Jian Zhang, Ruiqin Xiong and Wen Gao (2017). Video Compressive Sensing Reconstruction via Reweighted Residual Sparsity. TCSVT.

Jian Zhang, Ruiqin Xiong, Chen Zhao, Yongbing Zhang, Siwei Ma, Wen Gao (2016). CONCOLOR: COnstrained Non-Convex Low-Rank Model for Image Deblocking. TIP.

Chen Zhao, Jian Zhang, Siwei Ma and Wen Gao (2016). Nonconvex Lp Nuclear Norm based ADMM Framework for Compressive Sensing. DCC'16.

Chen Zhao, Jian Zhang, Siwei Ma and Wen Gao (2016). Compressive-Sensed Image Coding via Stripe-based DPCM. DCC'16.

Chen Zhao, Jian Zhang, Siwei Ma, Ruiqin Xiong, Wen Gao (2015). A Dual Structured-Sparsity Model for Compressive-Sensed Video Reconstruction. VCIP'15.

Chen Zhao, 马思伟, 张新峰, 张健, 高文 (2015). 基于云数据的高效图像编码方法. 计算机学报.

Chen Zhao, Siwei Ma, Wen Gao (2014). Thousand to one: An image compression system via cloud search. MMSP'15.

Haoming Chen, Chen Zhao, Ming-Ting Sun and Aaron Drake (2014). Adaptive intra-refresh for low-delay error-resilient video coding. JVCIR.

Chen Zhao, Siwei Ma, Wen Gao (2014). Video Compressive Sensing via Structured Laplacian Modelling. VCIP'14.

Haoming Chen, Chen Zhao, Ming-Ting Sun, Aaron Drake (2014). Adaptive intra-refresh for low-delay error-resilient video coding0. APSIPA'14.

Chen Zhao, Siwei Ma, Wen Gao (2014). Image Compressive-Sensing Recovery Using Structured Laplacian Sparsity in DCT Domain and Multi-Hypothesis Prediction. ICME'14.

Jian Zhang, Chen Zhao, Debin Zhao, Wen Gao (2014). Image Compressive Sensing Recovery Using Adaptively Learned Sparsifying Basis via L0 Minimization. SP.

Luming Zhang, Mingli Song, Yi Yang, Qi Zhao, Chen Zhao, Nicu Sebe (2014). Weakly Supervised Photo Cropping. TMM.

Chen Zhao, Jian Zhang, Siwei Ma and Wen Gao (2013). Wavelet Inpainting Driven Image Compression via Collaborative Sparsity at Low Bit Rates. ICIP'13.

Chen Zhao, Siwei Ma, Jian Zhang and Wen Gao (2013). A Highly Effective Error Concealment Method for Whole Frame Loss. ISCAS'13.

Jian Zhang, Chen Zhao, Ruiqin Xiong, Siwei Ma and Debin Zhao (2012). Image Super-Resolution via Dual-Dictionary Learning and Sparse Representation. ISCAS'12.

Jian Zhang, Ruiqin Xiong, Chen Zhao, Siwei Ma, Debin Zhao (2012). Exploiting Image Local and Nonlocal Consistency for Mixed Gaussian-Impulse Noise Removal. ICME'12.

Jian Zhang, Debin Zhao, Chen Zhao, Ruiqin Xiong, Siwei Ma and Wen Gao (2012). Compressed Sensing Recovery via Collaborative Sparsity. DCC'12.

Jian Zhang, Debin Zhao, Chen Zhao, Ruiqin Xiong, Siwei Ma, Wen Gao (2012). Image Compressive Sensing Recovery via Collaborative Sparsity. JETCAS.

Skills

Python

100%

Pytorch

100%

Matlab

70%

C++

70%

Contact

chen.zhao@kaust.edu.sa
KAUST, Thuwal, 23955
Enter Building 1 Level 2, Seaside