Jingwen Wang (王景文)

I am committed to delivering the best media content to billions of people, with cutting-edge multi-media understanding and enhancement technology.

I am currently a senior algorithm engineer at Tencent Cloud, working on real-world video restoration and super-resolution, in both livestreaming and offline video scenarios. Our developed media processing services have been widely recognized and applied to many well-known enterprises and products, including but not limited to Douyin Live(抖音直播), Shipinhao(视频号), Rednote(小红书), SeaArt(海艺).

I was previously a senior algorithm engineer at Huya Inc. (2021 ~ 2025), Bigo (2021) and a senior researcher at Tencent AI Lab (2018 ~ 2021).

In 2018, I received my Ph.D. degree from the Department of Computer Science and Technology, South China University of Technology, Guangzhou, China. During 2017 and 2018, I worked as a research intern under the supervision of Lin Ma in Tencent AI Lab. During 2015 and 2017 I was also a research intern in Microsoft Research Asia and worked closely with Tao Mei and Jianlong Fu.

news

Jul 16, 2026	Good News! Our developed game livestreaming service ranks 1st among all cloud service suppliers for Douyin (抖音直播, Chinese-version Tictok), with respect to picture clarity and quality, showcasing the leading advantage of our developed real-time generative enhancement and super-resolution algorithms.
Jun 25, 2025	I joined Tencent Cloud as a senior algorithm engineer focusing on real-world super resolution and restoration. We develop impactive and cutting-edge media processing algorithms and services to serve hundreds of our customers.
Jun 11, 2021	I joined Huya Inc. Incorporation, and focus on livestreaming restoration and super-resolution, video quality assessment, multi-modal understanding.
Dec 01, 2020	I joined Bigo as a staff algorithm engineer. My research interest includes multi-modal understanding. We developed AI algorithms to improve media content understanding and recommendation (mainly shorts and livestreaming).
Jul 17, 2018	I joined Tencent AI Lab as a senior researcher. My research interest includes video captioning, video grounding, and multi-modal understanding.
Jul 25, 2017	I joined Tencent AI Lab, Computer Vision Group, as a research intern under the supervision of Lin Ma. My research interest includes video captioning, and video grounding.
Oct 20, 2015	I joined Multimedia Search and Mining, Microsoft Research Asia, as a research intern under the supervision of Jianlong Fu and Tao Mei. My research interest includes visual sentiment analysis, and finegrained image classification.

awards

2024	Outstanding Employee of Intelligent Media Group (4/70), Huya Inc., 2024.
2019	Outstanding Employee of Strategic Bussiness, Tencent AI Lab, Tencent Inc., 2019.
2019	ACM Guangzhou Chapter Doctoral Dissertation Award, 2019.
2018	Gold Medal of the 2nd Youtube-8M Video Understanding Challenge (Rank 4/312), 2018.
2016	National Scholarship for Ph.D. Students (Top 1%), Ministry of Education of China, 2016.
2011	National Scholarship for Undergraduate Students (Top 1%), Ministry of Education of China, 2011.

publications

Bidirectional attentive fusion with context gating for dense video captioning

Jingwen Wang, Wenhao Jiang, Lin Ma, Wei Liu, and Yong Xu

In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018

PDF Code
Temporally Grounding Language Queries in Videos by Contextual Boundary-aware Prediction

Jingwen Wang, Lin Ma, and Wenhao Jiang

In The AAAI Conference on Artificial Intelligence (AAAI), 2019

PDF Code
Beyond object recognition: Visual sentiment analysis with deep coupled adjective and noun neural networks

Jingwen Wang, Jianlong Fu, Yong Xu, and Tao Mei

In International Joint Conference on Artificial Intelligence (IJCAI), 2016

PDF
Recurrent Exposure Generation for Low-Light Face Detection

Jinxiu Liang, Jingwen Wang, Yuhui Quan, Tianyi Chen, Jiaying Liu, and 2 more authors

IEEE Transactions on Multimedia (TMM), 2020

PDF Code
MARN: multi-level attentional reconstruction networks for weakly supervised video temporal grounding

Yijun Song, Jingwen Wang, Lin Ma, Jun Yu, Jinxiu Liang, and 2 more authors

Neurocomputing, 2023

PDF
Semantic Conditioned Dynamic Modulation for Temporal Sentence Grounding in Videos

Yitian Yuan, Lin Ma, Jingwen Wang, Wei Liu, and Wenwu Zhu

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2020

PDF Code
Semantic Conditioned Dynamic Modulation for Temporal Sentence Grounding in Videos

Yitian Yuan, Lin Ma, Jingwen Wang, Wei Liu, and Wenwu Zhu

In Advances in Neural Information Processing Systems (NeurIPS), 2019

PDF Code
Controllable video captioning with pos sequence guidance based on gated fusion network

Bairui Wang, Lin Ma, Wei Zhang, Wenhao Jiang, Jingwen Wang, and 1 more author

In IEEE/CVF International Conference on Computer Vision (ICCV), 2019

PDF Code
Deep bilateral retinex for low-light image enhancement

Jinxiu Liang, Yong Xu, Yuhui Quan, Jingwen Wang, Haibin Ling, and 1 more author

arXiv preprint arXiv:2007.02018, 2020

PDF
Controllable Video Captioning with an Exemplar Sentence

Yitian Yuan, Lin Ma, Jingwen Wang, and Wenwu Zhu

In Proceedings of the ACM International Conference on Multimedia (ACMMM), 2020

PDF Code
Sth: Spatio-temporal hybrid convolution for efficient action recognition

Xu Li, Jingwen Wang, Lin Ma, Kaihao Zhang, Fengzong Lian, and 2 more authors

arXiv preprint arXiv:2003.08042, 2020

PDF
Non-local netvlad encoding for video classification

Yongyi Tang, Xing Zhang, Lin Ma, Jingwen Wang, Shaoxiang Chen, and 1 more author

In Proceedings of the European Conference on Computer Vision (ECCV) Workshops, 2018

PDF