Scholar
Ting Yao
Google Scholar ID: 7Yc6yssAAAAJ
HiDream.ai, previously JD.com and Microsoft Research
Citations & Impact
Citations
17,944
H-index
58
i10-index
132
Publications
20
Co-authors
0
Contact
Publications
Resume (English only)
Academic Achievements
- 2022 Chinese Intelligent Computing Technology Innovator
- 2022 First Grade Scientific and Technology Prize, China Society of Image and Graphics (CSIG) – “Key Technologies and Applications of Ultrafine Image Recognition”
- 2022 IEEE ICME Multimedia Star Innovator Award – for outstanding innovative contribution in Multimedia Intelligence
- 2022 Nicolas D. Georganas Best Paper Award, ACM TOMM – “Smart Director: An Event-Driven Directing System for Live Broadcasting”
- 2019 IEEE Computer Society TCMC Rising Star Award – for contributions in video content recognition and description generation
- 2019 ACM SIGMM Rising Star Award – for contributions in activity recognition and video captioning
- 2015 ACM SIGMM Outstanding Ph.D. Thesis Award – “Multimedia Search by Self, External, and Crowdsourcing Knowledge”
- 2021 Best Open Source Award, ACM MM – “X-modaler: A Versatile and High-performance Codebase for Cross-modal Analytics”
- 2021 Outstanding Associate Editor, IEEE Transactions on Multimedia
- 2019 Second Place Best Demo Award, ACM MM – “Animating Your Life: Real-Time Video-to-Animation Translation”
- 2016 Best Paper Finalist, ACM ICMR
- 2013 Best Paper Award, ICIMCS
- Champion in 10+ international multimedia analytics competitions
- Rank 1, No Interaction Track, ICLR 2022 Workshop on Generalizable Policy Learning in the Physical World
- Rank 1, No Restriction Track, ICLR 2022 Workshop on Generalizable Policy Learning in the Physical World
Background
- Currently Co-Founder and CTO of HiDream.ai, leading it to become China's top Generative AI company.
- Research interests include video content understanding, video captioning, multimodal analytics, and spatiotemporal modeling.
- Co-authored over 100 peer-reviewed papers in top-tier conferences and journals.
- His Pseudo-3D network has become a standard 3D convolutional architecture for spatiotemporal data analysis.
- His MSR-VTT video-to-text dataset is used by 500+ institutions worldwide.
- His research has led to multiple commercial products with millions of daily active users.
- Serves as Associate Editor for IEEE Transactions on Multimedia, Pattern Recognition Letters, and Multimedia Systems; frequently acts as Area Chair and keynote/tutorial speaker at major conferences.
Co-authors