Rui Dai 戴瑞

I am currently an applied scientist at Amazon working on computer vision related projects. Prior to joining Amazon, I obtained my doctoral degree in Computer Science from Inria and Université Côte d'Azur under the supervision of Prof. François Brémond (Inria) and Dr. Gianpiero Francesca (Toyota Motor Europe).

My Inria email address is deactivated. Please contact me via

Email  /  CV  /  Google Scholar  /  ResearchGate  /  LinkedIn  /  GitHub  /  Instagram  / 

profile photo

My main research interests are in video understanding, action recognition and multi-modal representation learning.

Toyota Smarthome Untrimmed: Real-World Untrimmed Videos for Activity Detection
Rui Dai, Srijan Das, Saurav Sharma, Luca Minciullo, Lorenzo Garattoni, François Brémond, Gianpiero Francesca.

Project Link / Code
MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection
Rui Dai, Srijan Das, Kumara Kahatapitiya, Michael S. Ryoo, François Brémond.
CVPR 2022

Poster / Code
VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living
Srijan Das, Rui Dai, Di Yang, François Brémond.

An extension of Video Pose Network (ECCV'20) by using our cross-modal knowledge distillation mechanism proposed in ICCV'21.
THORN: Temporal Human Object Relation Network for Action Recognition
Mohammed Guermal, Rui Dai, François Brémond.
ICPR 2022

A continuation of CTRN, Code
CTRN: Class Temporal Relational Network for Action Detection
Rui Dai, Srijan Das, François Brémond.
BMVC 2021, Oral
Learning an Augmented RGB Representation with Cross-Modal Knowledge Distillation for Action Detection
Rui Dai, Srijan Das, François Brémond.
ICCV 2021
PDAN: Pyramid Dilated Attention Network for Action Detection.
Rui Dai, Srijan Das, Luca Minciullo, Lorenzo Garattoni, Gianpiero Francesca and François Brémond.
WACV 2021
Code / Video / Poster
Selective Spatio-Temporal Aggregation Based Pose Refinement System: Towards Understanding Human Activities in Real-World Videos.
Di Yang, Rui Dai, Yaohui Wang, Rupayan Mallick, Luca Minciullo, Gianpiero Francesca, François Brémond.
WACV 2021

Code / Video
VPN: Learning Video-Pose Embedding for Activities of Daily Living
Srijan Das, Saurav Sharma, Rui Dai, François Brémond, Monique Thonnat.
ECCV 2020

Code / Video
Toyota Smarthome: Real World Activities of Daily Living.
Srijan Das, Rui Dai, Michal Koperski, Luca Minciullo, Lorenzo Garattoni, François Brémond and Gianpiero Francesca.
ICCV 2019

Project Link / Code
PhD Thesis

On 13 September, 2022, I defended my PhD in Computer Science from the Spatio-Temporal Activity Recognition Systems (STARS) team of Inria, France. The topic of my Ph.D. was “Action Detection for Untrimmed Videos ” [link]. All the research involved in my thesis was conducted at Inria under the supervision of François Brémond.

The jury of my Ph.D. defense was:

  • President: Ivan Laptev , Professor, Inria Paris / L'École Normale Supérieure
  • Reviewer : Dima Damen, Professor, University of Bristol
  • Reviewer : Karteek Alahari, Research Scientist, Inria Grenoble Rhône-Alpes
  • Examiner : Ming-Hsuan Yang, Professor, Google / University of California Merced
  • Examiner : François Brémond, Research Director, Inria Sophia Antipolis