Rui Dai

I am a Ph.D. student in Computer Vision (CV) and Artificial Intelligence (AI) at the Inria under the supervision of Prof. Francois Bremond. I also have a close collabration with Toyota Motor Europe (TME). Rui Dai's research interests include human action understanding, scene understanding and transfer learning.

I received the Master and Engineer degree in Electronics from Toulouse University. I obtained his Bachelor degree in Computer Science from Beihang University (BUAA) in Beijing, China.

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

profile photo

I'm interested in deep learning methods for computer vision problems such as activity understanding and holistic scene understanding. My research goal is to comprehend how spatio-temporal scene context can help in better understanding of action dynamics. I am also curious about complex interplay and mutual learning of tasks related to different modalities.


  • Feb 2021 - Rui Dai taught 2 Lectures for "MSc DSAI: Deep Learning for Computer Vision" @ 3IA Cote d'Azur.
  • Nov 2020 - Two papers accepted at WACV2021.
  • Nov 2020 - Pre-print Toyota Smarthomes Untrimmed Dataset For Action Detection.
  • Jul 2020 - One Paper accepted at ECCV2020
  • Jun 2019 - One Paper accepted at ICCV2019

Toyota Smarthome Untrimmed: Real-World Untrimmed Videos for Activity Detection
Rui Dai, Srijan Das, Saurav Sharma, Luca Minciullo, Lorenzo Garattoni, Francois Bremond, Gianpiero Francesca.
(Arxiv Pre-print), October 2020

Project Link

Untrimmed daily-living action detection dataset with dense annotations and features several real world challenges

PDAN: Pyramid Dilated Attention Network for Action Detection.
Rui Dai, Srijan Das, Luca Minciullo, Lorenzo Garattoni, Gianpiero Francesca and Francois Bremond.
IEEE Winter Conference on Applications of Computer Vision (WACV'21 ONLINE), 2021

An effective temporal model for action detection using attention mechanism.

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, Francois Bremond.
IEEE Winter Conference on Applications of Computer Vision (WACV'21 ONLINE), 2021

Pose Refinement System (PRS) for handling the object-occluded poses.

VPN: Learning Video-Pose Embedding for Activities of Daily Living
Srijan Das, Saurav Sharma, Rui Dai, Francois Bremond, Monique Thonnat.
16th European Conference on Computer Vision (ECCV'20 ONLINE), 2020

Project Link

Temporal Activity Recognition using RGB videos guided by Human Pose based Attention Network

Smarthome : Real World Activities of Daily Living.
Srijan Das, Rui Dai, Michal Koperski, Luca Minciullo, Lorenzo Garattoni, Francois Bremond and Gianpiero Francesca.
In Proceedings of the 17th International Conference on Computer Vision (ICCV2019), in Seoul, Korea, 2019
Project Link

Real-world smarthome videos for action recognition.

Self-Attention Temporal Convolutional Network for Long-Term Daily Living Activity Detection.
Rui Dai, Luca Minciullo, Lorenzo Garattoni, Gianpiero Francesca and Francois Bremond.
In Proceedings of the 14th IEEE International Conference on Advanced Video and Signal-Based Surveillance (AVSS 2019), in Taipei, Taiwan, 2019 (Oral).
Academic Event Attended


  • Jan 2021 - Feb 2021    Lecture & TA for MSc. Data Science and Artificial Intelligence, at 3IA Cote d’Azur, France.

Theme by jonbarron