112 citations · 199 across the 10 of their papers we have counts for
16 papers
Loose Social-Interaction Recognition in Real-world Therapy Scenarios
Abid Ali, Rui Dai, Ashish Marisetty +5
The computer vision community has explored dyadic interactions for atomic actions such as pushing, carrying-object, etc. However, with the advancement in deep learning models, ther…
JOADAA: joint online action detection and action anticipation
Mohammed Guermal, Francois Bremond, Rui Dai +1
Action anticipation involves forecasting future actions by connecting past events to future ones. However, this reasoning ignores the real-life hierarchy of events which is conside…
AAN: Attributes-Aware Network for Temporal Action Detection
Rui Dai, Srijan Das, Michael S. Ryoo +1
The challenge of long-term video understanding remains constrained by the efficient extraction of object semantics and the modelling of their relationships for downstream tasks. Al…
Multi-modal Representation Learning for Social Post Location Inference
Ruiting Dai, Jiayi Luo, Xucheng Luo +3
Inferring geographic locations via social posts is essential for many practical location-based applications such as product marketing, point-of-interest recommendation, and infecto…
Human-Scene Network: A Novel Baseline with Self-rectifying Loss for Weakly supervised Video Anomaly Detection
Snehashis Majhi, Rui Dai, Quan Kong +3
Video anomaly detection in surveillance systems with only video-level labels (i.e. weakly-supervised) is challenging. This is due to, (i) the complex integration of human and scene…
THORN: Temporal Human-Object Relation Network for Action Recognition
Mohammed Guermal, Rui Dai, Francois Bremond
Most action recognition models treat human activities as unitary events. However, human activities often follow a certain hierarchy. In fact, many human activities are compositiona…