We introduce an object-aware decoder for improving the performance of spatio-temporal
representations on ego-centric videos. The key idea is to enhance object-awareness during …

What will the future be? We wonder! In this survey, we explore the gap between current
research in egocentric vision and the ever-anticipated future, where wearable computing …

This paper focuses on building object-centric representations for long-term action
anticipation in videos. Our key motivation is that objects provide important cues to recognize …

The discussion of compositional generalization in action recognition, ie., Compositional
Action Recognition (CAR), has recently received increasing attention. CAR challenges …

Abstract Current approaches in Group Activity Recognition (GAR) predominantly emphasize
Human Relations (HRs) while often neglecting the impact of Human-Object Interactions …

Video understanding has witnessed significant progress with recent video foundation
models demonstrating strong performance owing to self-supervised pre-training objectives; …

Few-shot action recognition aims at quickly adapting a pre-trained model to the novel data
with a distribution shift using only a limited number of samples. Key challenges include how …

Fine-grained action recognition typically faces challenges with lower inter-class variances
and higher intra-class variances. Supervised contrastive learning is inherently suitable for …

Transformer-based Single Image Deraining (SID) methods have achieved remarkable
success, primarily attributed to their robust capability in capturing long-range interactions …

Video understanding has made huge strides in recent years, relying largely on the power of
the transformer architecture. As this architecture is notoriously expensive and video is highly …