Human action anticipation aims at predicting what people will do in the future based on past
observations. In this paper we introduce Uncertainty-aware Action Decoupling Transformer …

Building upon the impressive success of CLIP (Contrastive Language-Image Pretraining),
recent pioneer works have proposed to adapt the powerful CLIP to video data, leading to …

We introduce a novel bottom-up approach for human body mesh reconstruction, specifically
designed to address the challenges posed by partial visibility and occlusion in input images …

Abstract Human Action Recognition (HAR) is a challenging domain in computer vision,
involving recognizing complex patterns by analyzing the spatiotemporal dynamics of …

An automatic vision-based sewer inspection plays a vital role of sewage system in a modern
city. Existing methods have utilized evidential deep learning to construct trusted models …

Scene knowledge plays an important role in visual analysis. For the task of action
recognition, human activities often occur in specific scenes. However, it should be …

Biometric recognition has primarily addressed closed-set identification, assuming all probe
subjects are in the gallery. However, most practical applications involve open-set biometrics …

Integrating deep learning and causal discovery has increased the interpretability of
Temporal Action Segmentation (TAS) tasks. However, frame-level causal relationships exist …

Computer vision systems have witnessed rapid progress over the past two decades due to
multiple advances in the field. As these systems are increasingly being deployed in high …

Spatial contexts, such as the backgrounds and surroundings, are considered critical in
Human-Object Interaction (HOI) recognition, especially when the instance-centric …