With the explosive growth of videos, weakly-supervised temporal action localization (WS-
TAL) task has become a promising research direction in pattern analysis and machine …

Humans commonly work with multiple objects in daily life and can intuitively transfer
manipulation skills to novel objects by understanding object functional regularities. However …

Recognizing the unseen combinations of action and different objects, namely (zero-shot)
compositional action recognition, is extremely challenging for conventional action …

Recognizing and generating object-state compositions has been a challenging task,
especially when generalizing to unseen compositions. In this paper, we study the task of …

Few-shot classification (FSC), which aims to identify novel classes in the presence of a few
labeled samples, has drawn vast attention in recent years. One of the representative few …

Compositional actions consist of dynamic (verbs) and static (objects) concepts. Humans can
easily recognize unseen compositions using the learned concepts. For machines, solving …

Human Action Recognition (HAR) is a vital area of computer vision with diverse applications
in security, healthcare, and human-computer interaction. Addressing the challenges of HAR …

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

Vision-Language Models (VLMs), pre-trained on large-scale datasets, have shown
impressive performance in various visual recognition tasks. This advancement paves the …

Panoramic activity recognition is required to jointly identify multi-granularity human
behaviors including individual actions, group activities, and global activities in multi-person …