Humans can naturally and effectively find salient regions in complex scenes. Motivated by
this observation, attention mechanisms were introduced into computer vision with the aim of …

Weakly-supervised temporal action localization aims to recognize and localize action
segments in untrimmed videos given only video-level action labels for training. Without the …

The goal of multimodal summarization is to extract the most important information from
different modalities to form summaries. Unlike unimodal summarization, the multimodal …

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 …

Implicit neural representations (INR) have gained increasing attention in representing 3D
scenes and images, and have been recently applied to encode videos (eg, NeRV, E-NeRV) …

The core of video understanding tasks such as recognition captioning and tracking is to
automatically detect objects or actions in a video and analyze their temporal evolution …

Video transformers have achieved impressive results on major video recognition
benchmarks, which however suffer from high computational cost. In this paper, we present …

Gait recognition, which aims at identifying individuals by their walking patterns, has recently
drawn increasing research attention. However, gait recognition still suffers from the conflicts …

Most existing RGB-D salient object detection (SOD) methods are primarily focusing on cross-
modal and cross-level saliency fusion, which has been proved to be efficient and effective …

Violence recognition is challenging since recognition must be performed on videos acquired
by a lot of surveillance cameras at any time or place. It should make reliable detections in …