In recent years, deep learning techniques have excelled in video action recognition.
However, currently commonly used video action recognition models minimize the …

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

Human action recognition (HAR) is one of most important tasks in video analysis. Since
video clips distributed on networks are usually untrimmed, it is required to accurately …

Sensor-based human activity recognition (HAR) requires the acquisition of channel state
information (CSI) data with time series based on sensors to predict human behavior. Many …

Abstract Real-time Action Recognition (ActRgn) of assembly workers can timely assist
manufacturers in correcting human mistakes and improving task performance. Yet …

To deal with the challenges in video object detection (VOD), such as occlusion and motion
blur, many state-of-the-art video object detectors adopt a feature aggregation module to …

In the field of action recognition, video clips are always treated as ordered frames for
subsequent processing. To achieve spatio-temporal perception, existing approaches …

The temporal action segmentation task segments videos temporally and predicts action
labels for all frames. Fully supervising such a segmentation model requires dense frame …

To leverage the strong cross-frame relations of videos, many video semantic segmentation
methods tend to explore feature reuse and feature warping based on motion clues …

Weakly-supervised Temporal Action Localization (W-TAL) aims to train a model to localize
all action instances potentially from different classes in an untrimmed video, using a training …