Temporal action segmentation (TAS) in videos aims at densely identifying video frames in
minutes-long videos with multiple action classes. As a long-range video understanding task …

Temporal action segmentation is crucial for understanding long-form videos. Previous works
on this task commonly adopt an iterative refinement paradigm by using multi-stage models …

With advances in data-driven machine learning research, a wide variety of prediction
models have been proposed to capture spatio-temporal features for the analysis of video …

Identifying human action segments in an untrimmed video is still challenging due to
boundary ambiguity and over-segmentation issues. To address these problems, we present …

To improve the performance of salient object detection (SOD) in scenes with low-light
conditions (eg, nighttime) and cluttered backgrounds, infrared thermal images are used to …

Temporal receptive fields of models play an important role in action segmentation. Large
receptive fields facilitate the long-term relations among video clips while small receptive …

Temporal/spatial receptive fields of models play an important role in sequential/spatial tasks.
Large receptive fields facilitate long-term relations, while small receptive fields help to …

Inspired by human neurological structures for action anticipation, we present an action
anticipation model that enables the prediction of plausible future actions by forecasting both …

Image salient object detection (SOD) is an active research topic in computer vision and
multimedia area. Fusing complementary information of RGB and depth has been …

Gesture recognition is a much studied research area which has myriad real-world
applications including robotics and human-machine interaction. Current gesture recognition …