Semantic-Weighted Spatio-Temporal Graphs for Structured Video Understanding and Captioning

Computer Vision and Image Understanding 2026

View at publisher
Authors: Vibhor Sharma, Anurag Singh, Sabrina Gaito
DOI: 10.1016/j.cviu.2026.104853
Cited by: 1
References: 24

Fields of Study & Subjects

Multimodal Machine Learning Applications Video Analysis and Summarization Human Pose and Action Recognition

Publication details

Journal / source
Computer Vision and Image Understanding
Publisher
Elsevier BV
Volume
270
Pages
104853–104853
Publication date
18 June 2026
Language
EN