You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
This project utilizes advanced deep learning techniques to automatically generate contextually relevant captions for videos by extracting spatial and temporal features, while incorporating Gaussian attention to focus on important regions. This enhances video indexing, retrieval, and accessibility for visually impaired individuals.
[Pattern Rcognition 2021] This is the Theano code for our paper "Enhancing the Alignment between Target Words and Corresponding Frames for Video Captioning".
Summary about Video-to-Text datasets. This repository is part of the review paper *Bridging Vision and Language from the Video-to-Text Perspective: A Comprehensive Review*