Dense-Captioning Events in Videos: SYSU Submission to ActivityNet Challenge 2020
arXiv:2006.11693
Abstract
This technical report presents a brief description of our submission to the dense video captioning task of ActivityNet Challenge 2020. Our approach follows a two-stage pipeline: first, we extract a set of temporal event proposals; then we propose a multi-event captioning model to capture the event-level temporal relationships and effectively fuse the multi-modal information. Our approach achieves a 9.28 METEOR score on the test set.
Second-place solution to TASK 2 (Dense video captioning) in ActivityNet Challenge 2020. Code is available at https://github.com/ttengwang/dense-video-captioning-pytorch