Technical Report for Soccernet 2023 -- Dense Video Captioning
Zheng Ruan, Ruixuan Liu, Shimin Chen, Mengying Zhou, Xinquan Yang, Wei, Li, Chen Chen, Wei Shen
TL;DR
This paper presents a method for dense video captioning of soccer videos by generating captions for each action and accurately locating their timestamps using a combination of Blip, sliding windows, and proposal classification.
Contribution
It introduces a novel approach combining Blip with multi-size sliding windows and proposal classification for precise dense captioning in sports videos.
Findings
Effective caption generation for soccer actions
Accurate timestamp localization achieved
Combines multiple techniques for improved performance
Abstract
In the task of dense video captioning of Soccernet dataset, we propose to generate a video caption of each soccer action and locate the timestamp of the caption. Firstly, we apply Blip as our video caption framework to generate video captions. Then we locate the timestamp by using (1) multi-size sliding windows (2) temporal proposal generation and (3) proposal classification.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsVideo Analysis and Summarization · Multimodal Machine Learning Applications · Human Pose and Action Recognition
MethodsBLIP: Bootstrapping Language-Image Pre-training