Technical Report for Soccernet 2023 -- Dense Video Captioning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ruan, Zheng, Liu, Ruixuan, Chen, Shimin, Zhou, Mengying, Yang, Xinquan, Li, Wei, Chen, Chen, Shen, Wei
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909375749160960
author Ruan, Zheng
Liu, Ruixuan
Chen, Shimin
Zhou, Mengying
Yang, Xinquan
Li, Wei
Chen, Chen
Shen, Wei
author_facet Ruan, Zheng
Liu, Ruixuan
Chen, Shimin
Zhou, Mengying
Yang, Xinquan
Li, Wei
Chen, Chen
Shen, Wei
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2411_00882
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Technical Report for Soccernet 2023 -- Dense Video Captioning
Ruan, Zheng
Liu, Ruixuan
Chen, Shimin
Zhou, Mengying
Yang, Xinquan
Li, Wei
Chen, Chen
Shen, Wei
Computer Vision and Pattern Recognition
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.
title Technical Report for Soccernet 2023 -- Dense Video Captioning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.00882