Overview
Who this competition fits
适合做过视频理解或多模态内容分析、能够结合视频标题与带时间戳的OCR字幕进行文本生成的人。也适合熟悉结构化预测输出、能按指定JSONL格式整理每个视频看点及起始位置的参赛者。
Read the original official blurb
本任务会给出视频、视频标题、视频字幕,要求参赛选手基于提供的信息提取出视频的所有看点,并给出所有看点的起始时间和看点摘要。 Official tags: 自然语言处理. Sign-ups: 194.
Resources
What this competition gives you
Taken from the competition's official page.
Preparation
From registration to a first submission
- 01
视频内容理解
- 02
OCR字幕处理
- 03
时间序列定位
- 04
文本摘要生成
- 05
JSONL文件生成
- 06
ROUGE评测
Before you commit: 难点在于同时完成“找全并定位看点”和“为每个看点写出合适摘要”:起始位置与摘要分别评测,且字幕时间以帧数给出、需要对应到视频时间。提交还必须严格保持测试集URL顺序,并将同一视频的看点按出现先后排序。
Source
How this page was assembled
Competition information is structured from the official page. Scores are platform estimates for decision support; official rules take precedence.
- Official competition page
- Baidu AI Studio
- Last checked
- Not recorded