H
HourVideo
keshik6/HourVideo
[NeurIPS 2024] Official code for HourVideo: 1-Hour Video Language Understanding
★145stars
Jupyter Notebook
Apache-2.0
Updated: 3d ago
📋 Project at a Glance
Tap to expand
What's this?A open-source Models project, built with Jupyter Notebook, focusing on 1-hour-video-language-understanding and benchmark-dataset
Who made it?Maintained by keshik6 team, 145⭐ on GitHub, #2386 out of 3201 in Models
Why does it exist?In the Models space, 1-hour-video-language-understanding workflows faced efficiency bottlenecks. HourVideo was built by keshik6 to address these benchmark-dataset challenges.
What can it do?Key use cases: egocentric-videos, evals, gemini-pro
How to install with AI?Use an AI coding assistant to follow the README and automatically handle the install and environment setup.
🔗 github.com/keshik6/HourVideo | 官网 https://hourvideo.stanford.edu
🔗 github.com/keshik6/HourVideo | 官网 https://hourvideo.stanford.edu
Topics
1-hour-video-language-understandingbenchmark-datasetegocentric-videosevalsgemini-progpt-4long-context-understandinglong-form-video-language-understandingmultimodal-large-language-modelsmultiple-choice-questionsnavigationneurips-2024perceptionreasoningspatial-intelligencesummarizationvideo-language-understandingvisual-reasoning