TheShadow29/vognet-pytorch

[CVPR20] Video Object Grounding using Semantic Roles in Language Description (https://arxiv.org/abs/2003.10606)

35
/ 100
Emerging

This tool helps researchers and video analysts pinpoint specific objects within a video based on a descriptive sentence. You input a video and a natural language query (e.g., "the person kicking the red ball"), and it outputs the exact location of the described object in each frame. It's designed for computer vision researchers or content analysis professionals working with video data.

No commits in the last 6 months.

Use this if you need to precisely locate objects in video clips using natural language descriptions, especially for research in video understanding or content analysis.

Not ideal if you need a plug-and-play solution for general video search or a tool that doesn't require technical setup and data preparation.

video-analysis object-localization content-understanding video-search computer-vision-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

69

Forks

7

Language

Python

License

MIT

Last pushed

Jun 10, 2020

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/TheShadow29/vognet-pytorch"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.