joslefaure/HERMES

[ICCV'25] HERMES: temporal-coHERent long-forM understanding with Episodes and Semantics

37
/ 100
Emerging

This project helps video analysts, content curators, and researchers understand the complete story within long-form videos like movies or instructional content. It takes a raw video and breaks it down into meaningful, temporally coherent episodes and semantic descriptions, providing a high-level summary that captures the main events and their relationships. This is useful for anyone needing to quickly grasp complex narratives or actions in extensive video footage.

No commits in the last 6 months.

Use this if you need to extract and understand the key events and their chronological order from very long videos, making it easier to summarize or analyze their content.

Not ideal if you are looking for highly granular, second-by-second action recognition or object detection rather than high-level narrative understanding.

video-analysis content-curation narrative-understanding long-form-media semantic-video-segmentation
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

38

Forks

5

Language

Python

License

MIT

Last pushed

Sep 10, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/joslefaure/HERMES"

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