joslefaure/HERMES
[ICCV'25] HERMES: temporal-coHERent long-forM understanding with Episodes and Semantics
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.
Stars
38
Forks
5
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
KimMeen/Time-LLM
[ICLR 2024] Official implementation of " 🦙 Time-LLM: Time Series Forecasting by Reprogramming...
om-ai-lab/VLM-R1
Solve Visual Understanding with Reinforced VLMs
bytedance/SALMONN
SALMONN family: A suite of advanced multi-modal LLMs
NVlabs/OmniVinci
OmniVinci is an omni-modal LLM for joint understanding of vision, audio, and language.
fixie-ai/ultravox
A fast multimodal LLM for real-time voice