zengqunzhao/Exp-CLIP
[WACV'25 Oral] Enhancing Zero-Shot Facial Expression Recognition by LLM Knowledge Transfer
This tool helps researchers and developers improve how well computer models can identify facial expressions in photos or videos, even for expressions they haven't been specifically trained on. You input images of faces, and the tool outputs enhanced predictions of specific facial expressions. This is ideal for AI/ML researchers, computer vision engineers, and anyone building systems that need to understand human emotions from facial cues.
No commits in the last 6 months.
Use this if you need to build or evaluate a system that can accurately recognize a wide range of facial expressions from images without needing a massive, pre-labeled dataset for every single expression.
Not ideal if you are looking for a plug-and-play solution for general image recognition tasks beyond facial expressions, or if your primary need is for a system that only recognizes expressions it has been explicitly trained on.
Stars
56
Forks
2
Language
Python
License
MIT
Category
Last pushed
Feb 25, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/zengqunzhao/Exp-CLIP"
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