jhcho99/CoFormer

[CVPR'22] Official PyTorch Implementation of "Collaborative Transformers for Grounded Situation Recognition"

37
/ 100
Emerging

This project helps computer vision researchers and AI developers advance the task of 'grounded situation recognition.' It takes an image as input and identifies the main activity (verb), the entities involved (nouns), and their precise locations (bounding boxes). Researchers focusing on improving visual understanding of complex scenes will find this useful.

No commits in the last 6 months.

Use this if you are developing or evaluating AI models for scene understanding and need to identify actions, objects, and their spatial relationships within images.

Not ideal if you are looking for an out-of-the-box solution for general image classification or object detection, as this is a research-oriented implementation.

computer-vision scene-understanding image-analysis AI-research object-recognition
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

50

Forks

7

Language

Python

License

Apache-2.0

Last pushed

Apr 09, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/jhcho99/CoFormer"

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