jhcho99/GSRTR

[BMVC'21] Official PyTorch Implementation of "Grounded Situation Recognition with Transformers"

40
/ 100
Emerging

This project helps identify and locate specific actions (verbs) and associated objects (nouns) within images. You input an image, and it outputs a description of the primary action, the key entities involved in that action, and their precise locations (bounding boxes). It's designed for researchers or developers working on advanced image understanding and computer vision applications.

No commits in the last 6 months.

Use this if you need to go beyond simple object detection and understand the full 'situation' depicted in an image, including the verb, its semantic roles, and the location of each role filler.

Not ideal if you only need to classify objects, perform basic image categorization, or if you're not comfortable working with machine learning models and datasets.

image-understanding computer-vision scene-analysis semantic-parsing visual-reasoning
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

27

Forks

11

Language

Python

License

Apache-2.0

Last pushed

Mar 30, 2022

Commits (30d)

0

Get this data via API

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

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