Symbolic Graph Inference for Compound Scene Understanding
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914997682044928 |
|---|---|
| author | Aryan, FNU Stepputtis, Simon Bhagat, Sarthak Campbell, Joseph Lee, Kwonjoon Mahjoub, Hossein Nourkhiz Sycara, Katia |
| author_facet | Aryan, FNU Stepputtis, Simon Bhagat, Sarthak Campbell, Joseph Lee, Kwonjoon Mahjoub, Hossein Nourkhiz Sycara, Katia |
| contents | Scene understanding is a fundamental capability needed in many domains, ranging from question-answering to robotics. Unlike recent end-to-end approaches that must explicitly learn varying compositions of the same scene, our method reasons over their constituent objects and analyzes their arrangement to infer a scene's meaning. We propose a novel approach that reasons over a scene's scene- and knowledge-graph, capturing spatial information while being able to utilize general domain knowledge in a joint graph search. Empirically, we demonstrate the feasibility of our method on the ADE20K dataset and compare it to current scene understanding approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_22626 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Symbolic Graph Inference for Compound Scene Understanding Aryan, FNU Stepputtis, Simon Bhagat, Sarthak Campbell, Joseph Lee, Kwonjoon Mahjoub, Hossein Nourkhiz Sycara, Katia Computer Vision and Pattern Recognition Scene understanding is a fundamental capability needed in many domains, ranging from question-answering to robotics. Unlike recent end-to-end approaches that must explicitly learn varying compositions of the same scene, our method reasons over their constituent objects and analyzes their arrangement to infer a scene's meaning. We propose a novel approach that reasons over a scene's scene- and knowledge-graph, capturing spatial information while being able to utilize general domain knowledge in a joint graph search. Empirically, we demonstrate the feasibility of our method on the ADE20K dataset and compare it to current scene understanding approaches. |
| title | Symbolic Graph Inference for Compound Scene Understanding |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2410.22626 |