MuRelSGG: Multimodal Relationship Prediction for Neurosymbolic Scene Graph Generation
Neurosymbolic Scene Graph Generation (SGG) is a promising approach that jointly leverages the perception capabilities of deep neural networks and the reasoning capabilities of symbolic techniques for scene understanding and visual reasoning. SGG systematically captures semantic components, including...
Saved in:
| Main Authors: | Muhammad Junaid Khan, Adil Masood Siddiqui, Hamid Saeed Khan, Faisal Akram, M. Jaleed Khan |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10925205/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Enhancing human-centered dynamic scene understanding via multiple LLMs collaborated reasoning
by: Hang Zhang, et al.
Published: (2025-03-01) -
SPIN-SGG: spatial integration for open-vocabulary scene graph generation
by: Nanhao Liang, et al.
Published: (2025-08-01) -
Education in the era of Neurosymbolic AI
by: Chris Davis Jaldi, et al.
Published: (2025-05-01) -
Sequential selection and calibration of video frames for 3D outdoor scene reconstruction
by: Weilin Sun, et al.
Published: (2024-12-01) -
Pattern-based engineering of Neurosymbolic AI Systems
by: Fajar J. Ekaputra
Published: (2025-05-01)