Decoupled Global-Local Alignment for Improving Compositional Understanding
Open Access
- 27 October 2025
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 3251-3260
Abstract
No abstract availableAll Related Versions
Funding Information
- National Natural Science Foundation of China (62301046)
This publication has 14 references indexed in Scilit:
- CLIP2UDA: Making Frozen CLIP Reward Unsupervised Domain Adaptation in 3D Semantic Segmentation2024
- Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional Understanding2024
- Synthesize, Diagnose, and Optimize: Towards Fine-Grained Vision-Language Understanding2024
- Sigmoid Loss for Language Image Pre-Training2023
- Teaching Structured Vision & Language Concepts to Vision & Language Models2023
- Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models2015
- Describing Textures in the Wild2014
- Food-101 – Mining Discriminative Components with Random Forests2014
- 3D Object Representations for Fine-Grained Categorization2013
- Automated Flower Classification over a Large Number of Classes2008