ConstraintMatch: Compositional Image-Text Matching through Constrained Regional Evidence Selection
cs.CV, cs.CL
Submitted: 2026-10-31
Updated: 2026-10-31
Terminology
Sources
- Similarity Is Not Logic: Factored Inference for Dual-Encoder Vision-Language Models
- Object-centric Binding in Contrastive Language-Image Pretraining
- SUGARCREPE++ Dataset: Vision-Language Model Sensitivity to Semantic and Lexical Alterations
- Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking
- Revisiting Compositionality in Dual-Encoder Vision-Language Models: The Role of Inference
- CORE: Improving Compositional Reasoning in MLLM Embedding via Reranker Distillation
- SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
- ABE-CLIP: Training-Free Attribute Binding Enhancement for Compositional Image-Text Matching
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs