The following papers were recommended by the Semantic Scholar API
\n- \n
- Background Matters Too: A Language-Enhanced Adversarial Framework for Person Re-Identification (2025) \n
- Dual Prompt Learning for Adapting Vision-Language Models to Downstream Image-Text Retrieval (2025) \n
- Context-Adaptive Multi-Prompt Embedding with Large Language Models for Vision-Language Alignment (2025) \n
- CLIP-IN: Enhancing Fine-Grained Visual Understanding in CLIP via Instruction Editing Data and Long Captions (2025) \n
- HQ-CLIP: Leveraging Large Vision-Language Models to Create High-Quality Image-Text Datasets and CLIP Models (2025) \n
- Hierarchical Cross-modal Prompt Learning for Vision-Language Models (2025) \n
- Attribute Guidance With Inherent Pseudo-label For Occluded Person Re-identification (2025) \n
Please give a thumbs up to this comment if you found it helpful!
\nIf you want recommendations for any Paper on Hugging Face checkout this Space
\n You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: \n\n@librarian-bot\n\t recommend
Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval
Abstract
GA-DMS framework enhances CLIP for person representation learning by improving data quality and model architecture, achieving state-of-the-art performance.
Although Contrastive Language-Image Pre-training (CLIP) exhibits strong performance across diverse vision tasks, its application to person representation learning faces two critical challenges: (i) the scarcity of large-scale annotated vision-language data focused on person-centric images, and (ii) the inherent limitations of global contrastive learning, which struggles to maintain discriminative local features crucial for fine-grained matching while remaining vulnerable to noisy text tokens. This work advances CLIP for person representation learning through synergistic improvements in data curation and model architecture. First, we develop a noise-resistant data construction pipeline that leverages the in-context learning capabilities of MLLMs to automatically filter and caption web-sourced images. This yields WebPerson, a large-scale dataset of 5M high-quality person-centric image-text pairs. Second, we introduce the GA-DMS (Gradient-Attention Guided Dual-Masking Synergetic) framework, which improves cross-modal alignment by adaptively masking noisy textual tokens based on the gradient-attention similarity score. Additionally, we incorporate masked token prediction objectives that compel the model to predict informative text tokens, enhancing fine-grained semantic representation learning. Extensive experiments show that GA-DMS achieves state-of-the-art performance across multiple benchmarks.
Community
Although Contrastive Language-Image Pretraining (CLIP) exhibits strong performance across diverse vision tasks, its application to person representation learning faces two critical challenges: (i) the scarcity of large-scale annotated vision-language data focused on person-centric images, and (ii) the inherent limitations of global contrastive learning, which struggles to maintain discriminative local features crucial for fine-grained matching while remaining vulnerable to noisy text tokens. This work advances CLIP for person representation learning through synergistic improvements in data curation and model architecture. First, we develop a noise-resistant data construction pipeline that leverages the in-context learning capabilities of MLLMs to automatically filter and caption web-sourced images. This yields WebPerson, a large-scale dataset of 5M high-quality person-centric image-text pairs. Second, we introduce the GA-DMS (GradientAttention Guided Dual-Masking Synergetic) framework, which improves cross-modal alignment by adaptively masking noisy textual tokens based on the gradient-attention similarity score. Additionally, we incorporate masked token prediction objectives that compel the model to predict informative text tokens, enhancing fine-grained semantic representation learning. Extensive experiments show that GA-DMS achieves state-of-the-art performance across multiple benchmarks.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- Background Matters Too: A Language-Enhanced Adversarial Framework for Person Re-Identification (2025)
- Dual Prompt Learning for Adapting Vision-Language Models to Downstream Image-Text Retrieval (2025)
- Context-Adaptive Multi-Prompt Embedding with Large Language Models for Vision-Language Alignment (2025)
- CLIP-IN: Enhancing Fine-Grained Visual Understanding in CLIP via Instruction Editing Data and Long Captions (2025)
- HQ-CLIP: Leveraging Large Vision-Language Models to Create High-Quality Image-Text Datasets and CLIP Models (2025)
- Hierarchical Cross-modal Prompt Learning for Vision-Language Models (2025)
- Attribute Guidance With Inherent Pseudo-label For Occluded Person Re-identification (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 2
Spaces citing this paper 0
No Space linking this paper