Hybrid, Unified and Iterative: A Novel Framework for Text-based Person Anomaly Retrieval
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917110420078592 |
|---|---|
| author | Nguyen, Tien-Huy Tran, Huu-Loc Phan-Nguyen, Huu-Phong Dinh, Quang-Vinh |
| author_facet | Nguyen, Tien-Huy Tran, Huu-Loc Phan-Nguyen, Huu-Phong Dinh, Quang-Vinh |
| contents | Text-based person anomaly retrieval has emerged as a challenging task, with most existing approaches relying on complex deep-learning techniques. This raises a research question: How can the model be optimized to achieve greater fine-grained features? To address this, we propose a Local-Global Hybrid Perspective (LHP) module integrated with a Vision-Language Model (VLM), designed to explore the effectiveness of incorporating both fine-grained features alongside coarse-grained features. Additionally, we investigate a Unified Image-Text (UIT) model that combines multiple objective loss functions, including Image-Text Contrastive (ITC), Image-Text Matching (ITM), Masked Language Modeling (MLM), and Masked Image Modeling (MIM) loss. Beyond this, we propose a novel iterative ensemble strategy, by combining iteratively instead of using model results simultaneously like other ensemble methods. To take advantage of the superior performance of the LHP model, we introduce a novel feature selection algorithm based on its guidance, which helps improve the model's performance. Extensive experiments demonstrate the effectiveness of our method in achieving state-of-the-art (SOTA) performance on PAB dataset, compared with previous work, with a 9.70\% improvement in R@1, 1.77\% improvement in R@5, and 1.01\% improvement in R@10. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_22470 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Hybrid, Unified and Iterative: A Novel Framework for Text-based Person Anomaly Retrieval Nguyen, Tien-Huy Tran, Huu-Loc Phan-Nguyen, Huu-Phong Dinh, Quang-Vinh Computer Vision and Pattern Recognition Text-based person anomaly retrieval has emerged as a challenging task, with most existing approaches relying on complex deep-learning techniques. This raises a research question: How can the model be optimized to achieve greater fine-grained features? To address this, we propose a Local-Global Hybrid Perspective (LHP) module integrated with a Vision-Language Model (VLM), designed to explore the effectiveness of incorporating both fine-grained features alongside coarse-grained features. Additionally, we investigate a Unified Image-Text (UIT) model that combines multiple objective loss functions, including Image-Text Contrastive (ITC), Image-Text Matching (ITM), Masked Language Modeling (MLM), and Masked Image Modeling (MIM) loss. Beyond this, we propose a novel iterative ensemble strategy, by combining iteratively instead of using model results simultaneously like other ensemble methods. To take advantage of the superior performance of the LHP model, we introduce a novel feature selection algorithm based on its guidance, which helps improve the model's performance. Extensive experiments demonstrate the effectiveness of our method in achieving state-of-the-art (SOTA) performance on PAB dataset, compared with previous work, with a 9.70\% improvement in R@1, 1.77\% improvement in R@5, and 1.01\% improvement in R@10. |
| title | Hybrid, Unified and Iterative: A Novel Framework for Text-based Person Anomaly Retrieval |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.22470 |