Hybrid, Unified and Iterative: A Novel Framework for Text-based Person Anomaly Retrieval

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Nguyen, Tien-Huy, Tran, Huu-Loc, Phan-Nguyen, Huu-Phong, Dinh, Quang-Vinh
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