Efficient Vision Language Model Fine-tuning for Text-based Person Anomaly Search
On the map: Multimodal LLMs / vision-language models → Chart understanding and anomaly detection
Abstract (arXiv)
This paper presents the HFUT-LMC team's solution to the WWW 2025 challenge on Text-based Person Anomaly Search (TPAS). The primary objective of this challenge is to accurately identify pedestrians exhibiting either normal or abnormal behavior within a large library of pedestrian images. Unlike traditional video analysis tasks, TPAS significantly emphasizes understanding and interpreting the subtle relationships between text descriptions and visual data. The complexity of this task lies in the model's need to not only match individuals to text descriptions in massive image datasets but also accurately differentiate between search results when faced with similar descriptions. To overcome these challenges, we introduce the Similarity Coverage Analysis (SCA) strategy to address the recognition difficulty caused by similar text descriptions. This strategy effectively enhances the model's capacity to manage subtle differences, thus improving both the accuracy and reliability of the search. Our proposed solution demonstrated excellent performance in this challenge.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Chart understanding and anomaly detection, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 18 of its 35 references that are in the map. First posted on arXiv 5 Feb 2025.
Builds on
18 of 35 references.
References · 18
- 2020Oscar: Object-Semantics Aligned Pre-training for Vision-Language Taskscited by 1,213
- 2020HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-trainingcited by 362
- 2021An Empirical Study of Training End-to-End Vision-and-Language Transformerscited by 271
- 2021Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Conceptscited by 255
- 2022VLP: A Survey on Vision-Language Pre-trainingcited by 159
- 2020In Defense of Grid Features for Visual Question Answeringcited by 155
- 2017Person Search with Natural Language Descriptioncited by 149
- 2019Improving Description-based Person Re-identification by Multi-granularity Image-text Alignmentscited by 64
- 2022Normalizing Flows for Human Pose Anomaly Detectioncited by 59
- 2019Position Focused Attention Network for Image-Text Matchingcited by 45
- 2020DeVLBert: Learning Deconfounded Visio-Linguistic Representationscited by 42
- 2023Multimodal Motion Conditioned Diffusion Model for Skeleton-based Video Anomaly Detectioncited by 42
6 more
- 2023An Empirical Study of CLIP for Text-based Person Searchcited by 38
- 2021Convolutional Transformer based Dual Discriminator Generative Adversarial Networks for Video Anomaly Detectioncited by 31
- 2024CaLa: Complementary Association Learning for Augmenting Composed Image Retrievalcited by 21
- 2023Text-based Person Search without Parallel Image-Text Datacited by 17
- 2024PLOT: Text-based Person Search with Part Slot Attention for Corresponding Part Discoverycited by 15
- 2024Beyond Walking: A Large-Scale Image-Text Benchmark for Text-based Person Anomaly Searchcited by 11
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2025Hybrid, Unified and Iterative: A Novel Framework for Text-based Person Anomaly Retrieval
- 2026Heterogeneous Vision-Language Ensemble with Disagreement-Aware Reranking for Text-Based Person Anomaly Retrieval
- 2025AnomalyLMM: Bridging Generative Knowledge and Discriminative Retrieval for Text-Based Person Anomaly Search
- 2026Bridging the Pose-Semantic Gap: A Cascade Framework for Text-Based Person Anomaly Search
- 2026Action-Aligned Retrieval with Pairwise Multimodal Reranking for Text-Based Person Anomaly Search
- 2023Exploiting the Textual Potential from Vision-Language Pre-training for Text-based Person Search
- 2026Unified Multi-Dataset Training for TBPS
- 2025Boosting Weak Positives for Text Based Person Search