Text-Based Person Search

Follow this topic Ask about this topic

Latest papers

9 papers1 paper in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

GradCO: Behavior-Aware Gradient-Conflict Offloading for Text-Based Person Anomaly Search
Oct 27, 2026Zhiheng Fu, Zixu Li, Zhiwei Chen +4Text-Based Person Search Person Re-Identification
Shandong University · National University of Singapore
SCOUT: Sim-to-Real Text-Based Person Retrieval by Embedding-Space Prediction over Frozen Video Features
Sep 16, 2026Abdarahmane Traoré, Andy Couturier, Éric HervetText-Based Person Search Synthetic-to-Real Domain Adaptation
Embia, Computer Science Department, Faculty of Science, Université de Moncton, Moncton, NB, Canada
Generative Retrieval for Unsupervised Text-Based Person Search
Sep 11, 2026Mang Ye, Yucheng Ji, Yang Bai +4Text-Based Person Search Unsupervised Learning
School of Computer Science, Wuhan University, Wuhan, China · School of Computer Science and Technology, Soochow University, SuZhou, China · Zhipu AI, Beijing 100089, China +1
FaLCon: Facet-Anchored Retrieval with Late Consensus for Sim2Real Text-Based Person Anomaly Search
Aug 10, 2026Hieu Dinh Trung Pham, Phuong Huu Vu Tran, Thuan Duc Mai +6Text-Based Person Search Fine-Grained Image Retrieval
PAMI Lab, Vietnamese-German University, Vietnam · Ho Chi Minh City University of Technology, Vietnam · Ho Chi Minh city University of Science, Vietnam +2
LightAIR: Lightweight Action Inversion and Riemannian Rectification for Text-based Person Anomaly Search
Aug 10, 2026Yulun Zhang, Zixu Li, Zhiwei Chen +6Text-Based Person Search Representation Disentanglement
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences Shenzhen, China · Shandong University Jinan, China
Achieving Text-based Person Retrieval with Any Granularity
Jul 23, 2026Jialong Zuo, Hanyu Zhou, Dongyue Wu +5Text-Based Person Search Cross-Modal Retrieval
National Key Laboratory of Multispectral Information Intelligent Processing Technology, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, China · School of Software Engineering, Huazhong University of Science and Technology, Wuhan 430074, China
ROGLE: Robust Global-Local Alignment with Automated Region Supervision for Text-Based Person Search
Jun 1, 2026Chaodong Jia, Zequn Xie, Xibei Jia +3Text-Based Person Search Image-Text Retrieval
Harnessing Weak Pair Uncertainty for Text-based Person Search
Apr 10, 2026Jintao Sun, Zhedong Zheng, Gangyi DingText-Based Person Search Image-Text Retrieval
School of Computer Science and Technology, Beijing Institute of Technology, China · Faculty of Science and Technology, University of Macau, China
Pretrain-then-Adapt: Uncertainty-Aware Test-Time Adaptation for Text-based Person Search
Apr 7, 2026Jiahao Zhang, Shaofei Huang, Yaxiong Wang +1Text-Based Person Search Test-Time Adaptation
University of Macau, Macau, China · Hefei University of Technology, Hefei, China

Oct 27, 2026J/K move · Enter open · S save

GradCO: Behavior-Aware Gradient-Conflict Offloading for Text-Based Person Anomaly Search

Zhiheng Fu, Zixu Li, Zhiwei Chen, Jiale Huang+3

Shandong University · National University of Singapore

Text-Based Person Search Person Re-Identification Gradient Interference Anomaly Detection

Open paper AskPDF arXiv

Text-based Person Anomaly Search (TPAS) retrieves a target pedestrian using natural-language descriptions of appearance and normal or anomalous behavior. Unlike conventional text-based person retrieval, TPAS must preserve identity cues while distinguishing fine-grained behaviors. It presents two challenges: same-identity, different-behavior hard negatives cause gradient conflict during granular alignment, while strong appearance cues can obscure weak behavioral evidence during aggregation. We propose GradCO (behavior-aware Gradient-Conflict Offloading), comprising three complementary components. Behavior-Aware Mixture-of-Experts (B-MoE) forms appearance, normal-behavior, and anomalous-behavior streams whose roles are learned from retrieval objectives without expert-specific semantic labels. Conflict Offload Learning (COL) uses pair-conditioned offload anchors in similarity computation to reduce the conflicting-gradient burden on the main text representations. Hierarchical Intent Alignment (HIA) aggregates expert similarities and features using query-conditioned weights. Experiments on five TPAS/TIPR benchmarks show GradCO significantly surpasses SOTA methods and validate our design.