{"total":65,"rows":[{"id":"2303.12501","title":"Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval","created":"2023-03-22","cited_by_count":132,"area":"lr"},{"id":"2210.10276","title":"CLIP-Driven Fine-grained Text-Image Person Re-identification","created":"2022-10-19","cited_by_count":79,"area":null},{"id":"2306.02898","title":"Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmark","created":"2023-06-05","cited_by_count":75,"area":null},{"id":"2308.09911","title":"Noisy-Correspondence Learning for Text-to-Image Person Re-identification","created":"2023-08-19","cited_by_count":56,"area":null},{"id":"2305.13653","title":"RaSa: Relation and Sensitivity Aware Representation Learning for Text-based Person Search","created":"2023-05-23","cited_by_count":54,"area":null},{"id":"2305.08386","title":"PLIP: Language-Image Pre-training for Person Representation Learning","created":"2023-05-15","cited_by_count":49,"area":null},{"id":"2208.14365","title":"Image-Specific Information Suppression and Implicit Local Alignment for Text-based Person Search","created":"2022-08-30","cited_by_count":38,"area":null},{"id":"2308.10045","title":"An Empirical Study of CLIP for Text-based Person Search","created":"2023-08-19","cited_by_count":38,"area":null},{"id":"2509.12662","title":"Chat-Driven Text Generation and Interaction for Person Retrieval","created":"2025-09-16","cited_by_count":34,"area":null},{"id":"2312.03441","title":"UFineBench: Towards Text-based Person Retrieval with Ultra-fine Granularity","created":"2023-12-06","cited_by_count":30,"area":null},{"id":"2401.06960","title":"Transformer for Object Re-Identification: A Survey","created":"2024-01-13","cited_by_count":22,"area":null},{"id":"2309.01420","title":"Unified Pre-training with Pseudo Texts for Text-To-Image Person Re-identification","created":"2023-09-04","cited_by_count":19,"area":null},{"id":"2305.12964","title":"Text-based Person Search without Parallel Image-Text Data","created":"2023-05-22","cited_by_count":17,"area":null},{"id":"2409.13475","title":"PLOT: Text-based Person Search with Part Slot Attention for Corresponding Part Discovery","created":"2024-09-20","cited_by_count":15,"area":null},{"id":"2601.18625","title":"CONQUER: Context-Aware Representation with Query Enhancement for Text-Based Person Search","created":"2026-01-26","cited_by_count":15,"area":null},{"id":"2404.10292","title":"From Data Deluge to Data Curation: A Filtering-WoRA Paradigm for Efficient Text-based Person Search","created":"2024-04-16","cited_by_count":14,"area":null},{"id":"2311.07514","title":"VGSG: Vision-Guided Semantic-Group Network for Text-based Person Search","created":"2023-11-13","cited_by_count":11,"area":null},{"id":"2407.04287","title":"MARS: Paying more attention to visual attributes for text-based person search","created":"2024-07-05","cited_by_count":11,"area":null},{"id":"2411.17776","title":"Beyond Walking: A Large-Scale Image-Text Benchmark for Text-based Person Anomaly Search","created":"2024-11-26","cited_by_count":11,"area":null},{"id":"2309.09496","title":"CLIP-based Synergistic Knowledge Transfer for Text-based Person Retrieval","created":"2023-09-18","cited_by_count":10,"area":null},{"id":"2503.04144","title":"DM-Adapter: Domain-Aware Mixture-of-Adapters for Text-Based Person Retrieval","created":"2025-03-06","cited_by_count":9,"area":"moe"},{"id":"2506.11036","title":"Human-centered Interactive Learning via MLLMs for Text-to-Image Person Re-identification","created":"2025-05-21","cited_by_count":9,"area":null},{"id":"2309.04675","title":"BiLMa: Bidirectional Local-Matching for Text-based Person Re-identification","created":"2023-09-09","cited_by_count":8,"area":null},{"id":"2311.09084","title":"Contrastive Transformer Learning with Proximity Data Generation for Text-Based Person Search","created":"2023-11-15","cited_by_count":8,"area":null},{"id":"2401.13201","title":"MLLMReID: Multimodal Large Language Model-based Person Re-identification","created":"2024-01-24","cited_by_count":8,"area":"mllm"},{"id":"2503.09962","title":"Modeling Thousands of Human Annotators for Generalizable Text-to-Image Person Re-identification","created":"2025-03-13","cited_by_count":8,"area":null},{"id":"2303.04497","title":"Exploiting the Textual Potential from Vision-Language Pre-training for Text-based Person Search","created":"2023-03-08","cited_by_count":7,"area":"mllm"},{"id":"2310.11210","title":"Learning Comprehensive Representations with Richer Self for Text-to-Image Person Re-Identification","created":"2023-10-17","cited_by_count":7,"area":null},{"id":"2504.07718","title":"Multi-modal Reference Learning for Fine-grained Text-to-Image Retrieval","created":"2025-04-10","cited_by_count":6,"area":null},{"id":"2504.18782","title":"CAMeL: Cross-modality Adaptive Meta-Learning for Text-based Person Retrieval","created":"2025-04-26","cited_by_count":6,"area":null},{"id":"2312.01745","title":"Cross-Modal Adaptive Dual Association for Text-to-Image Person Retrieval","created":"2023-12-04","cited_by_count":5,"area":null},{"id":"2408.00096","title":"From Attributes to Natural Language: A Survey and Foresight on Text-based Person Re-identification","created":"2024-07-31","cited_by_count":5,"area":null},{"id":"2501.15052","title":"Graph-Based Cross-Domain Knowledge Distillation for Cross-Dataset Text-to-Image Person Retrieval","created":"2025-01-25","cited_by_count":5,"area":"distill"},{"id":"2412.15106","title":"Knowing Where to Focus: Attention-Guided Alignment for Text-based Person Search","created":"2024-12-19","cited_by_count":4,"area":null},{"id":"2504.10084","title":"UP-Person: Unified Parameter-Efficient Transfer Learning for Text-based Person Retrieval","created":"2025-04-14","cited_by_count":4,"area":null},{"id":"2509.09118","title":"Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval","created":"2025-09-11","cited_by_count":4,"area":null},{"id":"2509.18715","title":"What Makes You Unique? Attribute Prompt Composition for Object Re-Identification","created":"2025-09-23","cited_by_count":4,"area":null},{"id":"2604.23282","title":"Bridging the Pose-Semantic Gap: A Cascade Framework for Text-Based Person Anomaly Search","created":"2026-04-25","cited_by_count":4,"area":null},{"id":"2211.08657","title":"Person Text-Image Matching via Text-Feature Interpretability Embedding and External Attack Node Implantation","created":"2022-11-16","cited_by_count":3,"area":null},{"id":"2304.05554","title":"Learning Transferable Pedestrian Representation from Multimodal Information Supervision","created":"2023-04-12","cited_by_count":3,"area":null},{"id":"2412.20646","title":"Enhancing Visual Representation for Text-based Person Searching","created":"2024-12-30","cited_by_count":3,"area":null},{"id":"2507.10195","title":"Minimizing the Pretraining Gap: Domain-aligned Text-Based Person Retrieval","created":"2025-07-14","cited_by_count":3,"area":null},{"id":"2510.05586","title":"CalibCLIP: Contextual Calibration of Dominant Semantics for Text-Driven Image Retrieval","created":"2025-10-07","cited_by_count":3,"area":"mllm"},{"id":"2510.15595","title":"FlexiReID: Adaptive Mixture of Expert for Multi-Modal Person Re-Identification","created":"2025-10-17","cited_by_count":3,"area":null},{"id":"2601.01024","title":"ITSELF: Attention Guided Fine-Grained Alignment for Vision-Language Retrieval","created":"2026-01-03","cited_by_count":3,"area":"mllm"},{"id":"2307.09059","title":"Text-guided Image Restoration and Semantic Enhancement for Text-to-Image Person Retrieval","created":"2023-07-18","cited_by_count":2,"area":null},{"id":"2308.11994","title":"Progressive Feature Mining and External Knowledge-Assisted Text-Pedestrian Image Retrieval","created":"2023-08-23","cited_by_count":2,"area":null},{"id":"2409.06385","title":"AMNS: Attention-Weighted Selective Mask and Noise Label Suppression for Text-to-Image Person Retrieval","created":"2024-09-10","cited_by_count":2,"area":null},{"id":"2601.10053","title":"DiCo: Disentangled Concept Representation for Text-to-image Person Re-identification","created":"2026-01-15","cited_by_count":2,"area":null},{"id":"2604.18376","title":"Towards Robust Text-to-Image Person Retrieval: Multi-View Reformulation for Semantic Compensation","created":"2026-04-20","cited_by_count":2,"area":null},{"id":"2304.02278","title":"SCMM: Calibrating Cross-modal Representations for Text-Based Person Search","created":"2023-04-05","cited_by_count":1,"area":null},{"id":"2312.01605","title":"TextAug: Test time Text Augmentation for Multimodal Person Re-identification","created":"2023-12-04","cited_by_count":1,"area":null},{"id":"2401.02173","title":"Prompt Decoupling for Text-to-Image Person Re-identification","created":"2024-01-04","cited_by_count":1,"area":null},{"id":"2503.21595","title":"PS-ReID: Advancing Person Re-Identification and Precise Segmentation with Multimodal Retrieval","created":"2025-03-27","cited_by_count":1,"area":null},{"id":"2503.22171","title":"An Empirical Study of Validating Synthetic Data for Text-Based Person Retrieval","created":"2025-03-28","cited_by_count":1,"area":null},{"id":"2505.24466","title":"SA-Person: Text-Based Person Retrieval with Scene-aware Re-ranking","created":"2025-05-30","cited_by_count":1,"area":null},{"id":"2508.07904","title":"CTC Transcription Alignment of the Bullinger Letters: Automatic Improvement of Annotation Quality","created":"2025-08-11","cited_by_count":1,"area":null},{"id":"2509.13754","title":"Cross-modal Full-mode Fine-grained Alignment for Text-to-Image Person Retrieval","created":"2025-09-17","cited_by_count":1,"area":null},{"id":"2604.08877","title":"Harnessing Weak Pair Uncertainty for Text-based Person Search","created":"2026-04-10","cited_by_count":1,"area":null},{"id":"2501.17586","title":"Boosting Weak Positives for Text Based Person Search","created":"2025-01-29","cited_by_count":0,"area":"mllm"},{"id":"2602.12936","title":"Unleashing MLLMs on the Edge: A Unified Framework for Cross-Modal ReID via Adaptive SVD Distillation","created":"2026-02-13","cited_by_count":0,"area":null},{"id":"2605.06012","title":"T2I-VeRW: Part-level Fine-grained Perception for Text-to-Image Vehicle Retrieval","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2606.01825","title":"ROGLE: Robust Global-Local Alignment with Automated Region Supervision for Text-Based Person Search","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.30458","title":"Cross-Resolution Semantic Transfer for Robust Text-to-Image Retrieval in Low-Resolution Surveillance","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2608.23503","title":"Action-Aligned Retrieval with Pairwise Multimodal Reranking for Text-Based Person Anomaly Search","created":"2026-08-24","cited_by_count":0,"area":null}],"next_cursor":null}