{"total":132,"rows":[{"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":"2305.08386","title":"PLIP: Language-Image Pre-training for Person Representation Learning","created":"2023-05-15","cited_by_count":49,"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":"2312.16245","title":"iKUN: Speak to Trackers without Retraining","created":"2023-12-25","cited_by_count":32,"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":"2503.10324","title":"IDEA: Inverted Text with Cooperative Deformable Aggregation for Multi-modal Object Re-Identification","created":"2025-03-13","cited_by_count":28,"area":null},{"id":"2310.17468","title":"Cross-modal Active Complementary Learning with Self-refining Correspondence","created":"2023-10-26","cited_by_count":22,"area":null},{"id":"2401.06960","title":"Transformer for Object Re-Identification: A Survey","created":"2024-01-13","cited_by_count":22,"area":null},{"id":"2406.00917","title":"Alignment-Free RGBT Salient Object Detection: Semantics-guided Asymmetric Correlation Network and A Unified Benchmark","created":"2024-06-03","cited_by_count":19,"area":null},{"id":"2405.04741","title":"All in One Framework for Multimodal Re-identification in the Wild","created":"2024-05-08","cited_by_count":18,"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":"2502.19958","title":"ChatReID: Open-ended Interactive Person Retrieval via Hierarchical Progressive Tuning for Vision Language Models","created":"2025-02-27","cited_by_count":16,"area":"mllm"},{"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":"2403.05105","title":"Learning to Rematch Mismatched Pairs for Robust Cross-Modal Retrieval","created":"2024-03-08","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":"2505.06566","title":"Dynamic Uncertainty Learning with Noisy Correspondence for Text-Based Person Search","created":"2025-05-10","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":"2402.11307","title":"ICHPro: Intracerebral Hemorrhage Prognosis Classification Via Joint-attention Fusion-based 3d Cross-modal Network","created":"2024-02-17","cited_by_count":10,"area":null},{"id":"2410.15624","title":"Test-time Adaptation for Cross-modal Retrieval with Query Shift","created":"2024-10-21","cited_by_count":10,"area":null},{"id":"2312.05777","title":"Negative Pre-aware for Noisy Cross-modal Matching","created":"2023-12-10","cited_by_count":9,"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":"2504.10174","title":"LLaVA-ReID: Selective Multi-image Questioner for Interactive Person Re-Identification","created":"2025-04-14","cited_by_count":9,"area":null},{"id":"2506.02439","title":"Video-Level Language-Driven Video-Based Visible-Infrared Person Re-Identification","created":"2025-06-03","cited_by_count":9,"area":null},{"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":"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":"2506.09385","title":"ReID5o: Achieving Omni Multi-modal Person Re-identification in a Single Model","created":"2025-06-11","cited_by_count":8,"area":null},{"id":"2507.07802","title":"Synergistic Prompting for Robust Visual Recognition with Missing Modalities","created":"2025-07-10","cited_by_count":8,"area":null},{"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":"2410.11255","title":"CLIP-DFGS: A Hard Sample Mining Method for CLIP in Generalizable Person Re-Identification","created":"2024-10-15","cited_by_count":7,"area":null},{"id":"2501.16065","title":"CILP-FGDI: Exploiting Vision-Language Model for Generalizable Person Re-Identification","created":"2025-01-27","cited_by_count":7,"area":"mllm"},{"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":"2401.05646","title":"Masked Attribute Description Embedding for Cloth-Changing Person Re-identification","created":"2024-01-11","cited_by_count":5,"area":null},{"id":"2403.16003","title":"Diverse Representation Embedding for Lifelong Person Re-Identification","created":"2024-03-24","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":"2305.04497","title":"IIITD-20K: Dense captioning for Text-Image ReID","created":"2023-05-08","cited_by_count":4,"area":null},{"id":"2404.18106","title":"Semi-supervised Text-based Person Search","created":"2024-04-28","cited_by_count":4,"area":null},{"id":"2405.11971","title":"Data Augmentation for Text-based Person Retrieval Using Large Language Models","created":"2024-05-20","cited_by_count":4,"area":null},{"id":"2406.09198","title":"CLIP-Driven Cloth-Agnostic Feature Learning for Cloth-Changing Person Re-Identification","created":"2024-06-13","cited_by_count":4,"area":null},{"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":"2509.04376","title":"AnomalyLMM: Bridging Generative Knowledge and Discriminative Retrieval for Text-Based Person Anomaly Search","created":"2025-09-04","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":"2511.13575","title":"Hierarchical Prompt Learning for Image- and Text-Based Person Re-Identification","created":"2025-11-17","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":"2407.12346","title":"Object-Aware Query Perturbation for Cross-Modal Image-Text Retrieval","created":"2024-07-17","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":"2502.14889","title":"Narrowing Information Bottleneck Theory for Multimodal Image-Text Representations Interpretability","created":"2025-02-16","cited_by_count":3,"area":null},{"id":"2506.13095","title":"Learning Event Completeness for Weakly Supervised Video Anomaly Detection","created":"2025-06-16","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":"2508.16707","title":"Sparse and Dense Retrievers Learn Better Together: Joint Sparse-Dense Optimization for Text-Image Retrieval","created":"2025-08-22","cited_by_count":3,"area":"mllm"},{"id":"2510.00936","title":"Resolution as a Direction: Vector-Panning Feature Alignment for Cross-Resolution Re-Identification","created":"2025-10-01","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":"2603.00550","title":"Weakly Supervised Video Anomaly Detection with Anomaly-Connected Components and Intention Reasoning","created":"2026-02-28","cited_by_count":3,"area":null},{"id":"2603.02663","title":"Evaluating Cross-Modal Reasoning Ability and Problem Characteristics with Multimodal Item Response Theory","created":"2026-03-03","cited_by_count":3,"area":"lr"},{"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":"2406.03721","title":"Attribute-Aware Implicit Modality Alignment for Text Attribute Person Search","created":"2024-06-06","cited_by_count":2,"area":null},{"id":"2408.05543","title":"PixelFade: Privacy-preserving Person Re-identification with Noise-guided Progressive Replacement","created":"2024-08-10","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":"2503.08201","title":"Scale-Aware Pre-Training for Human-Centric Visual Perception: Enabling Lightweight and Generalizable Models","created":"2025-03-11","cited_by_count":2,"area":null},{"id":"2507.05970","title":"Automatic Synthesis of High-Quality Triplet Data for Composed Image Retrieval","created":"2025-07-08","cited_by_count":2,"area":null},{"id":"2507.06744","title":"Dual-Granularity Cross-Modal Identity Association for Weakly-Supervised Text-to-Person Image Matching","created":"2025-07-09","cited_by_count":2,"area":null},{"id":"2511.08369","title":"Text-based Aerial-Ground Person Retrieval","created":"2025-11-11","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":"2401.10011","title":"CPCL: Cross-Modal Prototypical Contrastive Learning for Weakly Supervised Text-based Person Retrieval","created":"2024-01-18","cited_by_count":1,"area":null},{"id":"2403.04183","title":"YYDS: Visible-Infrared Person Re-Identification with Coarse Descriptions","created":"2024-03-07","cited_by_count":1,"area":null},{"id":"2407.18854","title":"Unifying Visual and Semantic Feature Spaces with Diffusion Models for Enhanced Cross-Modal Alignment","created":"2024-07-26","cited_by_count":1,"area":"diffusion"},{"id":"2503.07950","title":"Decoupled Cross-Modal Alignment Network for Text-RGBT Person Retrieval and A High-Quality Benchmark","created":"2025-03-11","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":"2504.05644","title":"iEBAKER: Improved Remote Sensing Image-Text Retrieval Framework via Eliminate Before Align and Keyword Explicit Reasoning","created":"2025-04-08","cited_by_count":1,"area":null},{"id":"2505.03567","title":"Uncertainty-Aware Prototype Semantic Decoupling for Text-Based Person Search in Full Images","created":"2025-05-06","cited_by_count":1,"area":null},{"id":"2505.05721","title":"Semantic-Space-Intervened Diffusive Alignment for Visual Classification","created":"2025-05-09","cited_by_count":1,"area":null},{"id":"2505.23365","title":"MCFNet: A Multimodal Collaborative Fusion Network for Fine-Grained Semantic Classification","created":"2025-05-29","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":"2507.01504","title":"Following the Clues: Experiments on Person Re-ID using Cross-Modal Intelligence","created":"2025-07-02","cited_by_count":1,"area":null},{"id":"2508.03375","title":"GaitAdapt: Continual Learning for Evolving Gait Recognition","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2509.03032","title":"Background Matters Too: A Language-Enhanced Adversarial Framework for Person Re-Identification","created":"2025-09-03","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":"2509.21747","title":"Incorporating Scene Context and Semantic Labels for Enhanced Group-level Emotion Recognition","created":"2025-09-26","cited_by_count":1,"area":null},{"id":"2510.13235","title":"EPIPTrack: Rethinking Prompt Modeling with Explicit and Implicit Prompts for Multi-Object Tracking","created":"2025-10-15","cited_by_count":1,"area":null},{"id":"2601.03191","title":"AnatomiX, an Anatomy-Aware Grounded Multimodal Large Language Model for Chest X-Ray Interpretation","created":"2026-01-06","cited_by_count":1,"area":"lr"},{"id":"2604.08877","title":"Harnessing Weak Pair Uncertainty for Text-based Person Search","created":"2026-04-10","cited_by_count":1,"area":null},{"id":"2607.14115","title":"DialogueVPR: Towards Conversational Visual Place Recognition","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2608.09474","title":"FaLCon: Facet-Anchored Retrieval with Late Consensus for Sim2Real Text-Based Person Anomaly Search","created":"2026-08-10","cited_by_count":1,"area":null},{"id":"2608.12843","title":"Heterogeneous Vision-Language Ensemble with Disagreement-Aware Reranking for Text-Based Person Anomaly Retrieval","created":"2026-08-13","cited_by_count":1,"area":null},{"id":"2304.04203","title":"OpenDriver: An Open-Road Driver State Detection Dataset","created":"2023-04-09","cited_by_count":0,"area":null},{"id":"2307.07184","title":"TVPR: Text-to-Video Person Retrieval and a New Benchmark","created":"2023-07-14","cited_by_count":0,"area":null},{"id":"2312.14834","title":"Prototype-Guided Text-based Person Search based on Rich Chinese Descriptions","created":"2023-12-22","cited_by_count":0,"area":null},{"id":"2403.17702","title":"The Solution for the CVPR 2023 1st foundation model challenge-Track2","created":"2024-03-26","cited_by_count":0,"area":null}],"next_cursor":"100"}