{"total":16,"rows":[{"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":"2411.18111","title":"When Large Vision-Language Models Meet Person Re-Identification","created":"2024-11-27","cited_by_count":15,"area":"mllm"},{"id":"2310.17218","title":"Prototypical Contrastive Learning-based CLIP Fine-tuning for Object Re-identification","created":"2023-10-26","cited_by_count":11,"area":"mllm"},{"id":"2401.13201","title":"MLLMReID: Multimodal Large Language Model-based Person Re-identification","created":"2024-01-24","cited_by_count":8,"area":"mllm"},{"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":"2605.24470","title":"TempRet: Temporal Enhancement and Two-Stage Reranking for CVPR 2026 EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge","created":"2026-05-23","cited_by_count":5,"area":"mllm"},{"id":"2410.09382","title":"CLIP-SCGI: Synthesized Caption-Guided Inversion for Person Re-Identification","created":"2024-10-12","cited_by_count":4,"area":"mllm"},{"id":"2511.17964","title":"X-ReID: Multi-granularity Information Interaction for Video-Based Visible-Infrared Person Re-Identification","created":"2025-11-22","cited_by_count":4,"area":"mllm"},{"id":"2407.20647","title":"Image Re-Identification: Where Self-supervision Meets Vision-Language Learning","created":"2024-07-30","cited_by_count":3,"area":"mllm"},{"id":"2507.00506","title":"SCING:Towards More Efficient and Robust Person Re-Identification through Selective Cross-modal Prompt Tuning","created":"2025-07-01","cited_by_count":2,"area":"mllm"},{"id":"2601.08617","title":"SoC: Semantic Orthogonal Calibration for Test-Time Prompt Tuning","created":"2026-01-13","cited_by_count":2,"area":"mllm"},{"id":"2506.12447","title":"CLIP-HandID: Vision-Language Model for Hand-Based Person Identification","created":"2025-06-14","cited_by_count":1,"area":"mllm"},{"id":"2512.03463","title":"Text-Printed Image: Bridging the Image-Text Modality Gap for Text-centric Training of Large Vision-Language Models","created":"2025-12-03","cited_by_count":1,"area":"mllm"},{"id":"2603.21482","title":"ALADIN:Attribute-Language Distillation Network for Person Re-Identification","created":"2026-03-23","cited_by_count":0,"area":"mllm"},{"id":"2606.16161","title":"Multimodal LLM-Empowered Re-Ranking for Generalizable Person Re-Identification","created":"2026-06-15","cited_by_count":0,"area":"mllm"},{"id":"2609.39492","title":"Front-to-Back: Benchmarking Vision-Language Models for Asymmetric Cross-View Vehicle Re-Identification","created":"2026-09-30","cited_by_count":0,"area":"mllm"}],"next_cursor":null}