{"list":"other","total":67,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"2412.05271","title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","created":"2024-12-06","cited_by_count":1599},{"id":"2311.12793","title":"ShareGPT4V: Improving Large Multi-Modal Models with Better Captions","created":"2023-11-21","cited_by_count":1005},{"id":"1411.4555","title":"Show and Tell: A Neural Image Caption Generator","created":"2014-11-17","cited_by_count":879},{"id":"2001.04193","title":"Deep Learning for Person Re-identification: A Survey and Outlook","created":"2020-01-13","cited_by_count":549},{"id":"2505.09568","title":"BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset","created":"2025-05-14","cited_by_count":376},{"id":"1702.05729","title":"Person Search with Natural Language Description","created":"2017-02-19","cited_by_count":149},{"id":"1711.05535","title":"Dual-Path Convolutional Image-Text Embeddings with Instance Loss","created":"2017-11-15","cited_by_count":145},{"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},{"id":"2107.12666","title":"Semantically Self-Aligned Network for Text-to-Image Part-aware Person Re-identification","created":"2021-07-27","cited_by_count":110},{"id":"2109.05534","title":"DSSL: Deep Surroundings-person Separation Learning for Text-based Person Retrieval","created":"2021-09-12","cited_by_count":102},{"id":"2012.03753","title":"Unsupervised Pre-training for Person Re-identification","created":"2020-12-07","cited_by_count":95},{"id":"2303.03032","title":"DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only Training","created":"2023-03-06","cited_by_count":84},{"id":"1903.10658","title":"Unpaired Image Captioning via Scene Graph Alignments","created":"2019-03-26","cited_by_count":82},{"id":"2405.19092","title":"Benchmarking and Improving Detail Image Caption","created":"2024-05-29","cited_by_count":81},{"id":"1811.10787","title":"Unsupervised Image Captioning","created":"2018-11-27","cited_by_count":79},{"id":"2210.10276","title":"CLIP-Driven Fine-grained Text-Image Person Re-identification","created":"2022-10-19","cited_by_count":79},{"id":"2005.07327","title":"ViTAA: Visual-Textual Attributes Alignment in Person Search by Natural Language","created":"2020-05-15","cited_by_count":78},{"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},{"id":"2003.03923","title":"Deconfounded Image Captioning: A Causal Retrospect","created":"2020-03-09","cited_by_count":65},{"id":"1906.09610","title":"Improving Description-based Person Re-identification by Multi-granularity Image-text Alignments","created":"2019-06-23","cited_by_count":64},{"id":"2305.14800","title":"Exploring Diverse In-Context Configurations for Image Captioning","created":"2023-05-24","cited_by_count":63},{"id":"2101.03036","title":"Contextual Non-Local Alignment over Full-Scale Representation for Text-Based Person Search","created":"2021-01-08","cited_by_count":62},{"id":"2207.07802","title":"Learning Granularity-Unified Representations for Text-to-Image Person Re-identification","created":"2022-07-16","cited_by_count":62},{"id":"2105.11628","title":"TIPCB: A Simple but Effective Part-based Convolutional Baseline for Text-based Person Search","created":"2021-05-25","cited_by_count":57},{"id":"2308.09911","title":"Noisy-Correspondence Learning for Text-to-Image Person Re-identification","created":"2023-08-19","cited_by_count":56},{"id":"2203.14713","title":"Image-text Retrieval: A Survey on Recent Research and Development","created":"2022-03-28","cited_by_count":55},{"id":"2110.10807","title":"Text-Based Person Search with Limited Data","created":"2021-10-20","cited_by_count":54},{"id":"2305.13653","title":"RaSa: Relation and Sensitivity Aware Representation Learning for Text-based Person Search","created":"2023-05-23","cited_by_count":54},{"id":"1809.08440","title":"Pose-Guided Multi-Granularity Attention Network for Text-Based Person Search","created":"2018-09-22","cited_by_count":52},{"id":"2305.08386","title":"PLIP: Language-Image Pre-training for Person Representation Learning","created":"2023-05-15","cited_by_count":49},{"id":"2206.08919","title":"VLMixer: Unpaired Vision-Language Pre-training via Cross-Modal CutMix","created":"2022-06-17","cited_by_count":45},{"id":"2203.16533","title":"Large-Scale Pre-training for Person Re-identification with Noisy Labels","created":"2022-03-30","cited_by_count":41},{"id":"2112.06714","title":"Learning Semantic-Aligned Feature Representation for Text-based Person Search","created":"2021-12-13","cited_by_count":40},{"id":"2209.05773","title":"CAIBC: Capturing All-round Information Beyond Color for Text-based Person Retrieval","created":"2022-09-13","cited_by_count":39},{"id":"2405.04940","title":"Harnessing the Power of MLLMs for Transferable Text-to-Image Person ReID","created":"2024-05-08","cited_by_count":39},{"id":"2308.10045","title":"An Empirical Study of CLIP for Text-based Person Search","created":"2023-08-19","cited_by_count":38},{"id":"2403.03715","title":"MeaCap: Memory-Augmented Zero-shot Image Captioning","created":"2024-03-06","cited_by_count":35},{"id":"2307.16525","title":"Transferable Decoding with Visual Entities for Zero-Shot Image Captioning","created":"2023-07-31","cited_by_count":34},{"id":"1711.08766","title":"Region-based Quality Estimation Network for Large-scale Person Re-identification","created":"2017-11-23","cited_by_count":33},{"id":"2304.06275","title":"Noisy Correspondence Learning with Meta Similarity Correction","created":"2023-04-13","cited_by_count":26},{"id":"2203.00242","title":"Unsupervised Vision-and-Language Pre-training via Retrieval-based Multi-Granular Alignment","created":"2022-03-01","cited_by_count":23},{"id":"2205.13125","title":"Prompt-based Learning for Unpaired Image Captioning","created":"2022-05-26","cited_by_count":23},{"id":"2412.03665","title":"Personalizing Multimodal Large Language Models for Image Captioning: An Experimental Analysis","created":"2024-12-04","cited_by_count":23},{"id":"2212.11958","title":"Asymmetric Cross-Scale Alignment for Text-Based Person Search","created":"2022-11-26","cited_by_count":18},{"id":"2308.12383","title":"With a Little Help from your own Past: Prototypical Memory Networks for Image Captioning","created":"2023-08-23","cited_by_count":18},{"id":"2305.12964","title":"Text-based Person Search without Parallel Image-Text Data","created":"2023-05-22","cited_by_count":17},{"id":"2006.13611","title":"Recurrent Relational Memory Network for Unsupervised Image Captioning","created":"2020-06-24","cited_by_count":16},{"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},{"id":"2312.08865","title":"Improving Cross-modal Alignment with Synthetic Pairs for Text-only Image Captioning","created":"2023-12-14","cited_by_count":14},{"id":"2401.02347","title":"Mining Fine-Grained Image-Text Alignment for Zero-Shot Captioning via Text-Only Training","created":"2024-01-04","cited_by_count":12},{"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},{"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},{"id":"2003.00808","title":"A Convolutional Baseline for Person Re-Identification Using Vision and Language Descriptions","created":"2020-02-20","cited_by_count":7},{"id":"2501.00437","title":"Unleashing Text-to-Image Diffusion Prior for Zero-Shot Image Captioning","created":"2024-12-31","cited_by_count":7},{"id":"2409.09427","title":"Prototypical Prompting for Text-to-image Person Re-identification","created":"2024-09-14","cited_by_count":6},{"id":"2404.18106","title":"Semi-supervised Text-based Person Search","created":"2024-04-28","cited_by_count":4},{"id":"2408.05503","title":"Disentangled Noisy Correspondence Learning","created":"2024-08-10","cited_by_count":4},{"id":"2406.10845","title":"LAIP: Learning Local Alignment from Image-Phrase Modeling for Text-based Person Search","created":"2024-06-16","cited_by_count":3},{"id":"2501.14828","title":"An Ensemble Model with Attention Based Mechanism for Image Captioning","created":"2025-01-22","cited_by_count":2},{"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},{"id":"2505.24466","title":"SA-Person: Text-Based Person Retrieval with Scene-aware Re-ranking","created":"2025-05-30","cited_by_count":1}],"next_cursor":null}