{"list":"other","total":59,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2208.12242","title":"DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation","created":"2022-08-25","cited_by_count":3300},{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"id":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"2308.12966","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","created":"2023-08-24","cited_by_count":2224},{"id":"2407.10671","title":"Qwen2 Technical Report","created":"2024-07-15","cited_by_count":2120},{"id":"2310.00426","title":"PixArt-$\\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis","created":"2023-09-30","cited_by_count":864},{"id":"2303.15389","title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","created":"2023-03-27","cited_by_count":798},{"id":"2304.08465","title":"MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing","created":"2023-04-17","cited_by_count":727},{"id":"2404.06395","title":"MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies","created":"2024-04-09","cited_by_count":723},{"id":"1711.08565","title":"Person Transfer GAN to Bridge Domain Gap for Person Re-Identification","created":"2017-11-23","cited_by_count":480},{"id":"2210.07574","title":"Is synthetic data from generative models ready for image recognition?","created":"2022-10-14","cited_by_count":320},{"id":"1904.07223","title":"Joint Discriminative and Generative Learning for Person Re-identification","created":"2019-04-15","cited_by_count":213},{"id":"2306.00984","title":"StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners","created":"2023-06-01","cited_by_count":177},{"id":"1702.05729","title":"Person Search with Natural Language Description","created":"2017-02-19","cited_by_count":149},{"id":"2306.06101","title":"Prodigy: An Expeditiously Adaptive Parameter-Free Learner","created":"2023-06-09","cited_by_count":133},{"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":"2312.04567","title":"Scaling Laws of Synthetic Images for Model Training ... for Now","created":"2023-12-07","cited_by_count":108},{"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":"2305.09972","title":"Real-Time Flying Object Detection with YOLOv8","created":"2023-05-17","cited_by_count":94},{"id":"2303.05657","title":"Tag2Text: Guiding Vision-Language Model via Image Tagging","created":"2023-03-10","cited_by_count":86},{"id":"1812.02162","title":"Dissecting Person Re-identification from the Viewpoint of Viewpoint","created":"2018-12-05","cited_by_count":83},{"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":"2208.08608","title":"See Finer, See More: Implicit Modality Alignment for Text-based Person Retrieval","created":"2022-08-18","cited_by_count":65},{"id":"2207.07802","title":"Learning Granularity-Unified Representations for Text-to-Image Person Re-identification","created":"2022-07-16","cited_by_count":62},{"id":"2308.09911","title":"Noisy-Correspondence Learning for Text-to-Image Person Re-identification","created":"2023-08-19","cited_by_count":56},{"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":"2305.08386","title":"PLIP: Language-Image Pre-training for Person Representation Learning","created":"2023-05-15","cited_by_count":49},{"id":"2006.12774","title":"Surpassing Real-World Source Training Data: Random 3D Characters for Generalizable Person Re-Identification","created":"2020-06-23","cited_by_count":42},{"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":"2405.04940","title":"Harnessing the Power of MLLMs for Transferable Text-to-Image Person ReID","created":"2024-05-08","cited_by_count":39},{"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},{"id":"2209.06209","title":"Look Before You Leap: Improving Text-based Person Retrieval by Learning A Consistent Cross-modal Common Manifold","created":"2022-09-13","cited_by_count":38},{"id":"2308.10045","title":"An Empirical Study of CLIP for Text-based Person Search","created":"2023-08-19","cited_by_count":38},{"id":"2012.04268","title":"UnrealPerson: An Adaptive Pipeline towards Costless Person Re-identification","created":"2020-12-08","cited_by_count":36},{"id":"2101.08238","title":"AXM-Net: Implicit Cross-Modal Feature Alignment for Person Re-identification","created":"2021-01-19","cited_by_count":34},{"id":"2210.09520","title":"Using Language to Extend to Unseen Domains","created":"2022-10-18","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":"2312.03441","title":"UFineBench: Towards Text-based Person Retrieval with Ultra-fine Granularity","created":"2023-12-06","cited_by_count":30},{"id":"2402.04625","title":"Noise Map Guidance: Inversion with Spatial Context for Real Image Editing","created":"2024-02-07","cited_by_count":25},{"id":"1701.03153","title":"Looking Beyond Appearances: Synthetic Training Data for Deep CNNs in Re-identification","created":"2017-01-11","cited_by_count":20},{"id":"2109.10498","title":"Less is More: Learning from Synthetic Data with Fine-grained Attributes for Person Re-Identification","created":"2021-09-22","cited_by_count":20},{"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},{"id":"2204.02611","title":"Cloning Outfits from Real-World Images to 3D Characters for Generalizable Person Re-Identification","created":"2022-04-06","cited_by_count":17},{"id":"2406.06045","title":"Synthesizing Efficient Data with Diffusion Models for Person Re-Identification Pre-Training","created":"2024-06-10","cited_by_count":11},{"id":"2309.04675","title":"BiLMa: Bidirectional Local-Matching for Text-based Person Re-identification","created":"2023-09-09","cited_by_count":8},{"id":"2311.09084","title":"Contrastive Transformer Learning with Proximity Data Generation for Text-Based Person Search","created":"2023-11-15","cited_by_count":8},{"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":"2406.16042","title":"Pose-dIVE: Pose-Diversified Augmentation with Diffusion Model for Person Re-Identification","created":"2024-06-23","cited_by_count":6},{"id":"2312.01745","title":"Cross-Modal Adaptive Dual Association for Text-to-Image Person Retrieval","created":"2023-12-04","cited_by_count":5},{"id":"2404.18106","title":"Semi-supervised Text-based Person Search","created":"2024-04-28","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}],"next_cursor":null}