{"total":32,"rows":[{"id":"2311.18803","title":"BioCLIP: A Vision Foundation Model for the Tree of Life","created":"2023-11-30","cited_by_count":161,"area":null},{"id":"2403.18816","title":"Garment3DGen: 3D Garment Stylization and Texture Generation","created":"2024-03-27","cited_by_count":26,"area":null},{"id":"2406.12723","title":"BIOSCAN-5M: A Multimodal Dataset for Insect Biodiversity","created":"2024-06-18","cited_by_count":24,"area":null},{"id":"2405.12420","title":"GarmentDreamer: 3DGS Guided Garment Synthesis with Diverse Geometry and Texture Details","created":"2024-05-20","cited_by_count":19,"area":null},{"id":"2502.18495","title":"A Comprehensive Survey on Composed Image Retrieval","created":"2025-02-19","cited_by_count":17,"area":null},{"id":"2309.05551","title":"OpenFashionCLIP: Vision-and-Language Contrastive Learning with Open-Source Fashion Data","created":"2023-09-11","cited_by_count":9,"area":null},{"id":"2410.17337","title":"Captions Speak Louder than Images: Generalizing Foundation Models for E-commerce from High-quality Multimodal Instruction Data","created":"2024-10-22","cited_by_count":6,"area":null},{"id":"2303.11761","title":"Reasonable Scale Machine Learning with Open-Source Metaflow","created":"2023-03-21","cited_by_count":5,"area":null},{"id":"2502.19782","title":"Open-Vocabulary Semantic Part Segmentation of 3D Human","created":"2025-02-27","cited_by_count":5,"area":null},{"id":"2508.15721","title":"EcomMMMU: Strategic Utilization of Visuals for Robust Multimodal E-commerce Models","created":"2025-08-21","cited_by_count":5,"area":null},{"id":"2507.09950","title":"Can GPT-4o mini and Gemini 2.0 Flash Predict Fine-Grained Fashion Product Attributes? A Zero-Shot Analysis","created":"2025-07-14","cited_by_count":3,"area":null},{"id":"2409.05347","title":"TriplePlay: Enhancing Federated Learning with CLIP for Non-IID Data and Resource Efficiency","created":"2024-09-09","cited_by_count":2,"area":null},{"id":"2503.12052","title":"A Text-to-3D Framework for Joint Generation of CG-Ready Humans and Compatible Garments","created":"2025-03-15","cited_by_count":2,"area":null},{"id":"2509.23242","title":"TATTOO: Training-free AesTheTic-aware Outfit recOmmendation","created":"2025-09-27","cited_by_count":2,"area":null},{"id":"2308.16126","title":"CorrEmbed: Evaluating Pre-trained Model Image Similarity Efficacy with a Novel Metric","created":"2023-08-30","cited_by_count":1,"area":null},{"id":"2311.09624","title":"AI Recommendation System for Enhanced Customer Experience: A Novel Image-to-Text Method","created":"2023-11-16","cited_by_count":1,"area":null},{"id":"2407.20845","title":"Assessing Graphical Perception of Image Embedding Models using Channel Effectiveness","created":"2024-07-30","cited_by_count":1,"area":null},{"id":"2606.27708","title":"ZooClaw-FashionSigLIP2: Distilled Fine-tuning for Robust Fashion Retrieval","created":"2026-06-26","cited_by_count":1,"area":null},{"id":"2304.11473","title":"(Vector) Space is Not the Final Frontier: Product Search as Program Synthesis","created":"2023-04-22","cited_by_count":0,"area":null},{"id":"2309.11608","title":"Dataset Factory: A Toolchain For Generative Computer Vision Datasets","created":"2023-09-20","cited_by_count":0,"area":null},{"id":"2404.01984","title":"Fashion Style Editing with Generative Human Prior","created":"2024-04-02","cited_by_count":0,"area":null},{"id":"2409.07464","title":"Reflective Human-Machine Co-adaptation for Enhanced Text-to-Image Generation Dialogue System","created":"2024-08-27","cited_by_count":0,"area":null},{"id":"2411.16096","title":"ENCLIP: Ensembling and Clustering-Based Contrastive Language-Image Pretraining for Fashion Multimodal Search with Limited Data and Low-Quality Images","created":"2024-11-25","cited_by_count":0,"area":null},{"id":"2509.24477","title":"Performance-Efficiency Trade-off for Fashion Image Retrieval","created":"2025-09-29","cited_by_count":0,"area":null},{"id":"2511.00072","title":"LookSync: Large-Scale Visual Product Search System for AI-Generated Fashion Looks","created":"2025-10-29","cited_by_count":0,"area":null},{"id":"2603.02658","title":"OmniFashion: Towards Generalist Fashion Intelligence via Multi-Task Vision-Language Learning","created":"2026-03-03","cited_by_count":0,"area":null},{"id":"2606.19627","title":"VCG: A Multimodal Retrieval Framework for E-Commerce Video Feeds under Extreme Cold-Start Conditions","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2607.20291","title":"Diverse-Intent Multi-Turn Fashion Image Retrieval","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2608.13888","title":"Autonomous Fashion Outfit Composition via Unified Aesthetic Foresight Model","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2608.25023","title":"CVE-SAI: Counterfactual Visual Evidence-Guided Selective Attribute Indexing for Risk-Controlled E-commerce Search","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2609.13279","title":"The MODA General Attribute Suite: A Four-Track Evaluation Benchmark for Fashion Attribute Extraction","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2610.17841","title":"FASHION-RQ: Mining Hierarchical Semantic Structure for Automated Evaluation of Fashion Retrieval","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}