{"total":134,"rows":[{"id":"2101.05278","title":"GAN Inversion: A Survey","created":"2021-01-14","cited_by_count":367,"area":null},{"id":"2212.07422","title":"ECON: Explicit Clothed humans Optimized via Normal integration","created":"2022-12-14","cited_by_count":199,"area":null},{"id":"2304.06025","title":"DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion","created":"2023-04-12","cited_by_count":167,"area":"diffusion"},{"id":"2307.00040","title":"DisCo: Disentangled Control for Realistic Human Dance Generation","created":"2023-06-30","cited_by_count":142,"area":null},{"id":"2111.06119","title":"Fine-Grained Image Analysis with Deep Learning: A Survey","created":"2021-11-11","cited_by_count":135,"area":null},{"id":"2311.12052","title":"MagicPose: Realistic Human Poses and Facial Expressions Retargeting with Identity-aware Diffusion","created":"2023-11-18","cited_by_count":117,"area":"diffusion"},{"id":"2308.08545","title":"TeCH: Text-guided Reconstruction of Lifelike Clothed Humans","created":"2023-08-16","cited_by_count":104,"area":"diffusion"},{"id":"2407.15886","title":"CatVTON: Concatenation Is All You Need for Virtual Try-On with Diffusion Models","created":"2024-07-21","cited_by_count":102,"area":"diffusion"},{"id":"2204.01694","title":"\"This is my unicorn, Fluffy\": Personalizing frozen vision-language representations","created":"2022-04-04","cited_by_count":95,"area":null},{"id":"2501.15891","title":"Any2AnyTryon: Leveraging Adaptive Position Embeddings for Versatile Virtual Clothing Tasks","created":"2025-01-27","cited_by_count":63,"area":null},{"id":"2303.02936","title":"UniHCP: A Unified Model for Human-Centric Perceptions","created":"2023-03-06","cited_by_count":59,"area":null},{"id":"2302.14383","title":"Linear Spaces of Meanings: Compositional Structures in Vision-Language Models","created":"2023-02-28","cited_by_count":48,"area":"mllm"},{"id":"2407.07111","title":"Diffusion Model-Based Video Editing: A Survey","created":"2024-06-26","cited_by_count":44,"area":"diffusion"},{"id":"2207.10053","title":"3D Clothed Human Reconstruction in the Wild","created":"2022-07-20","cited_by_count":42,"area":null},{"id":"2408.06047","title":"BooW-VTON: Boosting In-the-Wild Virtual Try-On via Mask-Free Pseudo Data Training","created":"2024-08-12","cited_by_count":37,"area":"diffusion"},{"id":"2207.10387","title":"Pose for Everything: Towards Category-Agnostic Pose Estimation","created":"2022-07-21","cited_by_count":36,"area":null},{"id":"2311.16094","title":"Street TryOn: Learning In-the-Wild Virtual Try-On from Unpaired Person Images","created":"2023-11-27","cited_by_count":34,"area":null},{"id":"2305.14236","title":"REC-MV: REconstructing 3D Dynamic Cloth from Monocular Videos","created":"2023-05-23","cited_by_count":29,"area":null},{"id":"2112.06183","title":"Few-shot Keypoint Detection with Uncertainty Learning for Unseen Species","created":"2021-12-12","cited_by_count":27,"area":null},{"id":"2306.15521","title":"What a MESS: Multi-Domain Evaluation of Zero-Shot Semantic Segmentation","created":"2023-06-27","cited_by_count":24,"area":null},{"id":"2105.06047","title":"Compatibility-aware Heterogeneous Visual Search","created":"2021-05-13","cited_by_count":23,"area":null},{"id":"2312.01697","title":"Hulk: A Universal Knowledge Translator for Human-Centric Tasks","created":"2023-12-04","cited_by_count":22,"area":null},{"id":"2310.08530","title":"X-Pose: Detecting Any Keypoints","created":"2023-10-12","cited_by_count":21,"area":null},{"id":"2203.15320","title":"Dressing in the Wild by Watching Dance Videos","created":"2022-03-29","cited_by_count":20,"area":null},{"id":"2502.03449","title":"Dress-1-to-3: Single Image to Simulation-Ready 3D Outfit with Diffusion Prior and Differentiable Physics","created":"2025-02-05","cited_by_count":20,"area":"diffusion"},{"id":"2411.18350","title":"TryOffDiff: Virtual-Try-Off via High-Fidelity Garment Reconstruction using Diffusion Models","created":"2024-11-27","cited_by_count":19,"area":"diffusion"},{"id":"2301.00394","title":"Deep Learning Technique for Human Parsing: A Survey and Outlook","created":"2023-01-01","cited_by_count":18,"area":null},{"id":"2303.16382","title":"ARMBench: An Object-centric Benchmark Dataset for Robotic Manipulation","created":"2023-03-29","cited_by_count":18,"area":null},{"id":"2410.10817","title":"When Does Perceptual Alignment Benefit Vision Representations?","created":"2024-10-14","cited_by_count":18,"area":null},{"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,"area":null},{"id":"2207.11169","title":"Rethinking Few-Shot Object Detection on a Multi-Domain Benchmark","created":"2022-07-22","cited_by_count":17,"area":null},{"id":"2302.09899","title":"A Survey on Semi-Supervised Semantic Segmentation","created":"2023-02-20","cited_by_count":17,"area":null},{"id":"2306.10169","title":"Meta-Personalizing Vision-Language Models to Find Named Instances in Video","created":"2023-06-16","cited_by_count":16,"area":"mllm"},{"id":"2501.09503","title":"AnyStory: Towards Unified Single and Multiple Subject Personalization in Text-to-Image Generation","created":"2025-01-16","cited_by_count":16,"area":null},{"id":"2112.03111","title":"Ethics and Creativity in Computer Vision","created":"2021-12-06","cited_by_count":15,"area":null},{"id":"2111.15140","title":"Robust 3D Garment Digitization from Monocular 2D Images for 3D Virtual Try-On Systems","created":"2021-11-30","cited_by_count":13,"area":null},{"id":"2407.10937","title":"IDOL: Unified Dual-Modal Latent Diffusion for Human-Centric Joint Video-Depth Generation","created":"2024-07-15","cited_by_count":11,"area":"diffusion"},{"id":"2108.01819","title":"Transfer Learning for Pose Estimation of Illustrated Characters","created":"2021-08-04","cited_by_count":10,"area":null},{"id":"2112.07200","title":"Weakly Supervised High-Fidelity Clothing Model Generation","created":"2021-12-14","cited_by_count":9,"area":null},{"id":"2406.00384","title":"CapeX: Category-Agnostic Pose Estimation from Textual Point Explanation","created":"2024-06-01","cited_by_count":9,"area":null},{"id":"2412.16156","title":"Personalized Representation from Personalized Generation","created":"2024-12-20","cited_by_count":9,"area":null},{"id":"2507.15037","title":"OmniVTON: Training-Free Universal Virtual Try-On","created":"2025-07-20","cited_by_count":9,"area":"diffusion"},{"id":"2304.03140","title":"From Saliency to DINO: Saliency-guided Vision Transformer for Few-shot Keypoint Detection","created":"2023-04-06","cited_by_count":8,"area":null},{"id":"2601.14706","title":"LookBench: A Live and Holistic Open Benchmark for Fashion Image Retrieval","created":"2026-01-21","cited_by_count":7,"area":null},{"id":"2607.06560","title":"Vision as Unified Multimodal Generation","created":"2026-07-07","cited_by_count":7,"area":null},{"id":"2107.05856","title":"eProduct: A Million-Scale Visual Search Benchmark to Address Product Recognition Challenges","created":"2021-07-13","cited_by_count":6,"area":null},{"id":"2112.02763","title":"MetaCloth: Learning Unseen Tasks of Dense Fashion Landmark Detection from a Few Samples","created":"2021-12-06","cited_by_count":6,"area":null},{"id":"2204.03111","title":"UIGR: Unified Interactive Garment Retrieval","created":"2022-04-06","cited_by_count":6,"area":null},{"id":"2208.11253","title":"FashionVQA: A Domain-Specific Visual Question Answering System","created":"2022-08-24","cited_by_count":6,"area":null},{"id":"2305.14986","title":"Non-adversarial Robustness of Deep Learning Methods for Computer Vision","created":"2023-05-24","cited_by_count":6,"area":null},{"id":"2106.12154","title":"Neural Fashion Image Captioning : Accounting for Data Diversity","created":"2021-06-23","cited_by_count":5,"area":null},{"id":"2109.04654","title":"Per Garment Capture and Synthesis for Real-time Virtual Try-on","created":"2021-09-10","cited_by_count":5,"area":null},{"id":"2204.11004","title":"Training and challenging models for text-guided fashion image retrieval","created":"2022-04-23","cited_by_count":5,"area":null},{"id":"2411.01846","title":"KptLLM: Unveiling the Power of Large Language Model for Keypoint Comprehension","created":"2024-11-04","cited_by_count":5,"area":"mllm"},{"id":"2110.02627","title":"MovingFashion: a Benchmark for the Video-to-Shop Challenge","created":"2021-10-06","cited_by_count":4,"area":null},{"id":"2111.00905","title":"Smart Fashion: A Review of AI Applications in the Fashion & Apparel Industry","created":"2021-10-28","cited_by_count":4,"area":null},{"id":"2111.12346","title":"Arbitrary Virtual Try-On Network: Characteristics Preservation and Trade-off between Body and Clothing","created":"2021-11-24","cited_by_count":4,"area":null},{"id":"2303.10945","title":"Open-World Pose Transfer via Sequential Test-Time Adaption","created":"2023-03-20","cited_by_count":4,"area":null},{"id":"2303.15266","title":"Multi-Granularity Archaeological Dating of Chinese Bronze Dings Based on a Knowledge-Guided Relation Graph","created":"2023-03-27","cited_by_count":4,"area":null},{"id":"2306.02928","title":"LRVS-Fashion: Extending Visual Search with Referring Instructions","created":"2023-06-05","cited_by_count":4,"area":null},{"id":"2309.13489","title":"Identifying Systematic Errors in Object Detectors with the SCROD Pipeline","created":"2023-09-23","cited_by_count":4,"area":null},{"id":"2505.21062","title":"Inverse Virtual Try-On: Generating Multi-Category Product-Style Images from Clothed Individuals","created":"2025-05-27","cited_by_count":4,"area":null},{"id":"2101.06770","title":"Improving Apparel Detection with Category Grouping and Multi-grained Branches","created":"2021-01-17","cited_by_count":3,"area":null},{"id":"2104.08422","title":"Fashion-Guided Adversarial Attack on Person Segmentation","created":"2021-04-17","cited_by_count":3,"area":null},{"id":"2201.09594","title":"Describe me if you can! Characterized Instance-level Human Parsing","created":"2022-01-24","cited_by_count":3,"area":null},{"id":"2202.09450","title":"Modern Augmented Reality: Applications, Trends, and Future Directions","created":"2022-02-18","cited_by_count":3,"area":null},{"id":"2206.10146","title":"KE-RCNN: Unifying Knowledge based Reasoning into Part-level Attribute Parsing","created":"2022-06-21","cited_by_count":3,"area":null},{"id":"2208.00725","title":"Fashion Recommendation Based on Style and Social Events","created":"2022-08-01","cited_by_count":3,"area":null},{"id":"2211.14451","title":"GLAMI-1M: A Multilingual Image-Text Fashion Dataset","created":"2022-11-17","cited_by_count":3,"area":null},{"id":"2301.06160","title":"TextileNet: A Material Taxonomy-based Fashion Textile Dataset","created":"2023-01-15","cited_by_count":3,"area":null},{"id":"2308.04912","title":"Cross-view Semantic Alignment for Livestreaming Product Recognition","created":"2023-08-09","cited_by_count":3,"area":null},{"id":"2309.16189","title":"Cloth2Body: Generating 3D Human Body Mesh from 2D Clothing","created":"2023-09-28","cited_by_count":3,"area":null},{"id":"2503.01092","title":"One-Shot Affordance Grounding of Deformable Objects in Egocentric Organizing Scenes","created":"2025-03-03","cited_by_count":3,"area":null},{"id":"2503.12588","title":"Progressive Limb-Aware Virtual Try-On","created":"2025-03-16","cited_by_count":3,"area":null},{"id":"2111.07815","title":"Sentiment Analysis of Fashion Related Posts in Social Media","created":"2021-11-15","cited_by_count":2,"area":null},{"id":"2403.11593","title":"End-to-end multi-modal product matching in fashion e-commerce","created":"2024-03-18","cited_by_count":2,"area":null},{"id":"2506.10182","title":"Improving Personalized Search with Regularized Low-Rank Parameter Updates","created":"2025-06-11","cited_by_count":2,"area":null},{"id":"2507.22361","title":"Object Recognition Datasets and Challenges: A Review","created":"2025-07-30","cited_by_count":2,"area":null},{"id":"2508.08488","title":"MuGa-VTON: Multi-Garment Virtual Try-On via Diffusion Transformers with Prompt Customization","created":"2025-08-11","cited_by_count":2,"area":"diffusion"},{"id":"2511.18765","title":"NI-Tex: Non-isometric Image-based Garment Texture Generation","created":"2025-11-24","cited_by_count":2,"area":null},{"id":"2105.03050","title":"fAshIon after fashion: A Report of AI in Fashion","created":"2021-05-07","cited_by_count":1,"area":null},{"id":"2112.05328","title":"Multimodal Interactions Using Pretrained Unimodal Models for SIMMC 2.0","created":"2021-12-10","cited_by_count":1,"area":null},{"id":"2204.03998","title":"SnapMode: An Intelligent and Distributed Large-Scale Fashion Image Retrieval Platform Based On Big Data and Deep Generative Adversarial Network Technologies","created":"2022-04-08","cited_by_count":1,"area":null},{"id":"2208.06962","title":"InvisibiliTee: Angle-agnostic Cloaking from Person-Tracking Systems with a Tee","created":"2022-08-15","cited_by_count":1,"area":null},{"id":"2304.08107","title":"DETR-based Layered Clothing Segmentation and Fine-Grained Attribute Recognition","created":"2023-04-17","cited_by_count":1,"area":null},{"id":"2312.01656","title":"The Contemporary Art of Image Search: Iterative User Intent Expansion via Vision-Language Model","created":"2023-12-04","cited_by_count":1,"area":"mllm"},{"id":"2401.12433","title":"A Novel Garment Transfer Method Supervised by Distilled Knowledge of Virtual Try-on Model","created":"2024-01-23","cited_by_count":1,"area":"distill"},{"id":"2402.05941","title":"Character-based Outfit Generation with Vision-augmented Style Extraction via LLMs","created":"2024-02-02","cited_by_count":1,"area":null},{"id":"2404.08582","title":"FashionFail: Addressing Failure Cases in Fashion Object Detection and Segmentation","created":"2024-04-12","cited_by_count":1,"area":null},{"id":"2407.16248","title":"Spatiotemporal Graph Guided Multi-modal Network for Livestreaming Product Retrieval","created":"2024-07-23","cited_by_count":1,"area":null},{"id":"2409.13513","title":"Efficient and Discriminative Image Feature Extraction for Universal Image Retrieval","created":"2024-09-20","cited_by_count":1,"area":null},{"id":"2411.13901","title":"Dressing the Imagination: A Dataset for AI-Powered Translation of Text into Fashion Outfits and A Novel NeRA Adapter for Enhanced Feature Adaptation","created":"2024-11-21","cited_by_count":1,"area":null},{"id":"2502.12095","title":"Descriminative-Generative Custom Tokens for Vision-Language Models","created":"2025-02-17","cited_by_count":1,"area":"mllm"},{"id":"2604.05039","title":"ID-Sim: An Identity-Focused Similarity Metric","created":"2026-04-06","cited_by_count":1,"area":null},{"id":"2605.22552","title":"FashionLens: Toward Versatile Fashion Image Retrieval via Task-Adaptive Learning","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2104.02830","title":"IndoFashion : Apparel Classification for Indian Ethnic Clothes","created":"2021-04-06","cited_by_count":0,"area":null},{"id":"2106.12139","title":"PatentNet: A Large-Scale Incomplete Multiview, Multimodal, Multilabel Industrial Goods Image Database","created":"2021-06-23","cited_by_count":0,"area":null},{"id":"2201.10431","title":"Main Product Detection with Graph Networks for Fashion","created":"2022-01-25","cited_by_count":0,"area":null},{"id":"2203.05201","title":"Online Deep Metric Learning via Mutual Distillation","created":"2022-03-10","cited_by_count":0,"area":null},{"id":"2203.10996","title":"Technologies for AI-Driven Fashion Social Networking Service with E-Commerce","created":"2022-03-11","cited_by_count":0,"area":null}],"next_cursor":"100"}