{"total":79,"rows":[{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013,"area":null},{"id":"2301.05712","title":"A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trends","created":"2023-01-13","cited_by_count":207,"area":null},{"id":"2304.03284","title":"SegGPT: Segmenting Everything In Context","created":"2023-04-06","cited_by_count":194,"area":null},{"id":"2308.06101","title":"Taming the Power of Diffusion Models for High-Quality Virtual Try-On with Appearance Flow","created":"2023-08-11","cited_by_count":124,"area":"diffusion"},{"id":"2112.00933","title":"PartImageNet: A Large, High-Quality Dataset of Parts","created":"2021-12-02","cited_by_count":107,"area":null},{"id":"2303.17602","title":"Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks","created":"2023-03-30","cited_by_count":96,"area":null},{"id":"2203.14335","title":"Deep Hierarchical Semantic Segmentation","created":"2022-03-27","cited_by_count":84,"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":"2106.06351","title":"Part-aware Panoptic Segmentation","created":"2021-06-11","cited_by_count":56,"area":null},{"id":"2404.18630","title":"4D-DRESS: A 4D Dataset of Real-world Human Clothing with Semantic Annotations","created":"2024-04-29","cited_by_count":54,"area":null},{"id":"2104.11536","title":"Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspective","created":"2021-04-23","cited_by_count":50,"area":null},{"id":"2305.08386","title":"PLIP: Language-Image Pre-training for Person Representation Learning","created":"2023-05-15","cited_by_count":49,"area":null},{"id":"2306.06211","title":"A Survey on Segment Anything Model (SAM): Vision Foundation Model Meets Prompt Engineering","created":"2023-05-12","cited_by_count":45,"area":null},{"id":"2111.10544","title":"Towards Scalable Unpaired Virtual Try-On via Patch-Routed Spatially-Adaptive GAN","created":"2021-11-20","cited_by_count":40,"area":null},{"id":"2303.05675","title":"HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining","created":"2023-03-10","cited_by_count":38,"area":null},{"id":"2108.05126","title":"M3D-VTON: A Monocular-to-3D Virtual Try-On Network","created":"2021-08-11","cited_by_count":31,"area":null},{"id":"2106.12733","title":"Feature Completion for Occluded Person Re-Identification","created":"2021-06-24","cited_by_count":30,"area":null},{"id":"2312.01623","title":"Universal Segmentation at Arbitrary Granularity with Language Instruction","created":"2023-12-04","cited_by_count":29,"area":null},{"id":"2111.14173","title":"CDGNet: Class Distribution Guided Network for Human Parsing","created":"2021-11-28","cited_by_count":26,"area":null},{"id":"2204.12037","title":"Causal Reasoning Meets Visual Representation Learning: A Prospective Study","created":"2022-04-26","cited_by_count":24,"area":"lr"},{"id":"2312.14404","title":"Cross-Covariate Gait Recognition: A Benchmark","created":"2023-12-22","cited_by_count":22,"area":null},{"id":"2204.07370","title":"2D Human Pose Estimation: A Survey","created":"2022-04-15","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":"2307.07187","title":"Erasing, Transforming, and Noising Defense Network for Occluded Person Re-Identification","created":"2023-07-14","cited_by_count":19,"area":null},{"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":"2105.05497","title":"CT-Net: Complementary Transfering Network for Garment Transfer with Arbitrary Geometric Changes","created":"2021-05-12","cited_by_count":17,"area":null},{"id":"2104.06770","title":"Graph-based Person Signature for Person Re-Identifications","created":"2021-04-14","cited_by_count":14,"area":null},{"id":"2103.05997","title":"Quality-Aware Network for Human Parsing","created":"2021-03-10","cited_by_count":13,"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":"2311.00603","title":"Occluded Person Re-Identification with Deep Learning: A Survey and Perspectives","created":"2023-11-01","cited_by_count":13,"area":null},{"id":"2207.14452","title":"Deep Learning-based Occluded Person Re-identification: A Survey","created":"2022-07-29","cited_by_count":12,"area":null},{"id":"2304.04140","title":"Semantic Human Parsing via Scalable Semantic Transfer over Multiple Label Domains","created":"2023-04-09","cited_by_count":11,"area":null},{"id":"2109.09113","title":"HPTQ: Hardware-Friendly Post Training Quantization","created":"2021-09-19","cited_by_count":10,"area":null},{"id":"2203.16168","title":"FLOAT: Factorized Learning of Object Attributes for Improved Multi-object Multi-part Scene Parsing","created":"2022-03-30","cited_by_count":9,"area":null},{"id":"2411.16619","title":"Human-Activity AGV Quality Assessment: A Benchmark Dataset and an Objective Evaluation Metric","created":"2024-11-25","cited_by_count":9,"area":null},{"id":"2401.02138","title":"Explore Human Parsing Modality for Action Recognition","created":"2024-01-04","cited_by_count":8,"area":null},{"id":"2105.11168","title":"Human-centric Relation Segmentation: Dataset and Solution","created":"2021-05-24","cited_by_count":7,"area":null},{"id":"2407.10918","title":"PartImageNet++ Dataset: Scaling up Part-based Models for Robust Recognition","created":"2024-07-15","cited_by_count":7,"area":null},{"id":"2410.06777","title":"HERM: Benchmarking and Enhancing Multimodal LLMs for Human-Centric Understanding","created":"2024-10-09","cited_by_count":7,"area":"mllm"},{"id":"2212.07671","title":"Multi-task Fusion for Efficient Panoptic-Part Segmentation","created":"2022-12-15","cited_by_count":6,"area":null},{"id":"2101.10620","title":"Graphonomy: Universal Image Parsing via Graph Reasoning and Transfer","created":"2021-01-26","cited_by_count":5,"area":null},{"id":"2303.09638","title":"Full-Body Cardiovascular Sensing with Remote Photoplethysmography","created":"2023-03-16","cited_by_count":5,"area":null},{"id":"2311.05077","title":"POISE: Pose Guided Human Silhouette Extraction under Occlusions","created":"2023-11-09","cited_by_count":5,"area":null},{"id":"2406.10114","title":"Task-aligned Part-aware Panoptic Segmentation through Joint Object-Part Representations","created":"2024-06-14","cited_by_count":5,"area":null},{"id":"2407.09686","title":"SPIN: Hierarchical Segmentation with Subpart Granularity in Natural Images","created":"2024-07-12","cited_by_count":5,"area":null},{"id":"2409.05277","title":"Disentangled Representations for Short-Term and Long-Term Person Re-Identification","created":"2024-09-09","cited_by_count":5,"area":null},{"id":"2105.01241","title":"End-to-end One-shot Human Parsing","created":"2021-05-04","cited_by_count":4,"area":null},{"id":"2109.10056","title":"Single Person Pose Estimation: A Survey","created":"2021-09-21","cited_by_count":4,"area":null},{"id":"2110.14147","title":"Image Comes Dancing with Collaborative Parsing-Flow Video Synthesis","created":"2021-10-27","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":"2406.19290","title":"Human Modelling and Pose Estimation Overview","created":"2024-06-27","cited_by_count":4,"area":null},{"id":"2105.02742","title":"Pose-Guided Sign Language Video GAN with Dynamic Lambda","created":"2021-05-06","cited_by_count":3,"area":null},{"id":"2201.03859","title":"On Exploring Pose Estimation as an Auxiliary Learning Task for Visible-Infrared Person Re-identification","created":"2022-01-11","cited_by_count":3,"area":null},{"id":"2210.07140","title":"U-HRNet: Delving into Improving Semantic Representation of High Resolution Network for Dense Prediction","created":"2022-10-13","cited_by_count":3,"area":null},{"id":"2304.05832","title":"Few Shot Semantic Segmentation: a review of methodologies, benchmarks, and open challenges","created":"2023-04-12","cited_by_count":3,"area":null},{"id":"2109.10322","title":"CondNet: Conditional Classifier for Scene Segmentation","created":"2021-09-21","cited_by_count":2,"area":null},{"id":"2111.06162","title":"Clicking Matters:Towards Interactive Human Parsing","created":"2021-11-11","cited_by_count":2,"area":null},{"id":"2202.04243","title":"Motion-Aware Transformer For Occluded Person Re-identification","created":"2022-02-09","cited_by_count":2,"area":null},{"id":"2212.13693","title":"Parsing Objects at a Finer Granularity: A Survey","created":"2022-12-28","cited_by_count":2,"area":null},{"id":"2307.07977","title":"Integrating Human Parsing and Pose Network for Human Action Recognition","created":"2023-07-16","cited_by_count":2,"area":null},{"id":"2311.18618","title":"JPPF: Multi-task Fusion for Consistent Panoptic-Part Segmentation","created":"2023-11-30","cited_by_count":2,"area":null},{"id":"2403.08650","title":"Data Augmentation in Human-Centric Vision","created":"2024-03-13","cited_by_count":2,"area":null},{"id":"2412.01048","title":"Cerberus: Attribute-based person re-identification using semantic IDs","created":"2024-12-02","cited_by_count":2,"area":null},{"id":"2503.08201","title":"Scale-Aware Pre-Training for Human-Centric Visual Perception: Enabling Lightweight and Generalizable Models","created":"2025-03-11","cited_by_count":2,"area":null},{"id":"2503.22237","title":"SCHNet: SAM Marries CLIP for Human Parsing","created":"2025-03-28","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":"2212.06550","title":"Body Segmentation Using Multi-task Learning","created":"2022-12-13","cited_by_count":1,"area":null},{"id":"2301.12416","title":"Deep Learning for Human Parsing: A Survey","created":"2023-01-29","cited_by_count":1,"area":null},{"id":"2307.13240","title":"Fashion Matrix: Editing Photos by Just Talking","created":"2023-07-25","cited_by_count":1,"area":null},{"id":"2309.00938","title":"Exploring the Robustness of Human Parsers Towards Common Corruptions","created":"2023-09-02","cited_by_count":1,"area":null},{"id":"2407.03549","title":"POSTURE: Pose Guided Unsupervised Domain Adaptation for Human Body Part Segmentation","created":"2024-07-04","cited_by_count":1,"area":null},{"id":"2211.06688","title":"Partial Visual-Semantic Embedding: Fashion Intelligence System with Sensitive Part-by-Part Learning","created":"2022-11-12","cited_by_count":0,"area":null},{"id":"2404.00107","title":"Robust Ensemble Person Re-Identification via Orthogonal Fusion with Occlusion Handling","created":"2024-03-29","cited_by_count":0,"area":null},{"id":"2404.08419","title":"Direct May Not Be the Best: An Incremental Evolution View of Pose Generation","created":"2024-04-12","cited_by_count":0,"area":null},{"id":"2411.02858","title":"OLAF: A Plug-and-Play Framework for Enhanced Multi-object Multi-part Scene Parsing","created":"2024-11-05","cited_by_count":0,"area":null},{"id":"2502.19540","title":"Dictionary-based Framework for Interpretable and Consistent Object Parsing","created":"2025-02-26","cited_by_count":0,"area":null},{"id":"2508.07144","title":"Dynamic Pattern Alignment Learning for Pretraining Lightweight Human-Centric Vision Models","created":"2025-08-10","cited_by_count":0,"area":"moe"},{"id":"2512.10102","title":"Hierarchical Instance Tracking to Balance Privacy Preservation with Accessible Information","created":"2025-12-10","cited_by_count":0,"area":null},{"id":"2601.01454","title":"PartImageNet++ Dataset: Enhancing Visual Models with High-Quality Part Annotations","created":"2026-01-04","cited_by_count":0,"area":null}],"next_cursor":null}