{"total":57,"rows":[{"id":"2307.04767","title":"Semantic-SAM: Segment and Recognize Anything at Any Granularity","created":"2023-07-10","cited_by_count":185,"area":null},{"id":"2103.16483","title":"Benchmarking Representation Learning for Natural World Image Collections","created":"2021-03-30","cited_by_count":168,"area":null},{"id":"2301.01795","title":"PACO: Parts and Attributes of Common Objects","created":"2023-01-04","cited_by_count":146,"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":"2201.10766","title":"A Comprehensive Study of Image Classification Model Sensitivity to Foregrounds, Backgrounds, and Visual Attributes","created":"2022-01-26","cited_by_count":56,"area":null},{"id":"2305.11173","title":"Going Denser with Open-Vocabulary Part Segmentation","created":"2023-05-18","cited_by_count":51,"area":null},{"id":"2502.08826","title":"Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented Generation","created":"2025-02-12","cited_by_count":42,"area":"rag"},{"id":"2404.01294","title":"CosmicMan: A Text-to-Image Foundation Model for Humans","created":"2024-04-01","cited_by_count":30,"area":null},{"id":"2503.13881","title":"MMR: A Large-scale Benchmark Dataset for Multi-target and Multi-granularity Reasoning Segmentation","created":"2025-03-18","cited_by_count":28,"area":"lr"},{"id":"2207.10614","title":"A Dense Material Segmentation Dataset for Indoor and Outdoor Scene Parsing","created":"2022-07-21","cited_by_count":23,"area":null},{"id":"2204.04654","title":"Fashionformer: A simple, Effective and Unified Baseline for Human Fashion Segmentation and Recognition","created":"2022-04-10","cited_by_count":16,"area":null},{"id":"2104.07767","title":"Exploring Visual Engagement Signals for Representation Learning","created":"2021-04-15","cited_by_count":12,"area":null},{"id":"2207.10664","title":"Exploring Fine-Grained Audiovisual Categorization with the SSW60 Dataset","created":"2022-07-21","cited_by_count":12,"area":null},{"id":"2306.07399","title":"4DHumanOutfit: a multi-subject 4D dataset of human motion sequences in varying outfits exhibiting large displacements","created":"2023-06-12","cited_by_count":12,"area":null},{"id":"2104.05072","title":"Instagram Filter Removal on Fashionable Images","created":"2021-04-11","cited_by_count":8,"area":null},{"id":"2102.01690","title":"From Culture to Clothing: Discovering the World Events Behind A Century of Fashion Images","created":"2021-02-02","cited_by_count":7,"area":null},{"id":"2507.22627","title":"LOTS of Fashion! Multi-Conditioning for Image Generation via Sketch-Text Pairing","created":"2025-07-30","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":"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":"2204.07486","title":"Patch-wise Contrastive Style Learning for Instagram Filter Removal","created":"2022-04-15","cited_by_count":5,"area":null},{"id":"2206.10090","title":"KTN: Knowledge Transfer Network for Learning Multi-person 2D-3D Correspondences","created":"2022-06-21","cited_by_count":5,"area":null},{"id":"2312.16264","title":"SPnet: Estimating Garment Sewing Patterns from a Single Image","created":"2023-12-26","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":"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":"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":"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":"2506.14808","title":"PARC: A Quantitative Framework Uncovering the Symmetries within Vision Language Models","created":"2025-06-03","cited_by_count":3,"area":"mllm"},{"id":"2108.12992","title":"SHIFT15M: Fashion-specific dataset for set-to-set matching with several distribution shifts","created":"2021-08-30","cited_by_count":2,"area":null},{"id":"2111.14145","title":"FashionSearchNet-v2: Learning Attribute Representations with Localization for Image Retrieval with Attribute Manipulation","created":"2021-11-28","cited_by_count":2,"area":null},{"id":"2310.15447","title":"DeepIron: Predicting Unwarped Garment Texture from a Single Image","created":"2023-10-24","cited_by_count":2,"area":null},{"id":"2407.14944","title":"Automatic Generation of Fashion Images using Prompting in Generative Machine Learning Models","created":"2024-07-20","cited_by_count":2,"area":null},{"id":"2409.14679","title":"Quantifying Context Bias in Domain Adaptation for Object Detection","created":"2024-09-23","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":"2605.26391","title":"Garment Particles: A 2D--3D Symmetric Garment Representation for Generation and Editing","created":"2026-05-25","cited_by_count":2,"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":"2308.09764","title":"The Impact of Background Removal on Performance of Neural Networks for Fashion Image Classification and Segmentation","created":"2023-08-18","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":"2407.03901","title":"DiCTI: Diffusion-based Clothing Designer via Text-guided Input","created":"2024-07-04","cited_by_count":1,"area":null},{"id":"2507.07079","title":"Evaluating Attribute Confusion in Fashion Text-to-Image Generation","created":"2025-07-09","cited_by_count":1,"area":null},{"id":"2206.05982","title":"Learning Fashion Compatibility from In-the-wild Images","created":"2022-06-13","cited_by_count":0,"area":null},{"id":"2305.02307","title":"Fashionpedia-Taste: A Dataset towards Explaining Human Fashion Taste","created":"2023-05-03","cited_by_count":0,"area":null},{"id":"2305.02360","title":"Fashionpedia-Ads: Do Your Favorite Advertisements Reveal Your Fashion Taste?","created":"2023-05-03","cited_by_count":0,"area":null},{"id":"2305.18482","title":"Fashion Object Detection for Tops & Bottoms","created":"2023-05-29","cited_by_count":0,"area":null},{"id":"2308.12218","title":"CIParsing: Unifying Causality Properties into Multiple Human Parsing","created":"2023-08-23","cited_by_count":0,"area":null},{"id":"2501.07434","title":"Guided SAM: Label-Efficient Part Segmentation","created":"2025-01-13","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":"2602.18309","title":"Multi-Level Conditioning by Pairing Localized Text and Sketch for Fashion Image Generation","created":"2026-02-20","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":"2603.08147","title":"MV-Fashion: Towards Enabling Virtual Try-On and Size Estimation with Multi-View Paired Data","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2604.09249","title":"FashionStylist: An Expert Knowledge-enhanced Multimodal Dataset for Fashion Understanding","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2605.06115","title":"CrossCult-KIBench: A Benchmark for Cross-Cultural Knowledge Insertion in MLLMs","created":"2026-05-07","cited_by_count":0,"area":"mllm"},{"id":"2605.14874","title":"LPH-VTON: Resolving the Structure-Texture Dilemma of Virtual Try-On via Latent Process Handover","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2608.22688","title":"FashionKG-RAG: Knowledge Graph-Enhanced Retrieval-Augmented Generation for Fashion Question Answering","created":"2026-08-24","cited_by_count":0,"area":"rag"},{"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":"2609.37230","title":"Seeing Is Not Addressing: Auditing Linguistic Access to Frozen Visual Geometry","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}