{"total":46,"rows":[{"id":"2302.10035","title":"Large-scale Multi-Modal Pre-trained Models: A Comprehensive Survey","created":"2023-02-20","cited_by_count":153,"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":"2404.09516","title":"State Space Model for New-Generation Network Alternative to Transformers: A Survey","created":"2024-04-15","cited_by_count":59,"area":null},{"id":"2105.11628","title":"TIPCB: A Simple but Effective Part-based Convolutional Baseline for Text-based Person Search","created":"2021-05-25","cited_by_count":57,"area":null},{"id":"2109.05686","title":"Spatial and Semantic Consistency Regularizations for Pedestrian Attribute Recognition","created":"2021-09-13","cited_by_count":32,"area":null},{"id":"2312.10692","title":"Pedestrian Attribute Recognition via CLIP based Prompt Vision-Language Fusion","created":"2023-12-17","cited_by_count":24,"area":null},{"id":"2107.03178","title":"Levels of explainable artificial intelligence for human-aligned conversational explanations","created":"2021-07-07","cited_by_count":21,"area":null},{"id":"2304.07230","title":"PARFormer: Transformer-based Multi-Task Network for Pedestrian Attribute Recognition","created":"2023-04-14","cited_by_count":19,"area":null},{"id":"2312.01640","title":"SequencePAR: Understanding Pedestrian Attributes via A Sequence Generation Paradigm","created":"2023-12-04","cited_by_count":13,"area":null},{"id":"2209.02522","title":"UPAR: Unified Pedestrian Attribute Recognition and Person Retrieval","created":"2022-09-06","cited_by_count":10,"area":null},{"id":"2304.10091","title":"Learning CLIP Guided Visual-Text Fusion Transformer for Video-based Pedestrian Attribute Recognition","created":"2023-04-20","cited_by_count":10,"area":null},{"id":"2408.09720","title":"Pedestrian Attribute Recognition: A New Benchmark Dataset and A Large Language Model Augmented Framework","created":"2024-08-19","cited_by_count":10,"area":null},{"id":"2405.04858","title":"Pedestrian Attribute Recognition as Label-balanced Multi-label Learning","created":"2024-05-08","cited_by_count":8,"area":null},{"id":"2312.06049","title":"SSPNet: Scale and Spatial Priors Guided Generalizable and Interpretable Pedestrian Attribute Recognition","created":"2023-12-11","cited_by_count":7,"area":null},{"id":"2312.09812","title":"Structural Information Guided Multimodal Pre-training for Vehicle-centric Perception","created":"2023-12-15","cited_by_count":7,"area":null},{"id":"2504.10018","title":"RGB-Event based Pedestrian Attribute Recognition: A Benchmark Dataset and An Asymmetric RWKV Fusion Framework","created":"2025-04-14","cited_by_count":7,"area":null},{"id":"2308.07537","title":"AttMOT: Improving Multiple-Object Tracking by Introducing Auxiliary Pedestrian Attributes","created":"2023-08-15","cited_by_count":6,"area":null},{"id":"2404.17929","title":"Spatio-Temporal Side Tuning Pre-trained Foundation Models for Video-based Pedestrian Attribute Recognition","created":"2024-04-27","cited_by_count":6,"area":null},{"id":"2408.00096","title":"From Attributes to Natural Language: A Survey and Foresight on Text-based Person Re-identification","created":"2024-07-31","cited_by_count":5,"area":null},{"id":"2105.11373","title":"Large-Scale Attribute-Object Compositions","created":"2021-05-24","cited_by_count":4,"area":null},{"id":"2405.06574","title":"Deep video representation learning: a survey","created":"2024-05-10","cited_by_count":4,"area":null},{"id":"2507.13659","title":"When Person Re-Identification Meets Event Camera: A Benchmark Dataset and An Attribute-guided Re-Identification Framework","created":"2025-07-18","cited_by_count":4,"area":null},{"id":"2105.05794","title":"Is Gender \"In-the-Wild\" Inference Really a Solved Problem?","created":"2021-05-12","cited_by_count":3,"area":null},{"id":"2303.14643","title":"POAR: Towards Open Vocabulary Pedestrian Attribute Recognition","created":"2023-03-26","cited_by_count":3,"area":null},{"id":"2312.06306","title":"Attribute Annotation and Bias Evaluation in Visual Datasets for Autonomous Driving","created":"2023-12-11","cited_by_count":3,"area":null},{"id":"2406.18845","title":"Retain, Blend, and Exchange: A Quality-aware Spatial-Stereo Fusion Approach for Event Stream Recognition","created":"2024-06-27","cited_by_count":3,"area":null},{"id":"2408.13031","title":"VFM-Det: Towards High-Performance Vehicle Detection via Large Foundation Models","created":"2024-08-23","cited_by_count":3,"area":null},{"id":"2110.08708","title":"Robust Pedestrian Attribute Recognition Using Group Sparsity for Occlusion Videos","created":"2021-10-17","cited_by_count":2,"area":null},{"id":"2111.08243","title":"CAR -- Cityscapes Attributes Recognition A Multi-category Attributes Dataset for Autonomous Vehicles","created":"2021-11-16","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":"2505.23313","title":"Adversarial Semantic and Label Perturbation Attack for Pedestrian Attribute Recognition","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2509.22331","title":"Pedestrian Attribute Recognition via Hierarchical Cross-Modality HyperGraph Learning","created":"2025-09-26","cited_by_count":2,"area":null},{"id":"2203.03079","title":"GlideNet: Global, Local and Intrinsic based Dense Embedding NETwork for Multi-category Attributes Prediction","created":"2022-03-07","cited_by_count":1,"area":null},{"id":"2307.14713","title":"GaitMorph: Transforming Gait by Optimally Transporting Discrete Codes","created":"2023-07-27","cited_by_count":1,"area":null},{"id":"2410.07857","title":"SNN-PAR: Energy Efficient Pedestrian Attribute Recognition via Spiking Neural Networks","created":"2024-10-10","cited_by_count":1,"area":null},{"id":"2504.05830","title":"Human Activity Recognition using RGB-Event based Sensors: A Multi-modal Heat Conduction Model and A Benchmark Dataset","created":"2025-04-08","cited_by_count":1,"area":null},{"id":"2508.04260","title":"Segment Any Vehicle: Semantic and Visual Context Driven SAM and A Benchmark","created":"2025-08-06","cited_by_count":1,"area":null},{"id":"2509.18874","title":"When Ads Become Profiles: Uncovering the Invisible Risk of Web Advertising at Scale with LLMs","created":"2025-09-23","cited_by_count":1,"area":null},{"id":"2205.14042","title":"Reinforced Pedestrian Attribute Recognition with Group Optimization Reward","created":"2022-05-21","cited_by_count":0,"area":null},{"id":"2207.05456","title":"TransFA: Transformer-based Representation for Face Attribute Evaluation","created":"2022-07-12","cited_by_count":0,"area":null},{"id":"2209.13444","title":"Design Perspectives of Multitask Deep Learning Models and Applications","created":"2022-09-27","cited_by_count":0,"area":null},{"id":"2603.05114","title":"UniPAR: A Unified Framework for Pedestrian Attribute Recognition","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2603.19565","title":"PFM-VEPAR: Prompting Foundation Models for RGB-Event Camera based Pedestrian Attribute Recognition","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2606.14770","title":"An Empirical Analysis of Optimization Dynamics and Sparsity Boundaries in Large-Scale Pedestrian Attribute Recognition","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2608.11770","title":"Achieving Near-Zero-Overhead Multi-Model Hierarchical Classification in Real-Time Detection Pipelines","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2610.14589","title":"Attribute-Centric Vision-Language Alignment for Fine-Grained Gait Understanding","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}