Papers with Code 아카이브
Pedestrian Attribute Recognition
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 8
- 보존된 평가 기록
- 30
Pedestrian attribution recognition is the task of recognizing pedestrian features - such as whether they are talking on a phone, whether they have a backpack, and so on.
<span style="color:grey; opacity: 0.6">( Image credit: HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis )</span>
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
ViTA-PAR: Visual and Textual Attribute Alignment with Attribute Prompting for Pedestrian Attribute Recognition
Adversarial Semantic and Label Perturbation Attack for Pedestrian Attribute Recognition
RGB-Event based Pedestrian Attribute Recognition: A Benchmark Dataset and An Asymmetric RWKV Fusion Framework
SNN-PAR: Energy Efficient Pedestrian Attribute Recognition via Spiking Neural Networks
Pedestrian Attribute Recognition: A New Benchmark Dataset and A Large Language Model Augmented Framework
An Empirical Study of Mamba-based Pedestrian Attribute Recognition
Pedestrian Attribute Recognition as Label-balanced Multi-label Learning
Spatio-Temporal Side Tuning Pre-trained Foundation Models for Video-based Pedestrian Attribute Recognition
Pedestrian Attribute Recognition via CLIP based Prompt Vision-Language Fusion
SSPNet: Scale and Spatial Priors Guided Generalizable and Interpretable Pedestrian Attribute Recognition
SequencePAR: Understanding Pedestrian Attributes via A Sequence Generation Paradigm
Hulk: A Universal Knowledge Translator for Human-Centric Tasks
HAP: Structure-Aware Masked Image Modeling for Human-Centric Perception
A Solution to Co-occurrence Bias: Attributes Disentanglement via Mutual Information Minimization for Pedestrian Attribute Recognition
Lightweight Attribute Localizing Models for Pedestrian Attribute Recognition
Knowledge Assembly: Semi-Supervised Multi-Task Learning from Multiple Datasets with Disjoint Labels
Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmark
PLIP: Language-Image Pre-training for Person Representation Learning
Learning CLIP Guided Visual-Text Fusion Transformer for Video-based Pedestrian Attribute Recognition
PARFormer: Transformer-based Multi-Task Network for Pedestrian Attribute Recognition
Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks
POAR: Towards Open Vocabulary Pedestrian Attribute Recognition
HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining
UniHCP: A Unified Model for Human-Centric Perceptions
Learning Disentangled Label Representations for Multi-label Classification
UPAR: Unified Pedestrian Attribute Recognition and Person Retrieval
Label2Label: A Language Modeling Framework for Multi-Attribute Learning
Reinforced Pedestrian Attribute Recognition with Group Optimization Reward
Robust Pedestrian Attribute Recognition Using Group Sparsity for Occlusion Videos
Spatial and Semantic Consistency Regularizations for Pedestrian Attribute Recognition
YinYang-Net: Complementing Face and Body Information for Wild Gender Recognition
Rethinking of Pedestrian Attribute Recognition: A Reliable Evaluation under Zero-Shot Pedestrian Identity Setting
Pedestrian Attribute Recognition in Video Surveillance Scenarios Based on View-attribute Attention Localization
UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehicles
Deep Template Matching for Pedestrian Attribute Recognition with the Auxiliary Supervision of Attribute-wise Keypoints
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.