SOTAVerified

Pedestrian Attribute Recognition

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.

( Image credit: HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 26–50 of 56 papers

TitleStatusHype
Data Augmentation Imbalance For Imbalanced Attribute Classification—0
Deep Template Matching for Pedestrian Attribute Recognition with the Auxiliary Supervision of Attribute-wise Keypoints—0
Enhanced Visual-Semantic Interaction with Tailored Prompts for Pedestrian Attribute Recognition—0
FOCUS: Fine-grained Optimization with Semantic Guided Understanding for Pedestrian Attributes Recognition—0
Identity-Aware Attribute Recognition via Real-Time Distributed Inference in Mobile Edge Clouds—0
Knowledge Assembly: Semi-Supervised Multi-Task Learning from Multiple Datasets with Disjoint Labels—0
Learning Disentangled Label Representations for Multi-label Classification—0
Lightweight Attribute Localizing Models for Pedestrian Attribute Recognition—0
Localization Guided Learning for Pedestrian Attribute Recognition—0
Multi-Task Learning via Co-Attentive Sharing for Pedestrian Attribute Recognition—0
Pedestrian Attribute Recognition in Video Surveillance Scenarios Based on View-attribute Attention Localization—0
Reinforced Pedestrian Attribute Recognition with Group Optimization Reward—0
Robust Pedestrian Attribute Recognition Using Group Sparsity for Occlusion Videos—0
Spatial and Semantic Consistency Regularizations for Pedestrian Attribute Recognition—0
Unsupervised Domain-Adaptive Person Re-identification Based on Attributes—0
A Temporal Attentive Approach for Video-Based Pedestrian Attribute Recognition—0
Incremental Few-Shot Learning for Pedestrian Attribute Recognition—0
ViTA-PAR: Visual and Textual Attribute Alignment with Attribute Prompting for Pedestrian Attribute RecognitionCode0
SequencePAR: Understanding Pedestrian Attributes via A Sequence Generation ParadigmCode0
SNN-PAR: Energy Efficient Pedestrian Attribute Recognition via Spiking Neural NetworksCode0
Adversarial Semantic and Label Perturbation Attack for Pedestrian Attribute RecognitionCode0
HydraPlus-Net: Attentive Deep Features for Pedestrian AnalysisCode0
SSPNet: Scale and Spatial Priors Guided Generalizable and Interpretable Pedestrian Attribute RecognitionCode0
YinYang-Net: Complementing Face and Body Information for Wild Gender RecognitionCode0
A Solution to Co-occurrence Bias: Attributes Disentanglement via Mutual Information Minimization for Pedestrian Attribute RecognitionCode0
Show:102550
← PrevPage 2 of 3Next →
All datasetsPA-100KPETARAPv2RAPUAV-HumanDukeMTMC-attributeMarket1501-AttributesUPAR

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1AttivisionF1 score93.1—Unverified
2PATH (Partial FT)Accuracy90.8—Unverified
3AttrivisionAccuracy 89.8—Unverified
4Hulk(Finetune, ViT-L)Accuracy88.97—Unverified
5Hulk(Finetune, ViT-B)Accuracy87.85—Unverified
6C2T-NetAccuracy87.2—Unverified
7SOLIDERAccuracy86.38—Unverified
8UniHCP (finetune)Accuracy86.18—Unverified
9APTMAccuracy80.17—Unverified
10Label2LabelAccuracy79.23—Unverified
#ModelMetricClaimedVerifiedStatus
1UniHCP (FT)Accuracy88.78—Unverified
2C2T-NetAccuracy88.2—Unverified
3ALM[tang2019Improving] (ICCV19)Accuracy79.52—Unverified
4Attribute-Specific LocalizationAccuracy79.52—Unverified
5strongbaselineAccuracy79.14—Unverified
6HP-netAccuracy76.13—Unverified
#ModelMetricClaimedVerifiedStatus
1Hulk(Finetune, ViT-L)Accuracy85.86—Unverified
2Hulk(Finetune, ViT-B)Accuracy85.26—Unverified
3AttrivisionAccuracy 84.2—Unverified
4UniHCP (finetune)Accuracy82.34—Unverified
#ModelMetricClaimedVerifiedStatus
1Attribute-Specific LocalizationAccuracy68.17—Unverified
2HP-netAccuracy65.39—Unverified
#ModelMetricClaimedVerifiedStatus
1DenseNetBackpack63.9—Unverified
2ResNetBackpack63.5—Unverified
#ModelMetricClaimedVerifiedStatus
1MBNETAccuracy91.13—Unverified
#ModelMetricClaimedVerifiedStatus
1AttrivisionAccuracy 83.8—Unverified
#ModelMetricClaimedVerifiedStatus
1AttrivisionAccuracy 89.4—Unverified