SOTAVerified

Activity Recognition

Human Activity Recognition is the problem of identifying events performed by humans given a video input. It is formulated as a binary (or multiclass) classification problem of outputting activity class labels. Activity Recognition is an important problem with many societal applications including smart surveillance, video search/retrieval, intelligent robots, and other monitoring systems.

Source: Learning Latent Sub-events in Activity Videos Using Temporal Attention Filters

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 301–325 of 1322 papers

TitleStatusHype
Adversarial Transferability in Wearable Sensor Systems—0
Deep Generative Domain Adaptation with Temporal Relation Knowledge for Cross-User Activity Recognition—0
A Semi-supervised Approach for Activity Recognition from Indoor Trajectory Data—0
Cross-modal Scalable Hierarchical Clustering in Hyperbolic space—0
ARN-LSTM: A Multi-Stream Fusion Model for Skeleton-based Action Recognition—0
Deep Generative Domain Adaptation with Temporal Attention for Cross-User Activity Recognition—0
Cross-modal Learning for Multi-modal Video Categorization—0
ARIC: An Activity Recognition Dataset in Classroom Surveillance Images—0
Adversarial Deep Feature Extraction Network for User Independent Human Activity Recognition—0
Cross-Domain HAR: Few Shot Transfer Learning for Human Activity Recognition—0
Cross-domain Activity Recognition via Substructural Optimal Transport—0
Cross-position Activity Recognition with Stratified Transfer Learning—0
Cross-Subject Transfer Learning in Human Activity Recognition Systems using Generative Adversarial Networks—0
Cross-user activity recognition using deep domain adaptation with temporal relation information—0
Cross-user activity recognition via temporal relation optimal transport—0
CrowdTransfer: Enabling Crowd Knowledge Transfer in AIoT Community—0
CSI-Based Cross-Domain Activity Recognition via Zero-Shot Prototypical Networks—0
CSI-Based Efficient Self-Quarantine Monitoring System Using Branchy Convolution Neural Network—0
Arianna+: Scalable Human Activity Recognition by Reasoning with a Network of Ontologies—0
A Close Look into Human Activity Recognition Models using Deep Learning—0
Cross-Country Skiing Gears Classification using Deep Learning—0
DanHAR: Dual Attention Network For Multimodal Human Activity Recognition Using Wearable Sensors—0
CROMOSim: A Deep Learning-based Cross-modality Inertial Measurement Simulator—0
A Review of Machine Learning Methods Applied to Video Analysis Systems—0
Creating a Large-scale Synthetic Dataset for Human Activity Recognition—0
Show:102550
← PrevPage 13 of 53Next →
All datasetsRWF-2000Stanford40First-Person Hand Action BenchmarkSelf-stimulatory Behavior Dataset

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Structured Keypoint PoolingAccuracy93.4—Unverified
2Semi-Supervised Hard Attention (SSHA); pretrained on Deepmind Kinetics datasetAccuracy90.4—Unverified
3Human Skeletons + Change DetectionAccuracy90.25—Unverified
4Separable Convolutional LSTMAccuracy89.75—Unverified
5SPIL ConvolutionAccuracy89.3—Unverified
6Flow Gated NetworkAccuracy87.25—Unverified
#ModelMetricClaimedVerifiedStatus
1FocusCLIPTop-3 Accuracy (%)10.47—Unverified
2CLIPTop-3 Accuracy (%)6.49—Unverified
#ModelMetricClaimedVerifiedStatus
1Boutaleb et al.1:1 Accuracy97.91—Unverified
#ModelMetricClaimedVerifiedStatus
1all-landmark-modelActivity Recognition0.76—Unverified