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 826–850 of 1322 papers

TitleStatusHype
Self-supervised transfer learning of physiological representations from free-living wearable dataCode1
Human activity recognition using improved dynamic image—0
Generic Semi-Supervised Adversarial Subject Translation for Sensor-Based Human Activity Recognition—0
Skeleton-based Relational Reasoning for Group Activity Analysis—0
Learning Generalizable Physiological Representations from Large-scale Wearable DataCode1
A Tree-structure Convolutional Neural Network for Temporal Features Exaction on Sensor-based Multi-resident Activity Recognition—0
Leveraging Activity Recognition to Enable Protective Behavior Detection in Continuous DataCode0
Semi-supervised Federated Learning for Activity Recognition—0
A Framework of Combining Short-Term Spatial/Frequency Feature Extraction and Long-Term IndRNN for Activity Recognition—0
Bubblenet: A Disperse Recurrent Structure To Recognize Activities—0
HHAR-net: Hierarchical Human Activity Recognition using Neural NetworksCode1
Improved Actor Relation Graph based Group Activity RecognitionCode1
Self-supervised Human Activity Recognition by Learning to Predict Cross-Dimensional Motion—0
Pose And Joint-Aware Action RecognitionCode0
Egok360: A 360 Egocentric Kinetic Human Activity Video Dataset—0
Automated Human Activity Recognition by Colliding Bodies Optimization-based Optimal Feature Selection with Recurrent Neural Network—0
Deep learning for time series classificationCode2
Attention-Driven Body Pose Encoding for Human Activity Recognition—0
Semi-supervised sequence classification through change point detection—0
Stacked Generalization for Human Activity Recognition—0
MARS: Mixed Virtual and Real Wearable Sensors for Human Activity Recognition with Multi-Domain Deep Learning Model—0
Multi-Label Activity Recognition using Activity-specific Features and Activity Correlations—0
Energy Expenditure Estimation Through Daily Activity Recognition Using a Smart-phone—0
Personalization in Human Activity Recognition—0
A benchmark of data stream classification for human activity recognition on connected objectsCode0
Show:102550
← PrevPage 34 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