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 926–950 of 1322 papers

TitleStatusHype
Cross-modal Learning for Multi-modal Video Categorization—0
A Deep Learning Method for Complex Human Activity Recognition Using Virtual Wearable Sensors—0
Uncertainty Quantification for Deep Context-Aware Mobile Activity Recognition and Unknown Context Discovery—0
Personalized Federated Learning for Intelligent IoT Applications: A Cloud-Edge based Framework—0
Mitigating Class Boundary Label Uncertainty to Reduce Both Model Bias and Variance—0
Human Activity Recognition using Multi-Head CNN followed by LSTMCode0
Convolutional Tensor-Train LSTM for Spatio-temporal LearningCode1
Three-Stream Fusion Network for First-Person Interaction Recognition—0
Human Activity Recognition: A Spatio-temporal Image Encoding of 3D Skeleton Data for Online Action DetectionCode0
An Information-rich Sampling Technique over Spatio-Temporal CNN for Classification of Human Actions in Videos—0
Measuring the Utilization of Public Open Spaces by Deep Learning: a Benchmark Study at the Detroit Riverfront—0
Multi-label Prediction in Time Series Data using Deep Neural Networks—0
Zero-Shot Activity Recognition with Videos—0
Are Accelerometers for Activity Recognition a Dead-end?—0
Deep Learning for Sensor-based Human Activity Recognition: Overview, Challenges and Opportunities—0
Motion Classification using Kinematically Sifted ACGAN-Synthesized Radar Micro-Doppler Signatures—0
Personalized Activity Recognition with Deep Triplet EmbeddingsCode0
Towards Generalizable Surgical Activity Recognition Using Spatial Temporal Graph Convolutional Networks—0
Classification of human activity recognition using smartphones—0
Improve Unsupervised Domain Adaptation with Mixup Training—0
Feature engineering workflow for activity recognition from synchronized inertial measurement unitsCode0
Bonn Activity Maps: Dataset Description—0
Enabling Machine Learning Across Heterogeneous Sensor Networks with Graph Autoencoders—0
DASZL: Dynamic Action Signatures for Zero-shot Learning—0
Kernel learning for visual perceptionCode0
Show:102550
← PrevPage 38 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