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 101–125 of 1322 papers

TitleStatusHype
Classification of Abnormal Hand Movement for Aiding in Autism Detection: Machine Learning StudyCode1
Online Semi-Supervised Learning of Composite Event Rules by Combining Structure and Mass-Based Predicate SimilarityCode1
3D Human Shape and Pose from a Single Low-Resolution Image with Self-Supervised LearningCode1
Panoramic Human Activity RecognitionCode1
Privacy and Utility Preserving Sensor-Data TransformationsCode1
Protecting Sensory Data against Sensitive InferencesCode1
Real-world Anomaly Detection in Surveillance VideosCode1
RelCon: Relative Contrastive Learning for a Motion Foundation Model for Wearable DataCode1
Convolutional Tensor-Train LSTM for Spatio-temporal LearningCode1
SelfHAR: Improving Human Activity Recognition through Self-training with Unlabeled DataCode1
Exploring Few-Shot Adaptation for Activity Recognition on Diverse DomainsCode1
SemiPFL: Personalized Semi-Supervised Federated Learning Framework for Edge IntelligenceCode1
MOMA-LRG: Language-Refined Graphs for Multi-Object Multi-Actor Activity ParsingCode1
SGA-INTERACT: A 3D Skeleton-based Benchmark for Group Activity Understanding in Modern Basketball TacticCode1
SPAct: Self-supervised Privacy Preservation for Action RecognitionCode1
Skeleton-based Action Recognition via Spatial and Temporal Transformer NetworksCode1
SWL-Adapt: An Unsupervised Domain Adaptation Model with Sample Weight Learning for Cross-User Wearable Human Activity RecognitionCode1
TASAR: Transfer-based Attack on Skeletal Action RecognitionCode1
Time Series Segmentation Applied to a New Data Set for Mobile Sensing of Human ActivitiesCode1
Towards Continual Egocentric Activity Recognition: A Multi-modal Egocentric Activity Dataset for Continual LearningCode1
Transfer Learning for Pose Estimation of Illustrated CharactersCode1
Transformer Networks for Data Augmentation of Human Physical Activity RecognitionCode1
Improved Actor Relation Graph based Group Activity RecognitionCode1
Adaptive Activity Monitoring with Uncertainty Quantification in Switching Gaussian Process Models—0
Adaptation of Surgical Activity Recognition Models Across Operating Rooms—0
Show:102550
← PrevPage 5 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