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 701–725 of 1322 papers

TitleStatusHype
A communication efficient distributed learning framework for smart environments—0
Incremental Learning Techniques for Online Human Activity Recognition—0
Multiscale Manifold Warping—0
RAPID: Retrofitting IEEE 802.11ay Access Points for Indoor Human Detection and Sensing—0
A distillation-based approach integrating continual learning and federated learning for pervasive services—0
Sensor Data Augmentation by Resampling for Contrastive Learning in Human Activity Recognition—0
Transformer Networks for Data Augmentation of Human Physical Activity RecognitionCode1
GroupFormer: Group Activity Recognition with Clustered Spatial-Temporal TransformerCode1
Spatio-Temporal Dynamic Inference Network for Group Activity RecognitionCode1
Few Shot Activity Recognition Using Variational Inference—0
Classification of Abnormal Hand Movement for Aiding in Autism Detection: Machine Learning StudyCode1
SALIENCE: An Unsupervised User Adaptation Model for Multiple Wearable Sensors Based Human Activity RecognitionCode0
Temporal Action Segmentation with High-level Complex Activity Labels—0
AdaRNN: Adaptive Learning and Forecasting of Time SeriesCode0
Pose is all you need: The pose only group activity recognition system (POGARS)—0
Transfer Learning for Pose Estimation of Illustrated CharactersCode1
Non-local Graph Convolutional Network for joint Activity Recognition and Motion Prediction—0
Improving Deep Learning for HAR with shallow LSTMsCode1
Unsupervised Deep Anomaly Detection for Multi-Sensor Time-Series Signals—0
Real-Time Activity Recognition and Intention Recognition Using a Vision-based Embedded System—0
Neural Style Transfer Enhanced Training Support For Human Activity Recognition—0
A Neurorobotics Approach to Behaviour Selection based on Human Activity Recognition—0
Inference for Change Points in High Dimensional Mean Shift Models—0
Group Activity Recognition Using Joint Learning of Individual Action Recognition and People GroupingCode0
Let's Play for Action: Recognizing Activities of Daily Living by Learning from Life Simulation Video GamesCode1
Show:102550
← PrevPage 29 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