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 1051–1075 of 1322 papers

TitleStatusHype
A Hybrid Framework for Action Recognition in Low-Quality Video Sequences—0
Pragmatic classification of movement primitives for stroke rehabilitation—0
Human Pose Estimation using Motion Priors and Ensemble Models—0
Online Learning of Weighted Relational Rules for Complex Event RecognitionCode0
Adaptive Feature Processing for Robust Human Activity Recognition on a Novel Multi-Modal Dataset—0
Adaptive Activity Monitoring with Uncertainty Quantification in Switching Gaussian Process Models—0
CamLoc: Pedestrian Location Detection from Pose Estimation on Resource-constrained Smart-cameras—0
A Multi-Stream Convolutional Neural Network Framework for Group Activity Recognition—0
Multi-Level Sequence GAN for Group Activity Recognition—0
Towards Robust Human Activity Recognition from RGB Video Stream with Limited Labeled Data—0
Dynamic Graph Modules for Modeling Object-Object Interactions in Activity Recognition—0
Tri-axial Self-Attention for Concurrent Activity Recognition—0
Spatio-Temporal Action Graph NetworksCode0
An Interpretable Machine Vision Approach to Human Activity Recognition using Photoplethysmograph Sensor Data—0
Uncertainty aware audiovisual activity recognition using deep Bayesian variational inference—0
LSTA: Long Short-Term Attention for Egocentric Action RecognitionCode0
Privacy-Preserving Action Recognition for Smart Hospitals using Low-Resolution Depth Images—0
Online Collective Animal Movement Activity Recognition—0
DNN Transfer Learning from Diversified Micro-Doppler for Motion Classification—0
Deep Auto-Set: A Deep Auto-Encoder-Set Network for Activity Recognition Using Wearables—0
Distributionally Robust Semi-Supervised Learning for People-Centric Sensing—0
BAR: Bayesian Activity Recognition using variational inference—0
PerceptionNet: A Deep Convolutional Neural Network for Late Sensor Fusion—0
Skeleton-based Activity Recognition with Local Order Preserving Match of Linear Patches—0
Informed Democracy: Voting-based Novelty Detection for Action Recognition—0
Show:102550
← PrevPage 43 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