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 1176–1200 of 1322 papers

TitleStatusHype
Sequential Lifted Bayesian Filtering in Multiset Rewriting Systems—0
Deep Learning for Sensor-based Activity Recognition: A SurveyCode0
An Interactive Greedy Approach to Group Sparsity in High DimensionsCode0
Application of Transfer Learning Approaches in Multimodal Wearable Human Activity Recognition—0
Structure Optimization for Deep Multimodal Fusion Networks using Graph-Induced Kernels—0
Recurrent Modeling of Interaction Context for Collective Activity Recognition—0
Re-Sign: Re-Aligned End-To-End Sequence Modelling With Deep Recurrent CNN-HMMs—0
Riemannian Nonlinear Mixed Effects Models: Analyzing Longitudinal Deformations in Neuroimaging—0
Dynamic Facial Analysis: From Bayesian Filtering to Recurrent Neural Network—0
Hierarchical Attentive Recurrent TrackingCode0
Cross-Country Skiing Gears Classification using Deep Learning—0
MobiRNN: Efficient Recurrent Neural Network Execution on Mobile GPUCode0
Non-Uniform Subset Selection for Active Learning in Structured DataCode0
Discriminatively Learned Hierarchical Rank Pooling NetworksCode0
Distributed Online Learning of Event DefinitionsCode0
Identifying First-person Camera Wearers in Third-person Videos—0
A Deep Learning Framework using Passive WiFi Sensing for Respiration Monitoring—0
Interpretable 3D Human Action Analysis with Temporal Convolutional NetworksCode0
Recognizing Activities of Daily Living from Egocentric Images—0
CERN: Confidence-Energy Recurrent Network for Group Activity Recognition—0
Generalized Rank Pooling for Activity Recognition—0
TS-LSTM and Temporal-Inception: Exploiting Spatiotemporal Dynamics for Activity RecognitionCode0
Pose-conditioned Spatio-Temporal Attention for Human Action Recognition—0
Ensembles of Deep LSTM Learners for Activity Recognition using Wearables—0
Progress Estimation and Phase Detection for Sequential Processes—0
Show:102550
← PrevPage 48 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