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 251–300 of 1322 papers

TitleStatusHype
Topological Machine Learning for Multivariate Time SeriesCode0
Chirality Nets for Human Pose RegressionCode0
HARMamba: Efficient and Lightweight Wearable Sensor Human Activity Recognition Based on Bidirectional MambaCode0
A Probabilistic Logic Programming Event CalculusCode0
Generative Pretrained Embedding and Hierarchical Irregular Time Series Representation for Daily Living Activity RecognitionCode0
Glimpse Clouds: Human Activity Recognition from Unstructured Feature PointsCode0
Fully Convolutional Network Bootstrapped by Word Encoding and Embedding for Activity Recognition in Smart HomesCode0
Action Recognition for Privacy-Preserving Ambient Assisted LivingCode0
Fine-grained Activity Recognition in Baseball VideosCode0
Generalized Relevance Learning Grassmann QuantizationCode0
Group Activity Recognition Using Joint Learning of Individual Action Recognition and People GroupingCode0
Approaches to human activity recognition via passive radarCode0
Evaluating Spiking Neural Network On Neuromorphic Platform For Human Activity RecognitionCode0
Exploring Video-Based Driver Activity Recognition under Noisy LabelsCode0
Enhancing Wearable Tap Water Audio Detection through Subclass Annotation in the HD-Epic DatasetCode0
ConSense: Continually Sensing Human Activity with WiFi via Growing and PickingCode0
Attention-Refined Unrolling for Sparse Sequential micro-Doppler ReconstructionCode0
Enhanced Spatio- Temporal Image Encoding for Online Human Activity RecognitionCode0
Easy Ensemble: Simple Deep Ensemble Learning for Sensor-Based Human Activity RecognitionCode0
Dynamic Vision Sensors for Human Activity RecognitionCode0
DYSAN: Dynamically sanitizing motion sensor data against sensitive inferences through adversarial networksCode0
Domain Adaptation Under Behavioral and Temporal Shifts for Natural Time Series Mobile Activity RecognitionCode0
Does SpatioTemporal information benefit Two video summarization benchmarks?Code0
Domain Adaptation with Representation Learning and Nonlinear Relation for Time SeriesCode0
Combining Public Human Activity Recognition Datasets to Mitigate Labeled Data ScarcityCode0
Accoustate: Auto-annotation of IMU-generated Activity Signatures under Smart InfrastructureCode0
Eidetic 3D LSTM: A Model for Video Prediction and BeyondCode0
Feature engineering workflow for activity recognition from synchronized inertial measurement unitsCode0
Directional Antenna Systems for Long-Range Through-Wall Human Activity RecognitionCode0
Differentially Private Integrated Decision Gradients (IDG-DP) for Radar-based Human Activity RecognitionCode0
Discriminating Spatial and Temporal Relevance in Deep Taylor Decompositions for Explainable Activity RecognitionCode0
Ensemble diverse hypotheses and knowledge distillation for unsupervised cross-subject adaptationCode0
Defending Black-box Skeleton-based Human Activity ClassifiersCode0
Explaining Human Activity Recognition with SHAP: Validating Insights with Perturbation and Quantitative MeasuresCode0
Context-Aware Predictive Coding: A Representation Learning Framework for WiFi SensingCode0
Context-Aware Predictive Coding: A Representation Learning Framework for WiFi SensingCode0
Discriminatively Learned Hierarchical Rank Pooling NetworksCode0
Deep Learning for Sensor-based Activity Recognition: A SurveyCode0
AdaRNN: Adaptive Learning and Forecasting of Time SeriesCode0
FAR: Fourier Aerial Video RecognitionCode0
Accurate Passive Radar via an Uncertainty-Aware Fusion of Wi-Fi Sensing DataCode0
Deep Residual Bidir-LSTM for Human Activity Recognition Using Wearable SensorsCode0
Distributed Online Learning of Event DefinitionsCode0
GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian ManifoldsCode0
DECOMPL: Decompositional Learning with Attention Pooling for Group Activity Recognition from a Single Volleyball ImageCode0
A Novel Skeleton-Based Human Activity Discovery Using Particle Swarm Optimization with Gaussian MutationCode0
Decomposing and Fusing Intra- and Inter-Sensor Spatio-Temporal Signal for Multi-Sensor Wearable Human Activity RecognitionCode0
Guidelines for Augmentation Selection in Contrastive Learning for Time Series ClassificationCode0
Spatio-Temporal Action Graph NetworksCode0
ActiveHARNet: Towards On-Device Deep Bayesian Active Learning for Human Activity RecognitionCode0
Show:102550
← PrevPage 6 of 27Next →
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