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
TRIS-HAR: Transmissive Reconfigurable Intelligent Surfaces-assisted Cognitive Wireless Human Activity Recognition Using State Space Models—0
TRTAR: Transmissive RIS-assisted Through-the-wall Human Activity Recognition—0
TSAK: Two-Stage Semantic-Aware Knowledge Distillation for Efficient Wearable Modality and Model Optimization in Manufacturing Lines—0
T-WaveNet: A Tree-Structured Wavelet Neural Network for Time Series Signal Analysis—0
T-WaveNet: Tree-Structured Wavelet Neural Network for Sensor-Based Time Series Analysis—0
Tweets Can Tell: Activity Recognition using Hybrid Long Short-Term Memory Model—0
Two-Person Interaction Augmentation with Skeleton Priors—0
Two-person interaction detection using body-pose features and multiple instance learning—0
Two-stage Human Activity Recognition on Microcontrollers with Decision Trees and CNNs—0
UMSNet: An Universal Multi-sensor Network for Human Activity Recognition—0
Uncertainty-Aware Audiovisual Activity Recognition Using Deep Bayesian Variational Inference—0
Uncertainty aware audiovisual activity recognition using deep Bayesian variational inference—0
Uncertainty Quantification for Deep Context-Aware Mobile Activity Recognition and Unknown Context Discovery—0
Uncertainty-sensitive Activity Recognition: a Reliability Benchmark and the CARING Models—0
Understanding and Improving Recurrent Networks for Human Activity Recognition by Continuous Attention—0
Understanding Human Activity with Uncertainty Measure for Novelty in Graph Convolutional Networks—0
Unified Keypoint-based Action Recognition Framework via Structured Keypoint Pooling—0
UniMiB SHAR: a new dataset for human activity recognition using acceleration data from smartphones—0
Unimodal and Multimodal Sensor Fusion for Wearable Activity Recognition—0
Unsupervised Deep Anomaly Detection for Multi-Sensor Time-Series Signals—0
Unsupervised Doppler Radar-Based Activity Recognition for e-Healthcare—0
Unsupervised Embedding Learning for Human Activity Recognition Using Wearable Sensor Data—0
Unsupervised explainable activity prediction in competitive Nordic Walking from experimental data—0
Unsupervised Human Action Detection by Action Matching—0
Unsupervised Learning of 3D Scene Flow with 3D Odometry Assistance—0
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