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 126–150 of 1322 papers

TitleStatusHype
An IoT Based Framework For Activity Recognition Using Deep Learning TechniqueCode0
Hierarchical Attentive Recurrent TrackingCode0
Hierarchical Deep Temporal Models for Group Activity RecognitionCode0
Human Activity Recognition: A Spatio-temporal Image Encoding of 3D Skeleton Data for Online Action DetectionCode0
An Interactive Greedy Approach to Group Sparsity in High DimensionsCode0
HARMamba: Efficient and Lightweight Wearable Sensor Human Activity Recognition Based on Bidirectional MambaCode0
Hard Regularization to Prevent Deep Online Clustering Collapse without Data AugmentationCode0
FedBChain: A Blockchain-enabled Federated Learning Framework for Improving DeepConvLSTM with Comparative Strategy InsightsCode0
Human Activity Recognition Based on Wearable Sensor Data: A Standardization of the State-of-the-ArtCode0
ActNetFormer: Transformer-ResNet Hybrid Method for Semi-Supervised Action Recognition in VideosCode0
Guidelines for Augmentation Selection in Contrastive Learning for Time Series ClassificationCode0
Group Activity Recognition Using Joint Learning of Individual Action Recognition and People GroupingCode0
A Correlation Based Feature Representation for First-Person Activity RecognitionCode0
SPARTAN: Self-supervised Spatiotemporal Transformers Approach to Group Activity RecognitionCode0
Hang-Time HAR: A Benchmark Dataset for Basketball Activity Recognition using Wrist-Worn Inertial SensorsCode0
GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian ManifoldsCode0
Generative Pretrained Embedding and Hierarchical Irregular Time Series Representation for Daily Living Activity RecognitionCode0
An Analysis of Parallelized Motion Masking Using Dual-Mode Single Gaussian ModelsCode0
A benchmark of data stream classification for human activity recognition on connected objectsCode0
Glimpse Clouds: Human Activity Recognition from Unstructured Feature PointsCode0
Human activity recognition from skeleton posesCode0
Analysis of Hand Segmentation in the WildCode0
Fine-grained Activity Recognition in Baseball VideosCode0
FedAli: Personalized Federated Learning with Aligned Prototypes through Optimal TransportCode0
Feature engineering workflow for activity recognition from synchronized inertial measurement unitsCode0
Show:102550
← PrevPage 6 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