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 826–850 of 1322 papers

TitleStatusHype
A Novel Multi-Stage Training Approach for Human Activity Recognition from Multimodal Wearable Sensor Data Using Deep Neural Network—0
Uncertainty-sensitive Activity Recognition: a Reliability Benchmark and the CARING Models—0
Context Aware Group Activity Recognition—0
SkipW: Resource adaptable RNN with strict upper computational limit—0
Anonymizing Egocentric Videos—0
Anomaly detection and regime searching in fitness-tracker data—0
Sequence Metric Learning as Synchronization of Recurrent Neural Networks—0
Dynamic Feature Selection for Efficient and Interpretable Human Activity Recognition—0
Deep Positive Unlabeled Learning with a Sequential Bias—0
3D Human motion anticipation and classification—0
Invariant Feature Learning for Sensor-based Human Activity Recognition—0
FedHome: Cloud-Edge based Personalized Federated Learning for In-Home Health Monitoring—0
T-WaveNet: Tree-Structured Wavelet Neural Network for Sensor-Based Time Series Analysis—0
Contrastive Predictive Coding for Human Activity Recognition—0
Transfer Learning for Human Activity Recognition using Representational Analysis of Neural Networks—0
Federated Learning with Heterogeneous Labels and Models for Mobile Activity Monitoring—0
MEVA: A Large-Scale Multiview, Multimodal Video Dataset for Activity Detection—0
Fine-grained activity recognition for assembly videos—0
Fully Convolutional Network Bootstrapped by Word Encoding and Embedding for Activity Recognition in Smart HomesCode0
A compact sequence encoding scheme for online human activity recognition in HRI applications—0
Post-training Iterative Hierarchical Data Augmentation for Deep Networks—0
LaHAR: Latent Human Activity Recognition using LDACode0
Yet it moves: Learning from Generic Motions to Generate IMU data from YouTube videos—0
Self-Supervised Transformers for Activity Classification using Ambient Sensors—0
Human activity recognition using improved dynamic image—0
Show:102550
← PrevPage 34 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