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 776–800 of 1322 papers

TitleStatusHype
Multi-Task Temporal Convolutional Networks for Joint Recognition of Surgical Phases and Steps in Gastric Bypass Procedures—0
Efficient Two-Stream Network for Violence Detection Using Separable Convolutional LSTMCode1
Transfer Learning for Future Wireless Networks: A Comprehensive Survey—0
SelfHAR: Improving Human Activity Recognition through Self-training with Unlabeled DataCode1
Efficient Multi-stream Temporal Learning and Post-fusion Strategy for 3D Skeleton-based Hand Activity Recognition—0
Improving state estimation through projection post-processing for activity recognition with application to footballCode0
Provably Secure Federated Learning against Malicious Clients—0
AHAR: Adaptive CNN for Energy-efficient Human Activity Recognition in Low-power Edge Devices—0
Cross-domain Activity Recognition via Substructural Optimal Transport—0
Gesture Recognition in Robotic Surgery: a Review—0
Embedding Symbolic Temporal Knowledge into Deep Sequential Models—0
Investigating the significance of adversarial attacks and their relation to interpretability for radar-based human activity recognition systems—0
Indoor Group Activity Recognition using Multi-Layered HMMs—0
B-HAR: an open-source baseline framework for in depth study of human activity recognition datasets and workflowsCode0
Human Interaction Recognition Framework based on Interacting Body Part Attention—0
Machine-Generated Hierarchical Structure of Human Activities to Reveal How Machines Think—0
Coarse Temporal Attention Network (CTA-Net) for Driver's Activity Recognition—0
Human Activity Recognition Using Multichannel Convolutional Neural Network—0
A*HAR: A New Benchmark towards Semi-supervised learning for Class-imbalanced Human Activity RecognitionCode0
Activity Recognition with Moving Cameras and Few Training Examples: Applications for Detection of Autism-Related Headbanging—0
Octave Mix: Data augmentation using frequency decomposition for activity recognition—0
Human Activity Recognition using Wearable Sensors: Review, Challenges, Evaluation BenchmarkCode1
Transformers in Vision: A Survey—0
Anomaly Recognition from surveillance videos using 3D Convolutional Neural Networks—0
A Novel Multi-Stage Training Approach for Human Activity Recognition from Multimodal Wearable Sensor Data Using Deep Neural Network—0
Show:102550
← PrevPage 32 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