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 176–200 of 1322 papers

TitleStatusHype
MU-MAE: Multimodal Masked Autoencoders-Based One-Shot Learning—0
Adversarial Domain Adaptation for Cross-user Activity Recognition Using Diffusion-based Noise-centred LearningCode0
Enhancing Human Action Recognition and Violence Detection Through Deep Learning Audiovisual Fusion—0
A Tiny Supervised ODL Core with Auto Data Pruning for Human Activity Recognition—0
MPT-PAR:Mix-Parameters Transformer for Panoramic Activity Recognition—0
Skeleton-Based Action Recognition with Spatial-Structural Graph ConvolutionCode0
Explainable Artificial Intelligence for Quantifying Interfering and High-Risk Behaviors in Autism Spectrum Disorder in a Real-World Classroom Environment Using Privacy-Preserving Video Analysis—0
FedBChain: A Blockchain-enabled Federated Learning Framework for Improving DeepConvLSTM with Comparative Strategy InsightsCode0
ActivityCLIP: Enhancing Group Activity Recognition by Mining Complementary Information from Text to Supplement Image Modality—0
Skeleton-based Group Activity Recognition via Spatial-Temporal Panoramic GraphCode1
Babel: A Scalable Pre-trained Model for Multi-Modal Sensing via Expandable Modality Alignment—0
C3T: Cross-modal Transfer Through Time for Sensor-based Human Activity Recognition—0
Wallcamera: Reinventing the Wheel?—0
Probing Fine-Grained Action Understanding and Cross-View Generalization of Foundation Models—0
Decoupled Prompt-Adapter Tuning for Continual Activity Recognition—0
CDFL: Efficient Federated Human Activity Recognition using Contrastive Learning and Deep Clustering—0
Evaluation of Encoding Schemes on Ubiquitous Sensor Signal for Spiking Neural Network—0
Guidelines for Augmentation Selection in Contrastive Learning for Time Series ClassificationCode0
Boosting Adversarial Transferability for Skeleton-based Action Recognition via Exploring the Model Posterior Space—0
Sensor-Aware Classifiers for Energy-Efficient Time Series Applications on IoT Devices—0
CrowdTransfer: Enabling Crowd Knowledge Transfer in AIoT Community—0
GeoWATCH for Detecting Heavy Construction in Heterogeneous Time Series of Satellite Images—0
Topological Persistence Guided Knowledge Distillation for Wearable Sensor Data—0
Self-supervised Learning via Cluster Distance Prediction for Operating Room Context Awareness—0
Natively neuromorphic LMU architecture for encoding-free SNN-based HAR on commercial edge devices—0
Show:102550
← PrevPage 8 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