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 876–900 of 1322 papers

TitleStatusHype
Investigating Deep Neural Network Architecture and Feature Extraction Designs for Sensor-based Human Activity Recognition—0
Investigating the significance of adversarial attacks and their relation to interpretability for radar-based human activity recognition systems—0
Is end-to-end learning enough for fitness activity recognition?—0
Is my Driver Observation Model Overconfident? Input-guided Calibration Networks for Reliable and Interpretable Confidence Estimates—0
Joint Learning of Social Groups, Individuals Action and Sub-group Activities in Videos—0
Jointly learning heterogeneous features for rgb-d activity recognition—0
Joint segmentation of multivariate time series with hidden process regression for human activity recognition—0
Kernel Learning for Extrinsic Classification of Manifold Features—0
Knowledge Augmented Relation Inference for Group Activity Recognition—0
Knowledge Distillation for Reservoir-based Classifier: Human Activity Recognition—0
Knowledge Graph Driven Approach to Represent Video Streams for Spatiotemporal Event Pattern Matching in Complex Event Processing—0
Knowledge Transfer across Multiple Principal Component Analysis Studies—0
Know Thy Neighbors: A Graph Based Approach for Effective Sensor-Based Human Activity Recognition in Smart Homes—0
Koopman pose predictions for temporally consistent human walking estimations—0
Label Flipping Data Poisoning Attack Against Wearable Human Activity Recognition System—0
Language-centered Human Activity Recognition—0
Laplacian LRR on Product Grassmann Manifolds for Human Activity Clustering in Multi-Camera Video Surveillance—0
Large Language Models are Few-Shot Health Learners—0
Large Language Models Memorize Sensor Datasets! Implications on Human Activity Recognition Research—0
Large Model for Small Data: Foundation Model for Cross-Modal RF Human Activity Recognition—0
Latent Embeddings for Collective Activity Recognition—0
Latent Hierarchical Model for Activity Recognition—0
Latent hypernet: Exploring all Layers from Convolutional Neural Networks—0
Latent Variable Algorithms for Multimodal Learning and Sensor Fusion—0
Layout Agnostic Human Activity Recognition in Smart Homes through Textual Descriptions Of Sensor Triggers (TDOST)—0
Show:102550
← PrevPage 36 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