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 601–625 of 1322 papers

TitleStatusHype
Discriminating sensor activation in activity recognition within multi-occupancy environments based on nearby interaction—0
Fine-grained Human Activity Recognition Using Virtual On-body Acceleration Data—0
Evaluation and comparison of federated learning algorithms for Human Activity Recognition on smartphones—0
The Contribution of Human Body Capacitance/Body-Area Electric Field To Individual and Collaborative Activity RecognitionCode0
Performance of different machine learning methods on activity recognition and pose estimation datasets—0
A Symbolic Representation of Human Posture for Interpretable Learning and Reasoning—0
MMTSA: Multimodal Temporal Segment Attention Network for Efficient Human Activity RecognitionCode0
Learning from the Best: Contrastive Representations Learning Across Sensor Locations for Wearable Activity Recognition—0
Smart-Badge: A wearable badge with multi-modal sensors for kitchen activity recognition—0
Robust Trajectory-based Density Estimation for Geometric Structure Recovery: Theory and Applications—0
RALACs: Action Recognition in Autonomous Vehicles using Interaction Encoding and Optical FlowCode0
Low-Resolution Action Recognition for Tiny Actions Challenge—0
DynImp: Dynamic Imputation for Wearable Sensing Data Through Sensory and Temporal Relatedness—0
Heterogeneous Recurrent Spiking Neural Network for Spatio-Temporal Classification—0
Contrastive Learning for Time Series on Dynamic Graphs—0
An Overview of Violence Detection Techniques: Current Challenges and Future Directions—0
Differentiable Frequency-based Disentanglement for Aerial Video Action Recognition—0
Out-of-Distribution Representation Learning for Time Series Classification—0
TASKED: Transformer-based Adversarial learning for human activity recognition using wearable sensors via Self-KnowledgE Distillation—0
BON: An extended public domain dataset for human activity recognition—0
Unsupervised Learning of 3D Scene Flow with 3D Odometry Assistance—0
Alignment-based conformance checking over probabilistic eventsCode0
Human Activity Recognition on Microcontrollers with Quantized and Adaptive Deep Neural Networks—0
To Store or Not? Online Data Selection for Federated Learning with Limited Storage—0
Attentive pooling for Group Activity Recognition—0
Show:102550
← PrevPage 25 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