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 576–600 of 1322 papers

TitleStatusHype
Using Anomaly Detection to Detect Poisoning Attacks in Federated Learning Applications—0
Federated Self-Supervised Learning in Heterogeneous Settings: Limits of a Baseline Approach on HAR—0
Federated Learning and catastrophic forgetting in pervasive computing: demonstration in HAR domain—0
Federated Continual Learning through distillation in pervasive computing—0
CHARM: A Hierarchical Deep Learning Model for Classification of Complex Human Activities Using Motion Sensors—0
SenseFi: A Library and Benchmark on Deep-Learning-Empowered WiFi Human SensingCode2
Multi-Modal Unsupervised Pre-Training for Surgical Operating Room Workflow Analysis—0
Hunting Group Clues with Transformers for Social Group Activity Recognition—0
Fine-grained Activities of People Worldwide—0
Domain Adaptation Under Behavioral and Temporal Shifts for Natural Time Series Mobile Activity RecognitionCode0
Adaptation of Surgical Activity Recognition Models Across Operating Rooms—0
WiFi-based Spatiotemporal Human Action Perception—0
Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency ConsistencyCode2
Semantic-Discriminative Mixup for Generalizable Sensor-based Cross-domain Activity Recognition—0
ProActive: Self-Attentive Temporal Point Process Flows for Activity SequencesCode0
Beyond the Gates of Euclidean Space: Temporal-Discrimination-Fusions and Attention-based Graph Neural Network for Human Activity Recognition—0
PrivHAR: Recognizing Human Actions From Privacy-preserving Lens—0
Two-stage Human Activity Recognition on Microcontrollers with Decision Trees and CNNs—0
Self-supervised Learning for Human Activity Recognition Using 700,000 Person-days of Wearable DataCode1
Human Activity Recognition on Time Series Accelerometer Sensor Data using LSTM Recurrent Neural Networks—0
Benchmark of DNN Model Search at Deployment Time—0
Ultra-compact Binary Neural Networks for Human Activity Recognition on RISC-V ProcessorsCode0
A Wireless-Vision Dataset for Privacy Preserving Human Activity Recognition—0
UMSNet: An Universal Multi-sensor Network for Human Activity Recognition—0
Contrastive Learning with Cross-Modal Knowledge Mining for Multimodal Human Activity RecognitionCode1
Show:102550
← PrevPage 24 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