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 801–825 of 1322 papers

TitleStatusHype
Self-Adaptation of Activity Recognition Systems to New Sensors—0
Self-Supervised Human Activity Recognition with Localized Time-Frequency Contrastive Representation Learning—0
Self-Supervised Human Activity Recognition by Augmenting Generative Adversarial Networks—0
Self-Supervised Learning for WiFi CSI-Based Human Activity Recognition: A Systematic Study—0
Self-supervised Learning via Cluster Distance Prediction for Operating Room Context Awareness—0
Self-supervised Multi-actor Social Activity Understanding in Streaming Videos—0
Self-Supervised Multimodal Fusion Transformer for Passive Activity Recognition—0
Self-supervised Optimization of Hand Pose Estimation using Anatomical Features and Iterative Learning—0
Self-Supervised Transformers for Activity Classification using Ambient Sensors—0
Self-supervised Human Activity Recognition by Learning to Predict Cross-Dimensional Motion—0
Self-Supervised WiFi-Based Activity Recognition—0
Semantic-Discriminative Mixup for Generalizable Sensor-based Cross-domain Activity Recognition—0
Semi-Supervised Convolutional Neural Networks for Human Activity Recognition—0
Semi-supervised Federated Learning for Activity Recognition—0
Semi-Supervised First-Person Activity Recognition in Body-Worn Video—0
Semi-supervised sequence classification through change point detection—0
Sensing with OFDM Waveform at mmWave Band based on Micro-Doppler Analysis—0
Sensor-Aware Classifiers for Energy-Efficient Time Series Applications on IoT Devices—0
Sensor-Based Data Acquisition via Ubiquitous Device to Detect Muscle Strength Training Activities—0
Sensor Data Augmentation by Resampling for Contrastive Learning in Human Activity Recognition—0
Sensor Data for Human Activity Recognition: Feature Representation and Benchmarking—0
Sentence Directed Video Object Codetection—0
Sequence Metric Learning as Synchronization of Recurrent Neural Networks—0
Sequential Lifted Bayesian Filtering in Multiset Rewriting Systems—0
SETransformer: A Hybrid Attention-Based Architecture for Robust Human Activity Recognition—0
Show:102550
← PrevPage 33 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