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

Showing 201225 of 1322 papers

TitleStatusHype
Feature engineering workflow for activity recognition from synchronized inertial measurement unitsCode0
Fine-grained Activity Recognition in Baseball VideosCode0
Explaining Human Activity Recognition with SHAP: Validating Insights with Perturbation and Quantitative MeasuresCode0
Evaluating Spiking Neural Network On Neuromorphic Platform For Human Activity RecognitionCode0
Interpretable 3D Human Action Analysis with Temporal Convolutional NetworksCode0
Ensemble diverse hypotheses and knowledge distillation for unsupervised cross-subject adaptationCode0
Exploring Video-Based Driver Activity Recognition under Noisy LabelsCode0
Eidetic 3D LSTM: A Model for Video Prediction and BeyondCode0
A Survey of Human Activity Recognition Using WiFi CSICode0
Attention-Refined Unrolling for Sparse Sequential micro-Doppler ReconstructionCode0
Activity and Subject Detection for UCI HAR Dataset with & without missing Sensor DataCode0
Enhanced Spatio- Temporal Image Encoding for Online Human Activity RecognitionCode0
Batch-based Activity Recognition from Egocentric Photo-Streams RevisitedCode0
Learning Actor Relation Graphs for Group Activity RecognitionCode0
Dynamic Vision Sensors for Human Activity RecognitionCode0
DYSAN: Dynamically sanitizing motion sensor data against sensitive inferences through adversarial networksCode0
Through-the-Wall Radar Human Activity Recognition WITHOUT Using Neural NetworksCode0
Leveraging LDA Feature Extraction to Augment Human Activity Recognition AccuracyCode0
Activity2Vec: Learning ADL Embeddings from Sensor Data with a Sequence-to-Sequence ModelCode0
MEx: Multi-modal Exercises Dataset for Human Activity RecognitionCode0
Easy Ensemble: Simple Deep Ensemble Learning for Sensor-Based Human Activity RecognitionCode0
Analysis of Hand Segmentation in the WildCode0
Enhancing Wearable Tap Water Audio Detection through Subclass Annotation in the HD-Epic DatasetCode0
A benchmark of data stream classification for human activity recognition on connected objectsCode0
FAR: Fourier Aerial Video RecognitionCode0
Show:102550
← PrevPage 9 of 53Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Structured Keypoint PoolingAccuracy93.4Unverified
2Semi-Supervised Hard Attention (SSHA); pretrained on Deepmind Kinetics datasetAccuracy90.4Unverified
3Human Skeletons + Change DetectionAccuracy90.25Unverified
4Separable Convolutional LSTMAccuracy89.75Unverified
5SPIL ConvolutionAccuracy89.3Unverified
6Flow Gated NetworkAccuracy87.25Unverified
#ModelMetricClaimedVerifiedStatus
1FocusCLIPTop-3 Accuracy (%)10.47Unverified
2CLIPTop-3 Accuracy (%)6.49Unverified
#ModelMetricClaimedVerifiedStatus
1Boutaleb et al.1:1 Accuracy97.91Unverified
#ModelMetricClaimedVerifiedStatus
1all-landmark-modelActivity Recognition0.76Unverified