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 351–375 of 1322 papers

TitleStatusHype
Creating a Large-scale Synthetic Dataset for Human Activity Recognition—0
CoSS: Co-optimizing Sensor and Sampling Rate for Data-Efficient AI in Human Activity Recognition—0
Deep Positive Unlabeled Learning with a Sequential Bias—0
Deep Recurrent Neural Network for Mobile Human Activity Recognition with High Throughput—0
A Transformer-Based Model for the Prediction of Human Gaze Behavior on Videos—0
Action Segmentation Using 2D Skeleton Heatmaps and Multi-Modality Fusion—0
Deep Structured Models For Group Activity Recognition—0
Deep Transfer Learning for Cross-domain Activity Recognition—0
Deep Transfer Learning with Graph Neural Network for Sensor-Based Human Activity Recognition—0
Disparity-Augmented Trajectories for Human Activity Recognition—0
Post-train Black-box Defense via Bayesian Boundary Correction—0
Attention-based Convolutional Neural Network for Weakly Labeled Human Activities Recognition with Wearable Sensors—0
Distribution estimation and change-point estimation for time series via DNN-based GANs—0
Description of Structural Biases and Associated Data in Sensor-Rich Environments—0
Design and Analysis of Efficient Attention in Transformers for Social Group Activity Recognition—0
DeSPITE: Exploring Contrastive Deep Skeleton-Pointcloud-IMU-Text Embeddings for Advanced Point Cloud Human Activity Understanding—0
Detecting Falls with X-Factor Hidden Markov Models—0
Detecting Intentions of Vulnerable Road Users Based on Collective Intelligence—0
Detecting Unseen Falls from Wearable Devices using Channel-wise Ensemble of Autoencoders—0
Using Anomaly Detection to Detect Poisoning Attacks in Federated Learning Applications—0
Detector-Free Weakly Supervised Group Activity Recognition—0
Device-Free Human State Estimation using UWB Multi-Static Radios—0
DFTerNet: Towards 2-bit Dynamic Fusion Networks for Accurate Human Activity Recognition—0
DGAR: A Unified Domain Generalization Framework for RF-Enabled Human Activity Recognition—0
Convolutional Relational Machine for Group Activity Recognition—0
Show:102550
← PrevPage 15 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