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 376–400 of 1322 papers

TitleStatusHype
Dynamic Facial Analysis: From Bayesian Filtering to Recurrent Neural Network—0
Differentiable Frequency-based Disentanglement for Aerial Video Action Recognition—0
Differentially Private 2D Human Pose Estimation—0
Augmenting Bag-of-Words: Data-Driven Discovery of Temporal and Structural Information for Activity Recognition—0
Differentially Private Video Activity Recognition—0
Digging Deeper into Egocentric Gaze Prediction—0
Augmenting Deep Learning Adaptation for Wearable Sensor Data through Combined Temporal-Frequency Image Encoding—0
Convolutional Relational Machine for Group Activity Recognition—0
DISC: a Dataset for Integrated Sensing and Communication in mmWave Systems—0
A Real-time Human Pose Estimation Approach for Optimal Sensor Placement in Sensor-based Human Activity Recognition—0
Discriminating sensor activation in activity recognition within multi-occupancy environments based on nearby interaction—0
A Masked Semi-Supervised Learning Approach for Otago Micro Labels Recognition—0
Discriminative Hierarchical Rank Pooling for Activity Recognition—0
Automated Activity Recognition in Clinical Documents—0
Discriminative training for Convolved Multiple-Output Gaussian processes—0
Disentangling Imperfect: A Wavelet-Infused Multilevel Heterogeneous Network for Human Activity Recognition in Flawed Wearable Sensor Data—0
Disparity-Augmented Trajectories for Human Activity Recognition—0
Distilled Mid-Fusion Transformer Networks for Multi-Modal Human Activity Recognition—0
Distributed Agent-Based Collaborative Learning in Cross-Individual Wearable Sensor-Based Human Activity Recognition—0
Automated Level Crossing System: A Computer Vision Based Approach with Raspberry Pi Microcontroller—0
Distributionally Robust Semi-Supervised Learning for People-Centric Sensing—0
Distribution estimation and change-point estimation for time series via DNN-based GANs—0
Automated Surgical Activity Recognition with One Labeled Sequence—0
Diverse Intra- and Inter-Domain Activity Style Fusion for Cross-Person Generalization in Activity Recognition—0
ConViViT -- A Deep Neural Network Combining Convolutions and Factorized Self-Attention for Human Activity Recognition—0
Show:102550
← PrevPage 16 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