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 451–475 of 1322 papers

TitleStatusHype
Sensing with OFDM Waveform at mmWave Band based on Micro-Doppler Analysis—0
Hard Regularization to Prevent Deep Online Clustering Collapse without Data AugmentationCode0
Time Series Segmentation Applied to a New Data Set for Mobile Sensing of Human ActivitiesCode1
Provable Robustness for Streaming Models with a Sliding Window—0
Multimodal video and IMU kinematic dataset on daily life activities using affordable devices (VIDIMU)Code1
Unified Keypoint-based Action Recognition Framework via Structured Keypoint Pooling—0
Learning and Verification of Task Structure in Instructional Videos—0
A Multi-Task Deep Learning Approach for Sensor-based Human Activity Recognition and Segmentation—0
Modeling the Trade-off of Privacy Preservation and Activity Recognition on Low-Resolution Images—0
Dual-path Adaptation from Image to Video TransformersCode1
Mobiprox: Supporting Dynamic Approximate Computing on Mobiles—0
Activity Recognition From Newborn Resuscitation Videos—0
DECOMPL: Decompositional Learning with Attention Pooling for Group Activity Recognition from a Single Volleyball ImageCode0
Zone-based Federated Learning for Mobile Sensing Data—0
Sleep Quality Prediction from Wearables using Convolution Neural Networks and Ensemble Learning—0
Robust Multimodal Fusion for Human Activity Recognition—0
SPARTAN: Self-supervised Spatiotemporal Transformers Approach to Group Activity RecognitionCode0
VALERIAN: Invariant Feature Learning for IMU Sensor-based Human Activity Recognition in the Wild—0
EdgeServe: A Streaming System for Decentralized Model Serving—0
Towards Activated Muscle Group Estimation in the WildCode1
Knowledge Augmented Relation Inference for Group Activity Recognition—0
Unsupervised Video Anomaly Detection for Stereotypical Behaviours in Autism—0
A Preliminary Study on Pattern Reconstruction for Optimal Storage of Wearable Sensor Data—0
FG-SSA: Features Gradient-based Signals Selection Algorithm of Linear Complexity for Convolutional Neural Networks—0
Weakly Supervised Temporal Convolutional Networks for Fine-grained Surgical Activity Recognition—0
Show:102550
← PrevPage 19 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