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 851–875 of 1322 papers

TitleStatusHype
Importance of user inputs while using incremental learning to personalize human activity recognition models—0
Improve Unsupervised Domain Adaptation with Mixup Training—0
Improving Human Activity Recognition Through Ranking and Re-ranking—0
Improving the Multi-label Atomic Activity Recognition by Robust Visual Feature and Advanced Attention @ ROAD++ Atomic Activity Recognition 2024—0
IMUTube: Automatic Extraction of Virtual on-body Accelerometry from Video for Human Activity Recognition—0
Incremental Activity Modeling and Recognition in Streaming Videos—0
Incremental Learning Techniques for Online Human Activity Recognition—0
Incremental Real-Time Personalization in Human Activity Recognition Using Domain Adaptive Batch Normalization—0
Indoor Activity Detection and Recognition for Sport Games Analysis—0
Indoor Group Activity Recognition using Multi-Layered HMMs—0
A Framework of Combining Short-Term Spatial/Frequency Feature Extraction and Long-Term IndRNN for Activity Recognition—0
Inference for Change Points in High Dimensional Mean Shift Models—0
Information We Can Extract About a User From 'One Minute Mobile Application Usage'—0
Informed Democracy: Voting-based Novelty Detection for Action Recognition—0
Initial Findings on Sensor based Open Vocabulary Activity Recognition via Text Embedding Inversion—0
Initial Investigation of Kolmogorov-Arnold Networks (KANs) as Feature Extractors for IMU Based Human Activity Recognition—0
InMyFace: Inertial and Mechanomyography-Based Sensor Fusion for Wearable Facial Activity Recognition—0
In-sensor 24 classes HAR under 850 Bytes—0
In Shift and In Variance: Assessing the Robustness of HAR Deep Learning Models against Variability—0
From Lab to Field: Real-World Evaluation of an AI-Driven Smart Video Solution to Enhance Community Safety—0
Integrating Audio Narrations to Strengthen Domain Generalization in Multimodal First-Person Action Recognition—0
Integrating Features for Recognizing Human Activities through Optimized Parameters in Graph Convolutional Networks and Transformer Architectures—0
International Workshop on Continual Semi-Supervised Learning: Introduction, Benchmarks and Baselines—0
Interpretable Parallel Recurrent Neural Networks with Convolutional Attentions for Multi-Modality Activity Modeling—0
Invariant Feature Learning for Sensor-based Human Activity Recognition—0
Show:102550
← PrevPage 35 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