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 1026–1050 of 1322 papers

TitleStatusHype
Wearable Sensor Data Based Human Activity Recognition using Machine Learning: A new approach—0
Multivariate Time Series Classification using Dilated Convolutional Neural NetworkCode0
Human Activity Recognition Using Visual Object Detection—0
Large-scale weakly-supervised pre-training for video action recognitionCode0
Human Activity Recognition Using LSTM-RNN Deep Neural Network Architecture—0
Eidetic 3D LSTM: A Model for Video Prediction and BeyondCode0
Pyramid Recurrent Neural Networks for Multi-Scale Change-Point Detection—0
Segmented convolutional gated recurrent neural networks for human activity recognition in ultra-wideband radar—0
Latent Variable Algorithms for Multimodal Learning and Sensor Fusion—0
Learning Actor Relation Graphs for Group Activity RecognitionCode0
Semi-Supervised First-Person Activity Recognition in Body-Worn Video—0
Smart Laptop Bag with Machine Learning for Activity Recognition—0
Unsupervised Synthesis of Anomalies in Videos: Transforming the Normal—0
Digging Deeper into Egocentric Gaze Prediction—0
Context-Aware Query Selection for Active Learning in Event Recognition—0
Convolutional Relational Machine for Group Activity Recognition—0
Subject Cross Validation in Human Activity RecognitionCode0
Cross-Subject Transfer Learning in Human Activity Recognition Systems using Generative Adversarial Networks—0
Few-Shot Learning-Based Human Activity Recognition—0
Attention-based Convolutional Neural Network for Weakly Labeled Human Activities Recognition with Wearable Sensors—0
Human Activity Recognition for Edge Devices—0
Adversarial Attacks on Deep Neural Networks for Time Series ClassificationCode0
DeepCount: Crowd Counting with WiFi via Deep Learning—0
Asymmetric Residual Neural Network for Accurate Human Activity Recognition—0
Online Human Activity Recognition Employing Hierarchical Hidden Markov Models—0
Show:102550
← PrevPage 42 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