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 1101–1150 of 1322 papers

TitleStatusHype
Can You Spot the Semantic Predicate in this Video?—0
DFTerNet: Towards 2-bit Dynamic Fusion Networks for Accurate Human Activity Recognition—0
Attention is All We Need: Nailing Down Object-centric Attention for Egocentric Activity RecognitionCode0
Deep Transfer Learning for Cross-domain Activity Recognition—0
Human Activity Recognition in RGB-D Videos by Dynamic Images—0
A Survey of Knowledge Representation in Service Robotics—0
Who did What at Where and When: Simultaneous Multi-Person Tracking and Activity Recognition—0
Multi-modal Egocentric Activity Recognition using Audio-Visual Features—0
Human Activity Prediction in Smart Home Environments with LSTM Neural Networks—0
Cross-position Activity Recognition with Stratified Transfer Learning—0
On Multi-resident Activity Recognition in Ambient Smart-Homes—0
Object Level Visual Reasoning in VideosCode0
Human Activity Recognition Based on Wearable Sensor Data: A Standardization of the State-of-the-ArtCode0
Qiniu Submission to ActivityNet Challenge 2018—0
Egocentric Activity Recognition on a Budget—0
Visually Guided Spatial Relation Extraction from Text—0
Surgical Activity Recognition in Robot-Assisted Radical Prostatectomy using Deep Learning—0
STS Classification with Dual-stream CNN—0
On Attention Models for Human Activity Recognition—0
Understanding and Improving Deep Neural Network for Activity RecognitionCode0
Interpretable Parallel Recurrent Neural Networks with Convolutional Attentions for Multi-Modality Activity Modeling—0
Object and Text-guided Semantics for CNN-based Activity Recognition—0
Human Activity Recognition using Recurrent Neural Networks—0
M-PACT: An Open Source Platform for Repeatable Activity Classification ResearchCode0
Fine-grained Activity Recognition in Baseball VideosCode0
Question Type Guided Attention in Visual Question Answering—0
Non-Linear Temporal Subspace Representations for Activity Recognition—0
Modelling the Influence of Cultural Information on Vision-Based Human Home Activity Recognition—0
Dynamic Vision Sensors for Human Activity RecognitionCode0
Analysis of Hand Segmentation in the WildCode0
Semi-Supervised Online Structure Learning for Composite Event RecognitionCode1
ReHAR: Robust and Efficient Human Activity Recognition—0
Glimpse Clouds: Human Activity Recognition from Unstructured Feature PointsCode0
Protecting Sensory Data against Sensitive InferencesCode1
Multimodal Explanations: Justifying Decisions and Pointing to the EvidenceCode0
Learning Attribute Representation for Human Activity Recognition—0
Personalized Human Activity Recognition Using Convolutional Neural Networks—0
When Vehicles See Pedestrians with Phones:A Multi-Cue Framework for Recognizing Phone-based Activities of Pedestrians—0
Human Activity Recognition for Mobile Robot—0
Semi-Supervised Convolutional Neural Networks for Human Activity Recognition—0
Time Series Segmentation through Automatic Feature Learning—0
Multivariate LSTM-FCNs for Time Series ClassificationCode1
Real-world Anomaly Detection in Surveillance VideosCode1
Stratified Transfer Learning for Cross-domain Activity Recognition—0
Im2Flow: Motion Hallucination from Static Images for Action RecognitionCode0
Human activity recognition from mobile inertial sensors using recurrence plots—0
Recognizing Plans by Learning Embeddings from Observed Action Distributions—0
Action Recognition in Video Sequences using Deep Bi-Directional LSTM With CNN FeaturesCode0
Temporal Relational Reasoning in VideosCode0
Fullie and Wiselie: A Dual-Stream Recurrent Convolutional Attention Model for Activity Recognition—0
Show:102550
← PrevPage 23 of 27Next →
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