On the public citation graph

From CNNs to Transformers in Multimodal Human Action Recognition: A Survey

https://doi.org/10.1145/3664815
0 signed · 126 inferred · view as graph

Inferred edges come from two machine sources: sweeps of open repository metadata (mostly SSRN and Zenodo), and a bulk OpenAlex citation snapshot. Every row below is labelled with the one it came from. Neither is a complete citation index — absence here is not evidence of absence.

Is this your work? Sign in with ORCID and put your name on the claims that are yours.
Claim with ORCID
Reference health. See whether every reference in this work resolves to a known work and none has been retracted — and get a dated CiteStamped badge you can embed.
See reference health

What this work says

Outgoing claims: the papers this work cites, builds on, or argues with.

inferredcites →https://doi.org/10.1007/3-540-48157-5_29openalex-snapshot
Towards a Better Understanding of Context and Context-Awareness
inferredcites →https://doi.org/10.1007/s00521-023-09186-5openalex-snapshot
Multimodal fusion for audio-image and video action recognition
inferredcites →https://doi.org/10.1007/s00530-010-0182-0openalex-snapshot
Multimodal fusion for multimedia analysis: a survey
inferredcites →https://doi.org/10.1007/s10044-019-00789-0openalex-snapshot
Human action recognition: a framework of statistical weighted segmentation and rank correlation-based selection
inferredcites →https://doi.org/10.1007/s11042-015-3177-1openalex-snapshot
A survey of depth and inertial sensor fusion for human action recognition
inferredcites →https://doi.org/10.1007/s11042-020-08806-9openalex-snapshot
Human action recognition using fusion of multiview and deep features: an application to video surveillance
inferredcites →https://doi.org/10.1007/s11263-021-01531-2openalex-snapshot
Rescaling Egocentric Vision: Collection, Pipeline and Challenges for EPIC-KITCHENS-100
inferredcites →https://doi.org/10.1016/j.compeleceng.2016.06.004openalex-snapshot
Human action recognition using fusion of features for unconstrained video sequences
inferredcites →https://doi.org/10.1016/j.cviu.2017.01.011openalex-snapshot
Space-time representation of people based on 3D skeletal data: A review
inferredcites →https://doi.org/10.1016/j.cviu.2018.04.007openalex-snapshot
RGB-D-based human motion recognition with deep learning: A survey
inferredcites →https://doi.org/10.1016/j.future.2019.01.029openalex-snapshot
Action recognition using optimized deep autoencoder and CNN for surveillance data streams of non-stationary environments
inferredcites →https://doi.org/10.1016/j.imavis.2016.06.007openalex-snapshot
From handcrafted to learned representations for human action recognition: A survey
inferredcites →https://doi.org/10.1016/j.imavis.2017.01.010openalex-snapshot
Going deeper into action recognition: A survey
inferredcites →https://doi.org/10.1016/j.neucom.2016.09.063openalex-snapshot
Learning deep event models for crowd anomaly detection
inferredcites →https://doi.org/10.1016/j.neucom.2018.10.104openalex-snapshot
A sequential deep learning application for recognising human activities in smart homes
inferredcites →https://doi.org/10.1016/j.patcog.2014.04.018openalex-snapshot
A survey on still image based human action recognition
inferredcites →https://doi.org/10.1016/j.patcog.2016.05.019openalex-snapshot
RGB-D-based action recognition datasets: A survey
inferredcites →https://doi.org/10.1016/j.patrec.2014.04.011openalex-snapshot
Human activity recognition from 3D data: A review
inferredcites →https://doi.org/10.1016/j.patrec.2018.04.035openalex-snapshot
Combining CNN streams of RGB-D and skeletal data for human activity recognition
inferredcites →https://doi.org/10.1016/j.robot.2020.103451openalex-snapshot
I-Support: A robotic platform of an assistive bathing robot for the elderly population
inferredcites →https://doi.org/10.1038/nature21054openalex-snapshot
A solution to the single-question crowd wisdom problem
inferredcites →https://doi.org/10.1038/s41598-022-22514-4openalex-snapshot
Artificial intelligence-based methods for fusion of electronic health records and imaging data
inferredcites →https://doi.org/10.1049/trit.2019.0002openalex-snapshot
New shape descriptor in the context of edge continuity
inferredcites →https://doi.org/10.1049/trit.2019.0017openalex-snapshot
Three‐stage network for age estimation
inferredcites →https://doi.org/10.1080/21681163.2020.1835550openalex-snapshot
LapFormer: surgical tool detection in laparoscopic surgical video using transformer architecture
inferredcites →https://doi.org/10.1109/access.2019.2931804openalex-snapshot
Action Recognition From Thermal Videos
inferredcites →https://doi.org/10.1109/access.2020.3023599openalex-snapshot
Infrared and 3D Skeleton Feature Fusion for RGB-D Action Recognition
inferredcites →https://doi.org/10.1109/iccv.1995.466933openalex-snapshot
Proceedings of IEEE International Conference on Computer Vision
inferredcites →https://doi.org/10.1109/icip.1997.638657openalex-snapshot
Proceedings International Conference On Image Processing
inferredcites →https://doi.org/10.1109/iros.1994.407417openalex-snapshot
Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'94)
inferredcites →https://doi.org/10.1109/iros45743.2020.9341699openalex-snapshot
Gimme Signals: Discriminative signal encoding for multimodal activity recognition
inferredcites →https://doi.org/10.1109/jsen.2015.2416651openalex-snapshot
Evaluating and Improving the Depth Accuracy of Kinect for Windows v2
inferredcites →https://doi.org/10.1109/tcsvt.2019.2894161openalex-snapshot
stagNet: An Attentive Semantic RNN for Group Activity and Individual Action Recognition
inferredcites →https://doi.org/10.1109/tpami.2017.2691321openalex-snapshot
Deep Multimodal Feature Analysis for Action Recognition in RGB+D Videos
inferredcites →https://doi.org/10.1109/tpami.2019.2916873openalex-snapshot
NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding
inferredcites →https://doi.org/10.1109/tpami.2020.2983686openalex-snapshot
Deep High-Resolution Representation Learning for Visual Recognition
inferredcites →https://doi.org/10.1109/tpami.2022.3183112openalex-snapshot
Human Action Recognition From Various Data Modalities: A Review
inferredcites →https://doi.org/10.1109/tpami.2023.3243465openalex-snapshot
Video Transformers: A Survey
inferredcites →https://doi.org/10.1145/2996463openalex-snapshot
Fixation Prediction through Multimodal Analysis
inferredcites →https://doi.org/10.1145/3317697openalex-snapshot
Proceedings of the 2019 ACM International Conference on Interactive Experiences for TV and Online Video
inferredcites →https://doi.org/10.1145/3408317openalex-snapshot
Survey on Deep Multi-modal Data Analytics: Collaboration, Rivalry, and Fusion
inferredcites →https://doi.org/10.1145/3409332openalex-snapshot
Knowledge-driven Egocentric Multimodal Activity Recognition
inferredcites →https://doi.org/10.1145/3416493openalex-snapshot
Socializing the Videos: A Multimodal Approach for Social Relation Recognition
inferredcites →https://doi.org/10.1145/3421725openalex-snapshot
A Multimodal, Multimedia Point-of-Care Deep Learning Framework for COVID-19 Diagnosis
inferredcites →https://doi.org/10.1145/3490686openalex-snapshot
A Multimodal Framework for Large-Scale Emotion Recognition by Fusing Music and Electrodermal Activity Signals
inferredcites →https://doi.org/10.18653/v1/2020.acl-main.244openalex-snapshot
Pretrained Transformers Improve Out-of-Distribution Robustness
inferredcites →https://doi.org/10.18653/v1/2020.emnlp-main.161openalex-snapshot
HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training
inferredcites →https://doi.org/10.3390/s19030489openalex-snapshot
Metrological and Critical Characterization of the Intel D415 Stereo Depth Camera
inferredcites →https://doi.org/10.3390/s19051005openalex-snapshot
A Comprehensive Survey of Vision-Based Human Action Recognition Methods
inferredcites →https://doi.org/10.3390/s19173808openalex-snapshot
Multi-Sensor Fusion for Activity Recognition—A Survey
inferredcites →https://doi.org/10.3390/s21124246openalex-snapshot
RGB-D Data-Based Action Recognition: A Review
inferredcites →https://doi.org/10.4230/lipics.cosit.2022.18openalex-snapshot
AI-Assisted Pipeline for Dynamic Generation of Trustworthy Health Supplement Content at Scale
inferredcites →https://doi.org/10.48550/arxiv.1703.07475openalex-snapshot
PKU-MMD: A Large Scale Benchmark for Continuous Multi-Modal Human Action Understanding
inferredcites →https://doi.org/10.48550/arxiv.1705.06950openalex-snapshot
The Kinetics Human Action Video Dataset
inferredcites →https://doi.org/10.48550/arxiv.1808.01340openalex-snapshot
A Short Note about Kinetics-600
inferredcites →https://doi.org/10.48550/arxiv.1812.05770openalex-snapshot
Action Machine: Rethinking Action Recognition in Trimmed Videos
inferredcites →https://doi.org/10.48550/arxiv.1906.05743openalex-snapshot
Learning Video Representations using Contrastive Bidirectional Transformer
inferredcites →https://doi.org/10.48550/arxiv.1907.06987openalex-snapshot
A Short Note on the Kinetics-700 Human Action Dataset
inferredcites →https://doi.org/10.48550/arxiv.1908.02265openalex-snapshot
ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
inferredcites →https://doi.org/10.48550/arxiv.2012.04124openalex-snapshot
Parameter Efficient Multimodal Transformers for Video Representation Learning
inferredcites →https://doi.org/10.48550/arxiv.2103.05247openalex-snapshot
Pretrained Transformers as Universal Computation Engines
inferredcites →https://doi.org/10.48550/arxiv.2104.11178openalex-snapshot
VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text
inferredcites →https://doi.org/10.48550/arxiv.2108.11575openalex-snapshot
Shifted Chunk Transformer for Spatio-Temporal Representational Learning
inferredcites →https://doi.org/10.5244/c.34.29openalex-snapshot
A Better Use of Audio-Visual Cues: Dense Video Captioning with Bi-modal Transformer
inferredcites →https://doi.org/10.57702/jtuxnt5mopenalex-snapshot
The kinetics human action video dataset

What points at this work

Incoming claims: where this work appears in other papers’ reference lists and arguments.

inferred← citeshttps://doi.org/10.1002/cpe.70729openalex-snapshot
A Student Behavior Recognition Method Based on the Fusion of Attention Mechanism and Kalman Filtering
inferred← citeshttps://doi.org/10.1007/978-3-032-01472-6_15openalex-snapshot
Automatic Recognition and Scoring System in Military Training Applies Modern Deep Learning Techniques
inferred← citeshttps://doi.org/10.1007/978-3-032-09321-9_34openalex-snapshot
Collaborative Multimodal Learning for Human-Human Interaction Recognition in Videos
inferred← citeshttps://doi.org/10.1007/978-3-032-26349-0_14openalex-snapshot
Query Based Deep Contextual Video Understanding
inferred← citeshttps://doi.org/10.1007/978-3-032-27515-8_16openalex-snapshot
Multi-modal Framework for Crime Event Analysis
inferred← citeshttps://doi.org/10.1007/978-3-032-31441-3_5openalex-snapshot
EgoHAnG: Graph-Enhanced Horizon Aware Egocentric Action Anticipation
inferred← citeshttps://doi.org/10.1007/978-981-95-1746-6_66openalex-snapshot
Transformer Model-Based Early Fusion of Skeletal and Inertial Modalities for Human Action Recognition
inferred← citeshttps://doi.org/10.1007/s00530-025-01950-yopenalex-snapshot
Kin-LeapK: an enhanced human–computer interaction system with improved AdaBoost visual and audio information recognition methods
inferred← citeshttps://doi.org/10.1007/s10791-026-10143-8openalex-snapshot
A deep learning driven framework with ObjTrackNet for real-time object and human detection in smart video surveillance
inferred← citeshttps://doi.org/10.1007/s11760-025-04964-1openalex-snapshot
PGFiT-Net: a two-stream human action recognition model with pose-gated and FiLM-conditioned fusion
inferred← citeshttps://doi.org/10.1007/s44163-026-01289-xopenalex-snapshot
A transformer-based intelligent online virtual conductor assistance system for choirs
inferred← citeshttps://doi.org/10.1007/s44163-026-01904-xopenalex-snapshot
Application of human action recognition in film and television editing based on multi-scale visual transformer and attention mechanism
inferred← citeshttps://doi.org/10.1007/s44163-026-02188-xopenalex-snapshot
DCA-based multimodal fusion for robust recognition of adolescent sports and abnormal health behaviors
inferred← citeshttps://doi.org/10.1007/s44196-025-01146-2openalex-snapshot
CoachXNet: An Artificial Intelligence and Internet of Things Integrated Platform for Personalized Training and Feedback in Digital Sports
inferred← citeshttps://doi.org/10.1016/j.engappai.2025.110466openalex-snapshot
A deep neural network for small object detection in complex environments with unmanned aerial vehicle imagery
inferred← citeshttps://doi.org/10.1016/j.neucom.2025.129820openalex-snapshot
Local and Global Spatial–Temporal Transformer for skeleton-based action recognition
inferred← citeshttps://doi.org/10.1016/j.neucom.2026.134402openalex-snapshot
Multi-view transformer with hierarchical attention for action recognition
inferred← citeshttps://doi.org/10.1016/j.procs.2025.07.223openalex-snapshot
GRU-Based Multi-Modal Human Activity Recognition
inferred← citeshttps://doi.org/10.1016/j.procs.2026.06.537openalex-snapshot
Skeleton Spirals and Temporal Saliency-based Key Poses for Enhanced Human Activity Detection in Indoor Settings
inferred← citeshttps://doi.org/10.1038/s41598-025-26297-2openalex-snapshot
A tiny inertial transformer for human activity recognition via multimodal knowledge distillation and explainable AI
inferred← citeshttps://doi.org/10.1038/s41598-026-38107-4openalex-snapshot
UncerTrans: uncertainty-aware temporal transformer for early action prediction
inferred← citeshttps://doi.org/10.1109/access.2024.3481631openalex-snapshot
Multimodal Human Action Recognition Framework Using an Improved CNNGRU Classifier
inferred← citeshttps://doi.org/10.1109/access.2025.3555539openalex-snapshot
A Review of Short-Term, Long-Term, and Memory Consolidation Mechanisms in the Hippocampus and Cerebral Cortex
inferred← citeshttps://doi.org/10.1109/access.2025.3590073openalex-snapshot
Next Generation Human Action Recognition: A Comprehensive Review of State-of-the-Art Signal Processing Techniques
inferred← citeshttps://doi.org/10.1109/cisat71030.2026.11682416openalex-snapshot
A human action recognition method based on convolutional neural networks
inferred← citeshttps://doi.org/10.1109/ic2ect66838.2025.11290976openalex-snapshot
TimeSformer-Based Spatiotemporal Attention for Dynamic Recognition and Evolution Modeling of Student Engagement in Online Learning
inferred← citeshttps://doi.org/10.1109/icedcs64328.2024.00024openalex-snapshot
Human Action Recognition Using CNN and ViT
inferred← citeshttps://doi.org/10.1109/icimtech202671078.2026.11698918openalex-snapshot
Self-Supervised Skeleton Representation for Imbalanced Ethnic Dance Motion Analysis
inferred← citeshttps://doi.org/10.1109/icrtcst68392.2026.11545409openalex-snapshot
Instruction-Following Agents for Multimodal Human-AI Collaboration in Industrial Robotics
inferred← citeshttps://doi.org/10.1109/iros60139.2025.11247108openalex-snapshot
Spatio-Temporal Hyperbolic Aggregation Neural Network for Human Action Recognition
inferred← citeshttps://doi.org/10.1109/jiot.2025.3638708openalex-snapshot
RF-ShopViT: Non-Line-of-Sight Shopping Behavior Recognition Using COTS RFID and Vision Transformer
inferred← citeshttps://doi.org/10.1109/jsen.2026.3653897openalex-snapshot
MultimodalMamba: An Efficient DHCNN–FAM–Mamba Architecture for Human Activity Recognition
inferred← citeshttps://doi.org/10.1109/rait65068.2025.11089208openalex-snapshot
Action recognition from egocentric videos using RGB + Depth modalities
inferred← citeshttps://doi.org/10.1109/tce.2025.3593333openalex-snapshot
Learning Three-Modal Joint Representations With Multimodal Transformer for Multimodal Sentiment Analysis
inferred← citeshttps://doi.org/10.1109/tcsvt.2025.3642759openalex-snapshot
MR-MAR: Multi-Layer Representation Learning for Multi-Modal Action Recognition
inferred← citeshttps://doi.org/10.1109/tcsvt.2026.3707206openalex-snapshot
DEFT-DPT: A Lightweight Multimodal Framework for Egocentric Video Action Recognition
inferred← citeshttps://doi.org/10.1109/tcyb.2025.3629343openalex-snapshot
Pedestrian Group Activity Recognition for Autonomous Vehicles and Robots: A Survey and Perspectives
inferred← citeshttps://doi.org/10.1109/wacv61042.2026.00668openalex-snapshot
Alignment and Distillation: A Robust Framework for Multimodal Domain Generalizable Human Action Recognition
inferred← citeshttps://doi.org/10.1145/3746640openalex-snapshot
Towards Key Point Identification (KPI) for Lecture Videos: Approaches and Performance Evaluation
inferred← citeshttps://doi.org/10.1145/3786334openalex-snapshot
Advances, Evaluation, and Explainability of Large Language Models in Healthcare: A Systematic Review
inferred← citeshttps://doi.org/10.1145/3832322openalex-snapshot
Global-local Temporal Modeling Enhanced 2DCNN with Category-supervised Contrastive Learning for Action Recognition
inferred← citeshttps://doi.org/10.1145/3838457.3838564openalex-snapshot
Design of Intelligent Training System for Higher Vocational Basketball Based on CNN Multimodal Action Recognition
inferred← citeshttps://doi.org/10.1145/3839227openalex-snapshot
MICA-Net: A Multimodal Cross-Attention Network for Human Action Recognition
inferred← citeshttps://doi.org/10.1504/ijict.2025.146102openalex-snapshot
Deep learning models combining stereo vision for dance movement evaluation
inferred← citeshttps://doi.org/10.2139/ssrn.5475996openalex-snapshot
A Spatiotemporal Dynamic Weighting Method Based on Hyperspherical Tensor Mapping for Action Recognition
inferred← citeshttps://doi.org/10.2139/ssrn.6668913openalex-snapshot
Multi-Scale Transformer-based architectures with temporal granularity for Human Action Recognition in industrial assembly
inferred← citeshttps://doi.org/10.26782/jmcms.2026.08.00010openalex-snapshot
AN EFFICIENT MULTIMODAL FRAMEWORK FOR HUMAN ACTION RECOGNITION USING TCN AND BILSTM WITH LATE FUSION
inferred← citeshttps://doi.org/10.3389/frai.2026.1928901openalex-snapshot
DXSP: gesture-only temporal localization of decisive moments in dyadic persuasion
inferred← citeshttps://doi.org/10.3390/app15179390openalex-snapshot
Robust Face Recognition Under Challenging Conditions: A Comprehensive Review of Deep Learning Methods and Challenges
inferred← citeshttps://doi.org/10.3390/electronics15091910openalex-snapshot
CDFMD: Causal Dynamic Fusion Reasoning-Based Multimodal Intelligent Fault Diagnosis Model for Power Transformers
inferred← citeshttps://doi.org/10.3390/electronics15122644openalex-snapshot
Temporally Consistent Student Behavior Recognition in Smart Classrooms via Attention-Guided Perception and State Estimation
inferred← citeshttps://doi.org/10.3390/make8100298openalex-snapshot
Auditing Multimodal Fusion Benchmarks: Leakage, Attribution, and Calibration in Elderly Fall Detection
inferred← citeshttps://doi.org/10.3390/multimedia2030015openalex-snapshot
DMART-HAR: Dynamic Multimodal Transformer Learning for Cross-Domain Human Activity Recognition
inferred← citeshttps://doi.org/10.3390/s25092930openalex-snapshot
Multi-Head Attention-Based Framework with Residual Network for Human Action Recognition
inferred← citeshttps://doi.org/10.3390/s25123794openalex-snapshot
Gait Recognition via Enhanced Visual–Audio Ensemble Learning with Decision Support Methods
inferred← citeshttps://doi.org/10.3390/s25134028openalex-snapshot
A Comprehensive Methodological Survey of Human Activity Recognition Across Diverse Data Modalities
inferred← citeshttps://doi.org/10.3390/s25154763openalex-snapshot
Multimodal Sensing-Enabled Large Language Models for Automated Emotional Regulation: A Review of Current Technologies, Opportunities, and Challenges
inferred← citeshttps://doi.org/10.3390/s25185824openalex-snapshot
Enhancing Long-Term Action Quality Assessment: A Dual-Modality Dataset and Causal Cross-Modal Framework for Trampoline Gymnastics
inferred← citeshttps://doi.org/10.5909/jbe.2026.31.1.77openalex-snapshot
A Study on a VLM-based Natural Language Question-answering System for Real-time Multi-channel Video Analysis Systems
inferred← citeshttps://doi.org/10.70675/75b42392zb2dcz4253z929dz96f2be9ad2e3openalex-snapshot
Approches basées sur les variétés pour la reconnaissance des actions et des gestes
inferred← citeshttps://doi.org/10.7717/peerj-cs.3514openalex-snapshot
Complex interaction recognition via advanced multilevel feature fusion and deep learning model
Editorial review for independent work. ICSAC — the Institute for Complexity Science and Advanced Computing — runs a structured editorial panel for researchers publishing outside journals, and publishes on CiteStamp rails. Submission is free and goes through ORCID: icsacinstitute.org/submit.