Article

TransMODAL: A Dual-Stream Transformer with Adaptive Co-Attention for Efficient Human Action Recognition

2025-07-29

Abstract excerpt

Human Action Recognition has seen significant advances through Transformer-based architectures, yet achieving nuanced understanding often requires fusing multiple data modalities. Standard models relying solely on RGB video can struggle with actions defined by subtle motion cues rather than appearance. This paper introduces TransMODAL, a novel dual-stream Transformer that synergistically fuses spatiotemporal appea...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 9084ab35-6f62-50b9-983d-0ee4cb87f1f2
DOI: 10.20944/preprints202507.2386.v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

TransMODAL: A Dual-Stream Transformer with Adaptive Co-Attention for Efficient Human Action RecognitionDOI 10.20944/preprints202507.2386.v1Read

Cross-Domain Semantic-Enhanced Adaptive Graph Fusion Network for Robust Skeleton Action RecognitionSemantic proximity Read

A Comprehensive Literature Review on the Use of Restricted Boltzmann Machines and Deep Belief Networks for Human Action RecognitionSemantic proximity Read

A Comprehensive Literature Review on the Use of Restricted Boltzmann Machines and Deep Belief Networks for Human Action RecognitionSemantic proximity Read

VT-BPAN: Vision Transformer-based bilinear pooling and attention network fusion of RGB and skeleton features for human action recognitionSemantic proximity Read

A Two-Stream Deep Learning Approach for Enhanced Two-Person Human Interaction Recognition in VideosSemantic proximity Read

Human Activity Recognition in the Deep Learning Era: Different Modalities, Recent Advances in Applications, and Emerging TechniquesSemantic proximity Read

A Spatiotemporal Bidirectional Mamba Network with Global–Local Skeletal Enhancement for 3D Human Pose EstimationSemantic proximity Read

Cricket Stroke Classification Using Temporal Deep Learning Models: A Systematic Comparative Study of Sequence Modeling Architectures for Fine-Grained Action RecognitionSemantic proximity Read

Video Human Action Recognition by the Fusion of Significant Motion and Coarse-fine Temporal Granularity FeaturesSemantic proximity Read

Enhancing Aerial Human Action Recognition through GAN-boosted ResNeXt Architecture with Squeeze-and-Excitation NetworkSemantic proximity Read

Real-Time Sports Action Recognition Using a CNN–Transformer Hybrid Deep Learning FrameworkSemantic proximity Read

XTinyHAR: A Tiny Inertial Transformer for Human Activity Recognition via Multimodal Knowledge Distillation and Explainable AISemantic proximity Read