EVFormer: An Egocentric Vision-EMG Bidirectional Attention Model for Bimanual Hand Pose Estimation
cs.LG, cs.HC
Submitted: 2026-10-03
Updated: 2026-10-03
Code: https://github.com/zhenqis123/EgoEMG
Sources
- EgoEMG: A Multimodal Egocentric Dataset with Bilateral EMG and Vision for Hand Pose Estimation
- emg2pose: A Large and Diverse Benchmark for Surface Electromyographic Hand Pose Estimation
- Attention Is All You Need
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- UmeTrack: Unified multi-view end-to-end hand tracking for VR
- HOT3D: Hand and Object Tracking in 3D from Egocentric Multi-View Videos
- WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wild
- EMGBench: Benchmarking Out-of-Distribution Generalization and Adaptation for Electromyography
- DexEMG: Towards Dexterous Teleoperation System via EMG2Pose Generalization
- GigaHands: A Massive Annotated Dataset of Bimanual Hand Activities
- Deep Residual Learning for Image Recognition
- DINOv2: Learning Robust Visual Features without Supervision
- Decoupled Weight Decay Regularization
- Squeeze-and-Excitation Networks
- CPEP: Contrastive Pose-EMG Pre-training Enhances Gesture Generalization on EMG Signals
- TinyMyo: a Tiny Foundation Model for Flexible EMG Signal Processing at the Edge
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks