What Egocentric Video Embeddings Encode and How to Combine Them with Inertial Sensors for Human Activity Recognition
cs.CV
Submitted: 2026-10-09
Updated: 2026-10-09
Comments: 31 pages, 11 figures, 11 tables. Solution to the 3rd WEAR Dataset Challenge @ HASCA 2026
Code: https://github.com/acco-cyber/wearhasca2026-challenge
Project page: https://mariusbock.github.io/wear/challenge.html
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- WEAR: An Outdoor Sports Dataset for Wearable and Egocentric Activity Recognition
- Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives
- Left-Right Swapping and Upper-Lower Limb Pairing for Robust Multi-Wearable Workout Activity Detection
- Robust In-the-Wild Exercise Recognition from a Single Wearable: Data-Side Fusion, Sensor Rotation, and Feature Engineering
- Advancing Location-Invariant and Device-Agnostic Motion Activity Recognition on Wearable Devices
- Unifying distillation and privileged information
- COMODO: Cross-Modal Video-to-IMU Distillation for Efficient Egocentric Human Activity Recognition
- Temporal Structure Matters for Efficient Test-Time Adaptation in Wearable Human Activity Recognition
- Label Propagation for Deep Semi-supervised Learning
- All-but-the-Top: Simple and Effective Postprocessing for Word Representations
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models