Cover Image

HAR-DoReMi: Optimizing Data Mixture for Self-Supervised Human Activity Recognition Across Heterogeneous IMU Datasets

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ban, Lulu, Zhu, Tao, Lu, Xiangqing, Qiu, Qi, Han, Wenyong, Li, Shuangjian, Chen, Liming, Wang, Kevin I-Kai, Nie, Mingxing, Wan, Yaping
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

DoReMi: Bridging 3D Domains via Topology-Aware Domain-Representation Mixture of Experts
by: Xing, Mingwei, et al.
Published: (2025)

S2C‐HAR: A Semi‐Supervised Human Activity Recognition Framework Based on Contrastive Learning
by: Xue Li, et al.
Published: (2025)

DoReMi: Grounding Language Model by Detecting and Recovering from Plan-Execution Misalignment
by: Guo, Yanjiang, et al.
Published: (2023)

FLOW: Fusing and Shuffling Global and Local Views for Cross-User Human Activity Recognition with IMUs
by: Qiu, Qi, et al.
Published: (2024)

HARMamba: Efficient and Lightweight Wearable Sensor Human Activity Recognition Based on Bidirectional Mamba
by: Li, Shuangjian, et al.
Published: (2024)

P2LHAP:Wearable sensor-based human activity recognition, segmentation and forecast through Patch-to-Label Seq2Seq Transformer
by: Li, Shuangjian, et al.
Published: (2024)

PTMs-TSCIL Pre-Trained Models Based Class-Incremental Learning
by: Wu, Yuanlong, et al.
Published: (2025)

BenchHAR: Benchmarking Self-Supervised Learning for Generalizable Sensor-based Activity Recognition
by: Cai, Yize, et al.
Published: (2026)

ALS-HAR: Harnessing Wearable Ambient Light Sensors to Enhance IMU-based Human Activity Recogntion
by: Ray, Lala Shakti Swarup, et al.
Published: (2024)

Matching Skeleton-based Activity Representations with Heterogeneous Signals for HAR
by: Li, Shuheng, et al.
Published: (2025)

BasketHAR: A Multimodal Dataset for Human Activity Recognition and Sport Analysis in Basketball Training Scenarios
by: Gao, Xian, et al.
Published: (2026)

MCformer: Multivariate Time Series Forecasting with Mixed-Channels Transformer
by: Han, Wenyong, et al.
Published: (2024)

RAG-HAR: Retrieval Augmented Generation-based Human Activity Recognition
by: Sivaroopan, Nirhoshan, et al.
Published: (2025)

CMD-HAR: Cross-Modal Disentanglement for Wearable Human Activity Recognition
by: Yu, Ying, et al.
Published: (2025)

Hang-Time HAR: A Benchmark Dataset for Basketball Activity Recognition using Wrist-Worn Inertial Sensors
by: Hoelzemann, Alexander, et al.
Published: (2023)

WatchHAR: Real-time On-device Human Activity Recognition System for Smartwatches
by: Yeon, Taeyoung, et al.
Published: (2025)

STA‐HAR: A Spatiotemporal Attention‐Based Framework for Human Activity Recognition
by: Md. Khaliluzzaman, et al.
Published: (2024)

Non-stationary BERT: Exploring Augmented IMU Data For Robust Human Activity Recognition
by: Sun, Ning, et al.
Published: (2024)

iKAN: Global Incremental Learning with KAN for Human Activity Recognition Across Heterogeneous Datasets
by: Liu, Mengxi, et al.
Published: (2024)

Activity and Subject Detection for UCI HAR Dataset with & without missing Sensor Data
by: Saha, Debashish, et al.
Published: (2025)

FieldHAR: A Fully Integrated End-to-end RTL Framework for Human Activity Recognition with Neural Networks from Heterogeneous Sensors
by: Liu, Mengxi, et al.
Published: (2023)

TRIS-HAR: Transmissive Reconfigurable Intelligent Surfaces-assisted Cognitive Wireless Human Activity Recognition Using State Space Models
by: Liu, Junshuo, et al.
Published: (2024)

PrivHAR-Bench: A Graduated Privacy Benchmark Dataset for Video-Based Action Recognition
by: Ansari, Samar
Published: (2026)

UniMotion: Self-Supervised Learning for Cross-Domain IMU Motion Recognition
by: Khanna, Prerna, et al.
Published: (2026)

Neural-HAR: A Dimension-Gated CNN Accelerator for Real-Time Radar Human Activity Recognition
by: Wu, Yizhuo, et al.
Published: (2025)

LS-HAR: Language Supervised Human Action Recognition with Salient Fusion, Construction Sites as a Use-Case
by: Mahdavian, Mohammad, et al.
Published: (2024)

Beyond Motion Primitives: Behavioral Activity Recognition from Head-Mounted IMU
by: Huang, Chung-Ta, et al.
Published: (2026)

TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices
by: Bian, Sizhen, et al.
Published: (2025)

Weak-Annotation of HAR Datasets using Vision Foundation Models
by: Bock, Marius, et al.
Published: (2024)

A Survey of IMU Based Cross-Modal Transfer Learning in Human Activity Recognition
by: Kamboj, Abhi, et al.
Published: (2024)

SensingAgents: A Multi-Agent Collaborative Framework for Robust IMU Activity Recognition
by: Zheng, Naiyu, et al.
Published: (2026)

EgoCHARM: Resource-Efficient Hierarchical Activity Recognition using an Egocentric IMU Sensor
by: Padmanabha, Akhil, et al.
Published: (2025)

COMODO: Cross-Modal Video-to-IMU Distillation for Efficient Egocentric Human Activity Recognition
by: Chen, Baiyu, et al.
Published: (2025)

Graph Privacy: A Heterogeneous Federated GNN for Trans-Border Financial Data Circulation
by: Tan, Zhizhong, et al.
Published: (2025)

BabyMamba-HAR: Lightweight Selective State Space Models for Efficient Human Activity Recognition on Resource Constrained Devices
by: Mandal, Mridankan
Published: (2026)

OWP-IMU: An RSS-based Optical Wireless and IMU Indoor Positioning Dataset
by: Wu, Fan, et al.
Published: (2025)

StrengthSense: A Dataset of IMU Signals Capturing Everyday Strength-Demanding Activities
by: Yang, Zeyu, et al.
Published: (2025)

PoHAR: Understanding Hyperlocal Human Activities with Pollution Sensor Networks
by: Karmakar, Prasenjit, et al.
Published: (2026)

Personality-aware Human-centric Multimodal Reasoning: A New Task, Dataset and Baselines
by: Zhu, Yaochen, et al.
Published: (2023)

Adversarial Domain Adaptation Enables Knowledge Transfer Across Heterogeneous RNA-Seq Datasets
by: Dradjat, Kevin, et al.
Published: (2026)