# Enhancing Inertial Hand based HAR through Joint Representation of Language, Pose and Synthetic IMUs

arXiv: https://arxiv.org/abs/2406.01316 · HTML: https://mlsanity.com/paper/2406.01316/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 36 references that are in the map.
- First posted on arXiv 3 Jun 2024.

## Builds on (most cited first, 16 of 16)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1611.08050/) (2016)
- [MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model](https://mlsanity.com/paper/2208.15001/) (2022)
- [T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations](https://mlsanity.com/paper/2301.06052/) (2023)
- [GRAB: A Dataset of Whole-Body Human Grasping of Objects](https://mlsanity.com/paper/2008.11200/) (2020)
- [One Embedder, Any Task: Instruction-Finetuned Text Embeddings](https://mlsanity.com/paper/2212.09741/) (2022)
- [AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time](https://mlsanity.com/paper/2211.03375/) (2022)
- [How2Sign: A Large-scale Multimodal Dataset for Continuous American Sign Language](https://mlsanity.com/paper/2008.08143/) (2020)
- [IMUTube: Automatic Extraction of Virtual on-body Accelerometry from Video for Human Activity Recognition](https://mlsanity.com/paper/2006.05675/) (2020)
- [Generating Virtual On-body Accelerometer Data from Virtual Textual Descriptions for Human Activity Recognition](https://mlsanity.com/paper/2305.03187/) (2023)
- [OpenPack: A Large-scale Dataset for Recognizing Packaging Works in IoT-enabled Logistic Environments](https://mlsanity.com/paper/2212.11152/) (2022)
- [MESEN: Exploit Multimodal Data to Design Unimodal Human Activity Recognition with Few Labels](https://mlsanity.com/paper/2404.01958/) (2024)
- [PresSim: An End-to-end Framework for Dynamic Ground Pressure Profile Generation from Monocular Videos Using Physics-based 3D Simulation](https://mlsanity.com/paper/2302.00391/) (2023)
- [Text me the data: Generating Ground Pressure Sequence from Textual Descriptions for HAR](https://mlsanity.com/paper/2402.14427/) (2024)
- [Spatial-Related Sensors Matters: 3D Human Motion Reconstruction Assisted with Textual Semantics](https://mlsanity.com/paper/2401.05412/) (2023)

## Built on by (most cited first, 6 of 6)

- [MuJo: Multimodal Joint Feature Space Learning for Human Activity Recognition](https://mlsanity.com/paper/2406.03857/) (2024)
- [OpenMarcie: Dataset for Multimodal Action Recognition in Industrial Environments](https://mlsanity.com/paper/2603.02390/) (2026)
- [TxP: Reciprocal Generation of Ground Pressure Dynamics and Activity Descriptions for Improving Human Activity Recognition](https://mlsanity.com/paper/2505.02052/) (2025)
- [ALS-HAR: Harnessing Wearable Ambient Light Sensors to Enhance IMU-based Human Activity Recogntion](https://mlsanity.com/paper/2408.09527/) (2024)
- [SImpHAR: Advancing impedance-based human activity recognition using 3D simulation and text-to-motion models](https://mlsanity.com/paper/2507.06405/) (2025)
- [SPECTRA: An Efficient Spectral-Informed Neural Network for Sensor-Based Activity Recognition](https://mlsanity.com/paper/2603.26482/) (2026)

## Abstract (arXiv)

Due to the scarcity of labeled sensor data in HAR, prior research has turned to video data to synthesize Inertial Measurement Units (IMU) data, capitalizing on its rich activity annotations. However, generating IMU data from videos presents challenges for HAR in real-world settings, attributed to the poor quality of synthetic IMU data and its limited efficacy in subtle, fine-grained motions. In this paper, we propose Multi3Net, our novel multi-modal, multitask, and contrastive-based framework approach to address the issue of limited data. Our pretraining procedure uses videos from online repositories, aiming to learn joint representations of text, pose, and IMU simultaneously. By employing video data and contrastive learning, our method seeks to enhance wearable HAR performance, especially in recognizing subtle activities.Our experimental findings validate the effectiveness of our approach in improving HAR performance with IMU data. We demonstrate that models trained with synthetic IMU data generated from videos using our method surpass existing approaches in recognizing fine-grained activities.