Jingbo Shang, Xiyuan Zhang, Diyan Teng, Ranak Chowdhury, Shuheng Li, Dezhi Hong, Rajesh Gupta
We lifted 8 functions out of this paper's own repositories and ran 3 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| xiyuanzh/unimts | canonical | 3 of 8 |
| Function | Status | Where it lives |
|---|---|---|
| get_hop_distance | Ran | xiyuanzh/unimts/model.py pointer only (licence: NONE) · get_code("c257ac36cba643a2") |
| normalize_digraph | Ran | xiyuanzh/unimts/model.py pointer only (licence: NONE) · get_code("8158f4435afa26b7") |
| normalize_undigraph | Ran | xiyuanzh/unimts/model.py pointer only (licence: NONE) · get_code("f3dfe2628c96a73d") |
| augment_data | Not yet run | xiyuanzh/unimts/utils.py pointer only (licence: NONE) · get_code("a7a90479c224d2be") |
| load_api_key | Not yet run | xiyuanzh/unimts/text_aug.py pointer only (licence: NONE) · get_code("c1bf9f2229ec2d0e") |
| plot_skeleton | Not yet run | xiyuanzh/unimts/utils.py pointer only (licence: NONE) · get_code("cf62236765805405") |
| select_samples | Not yet run | xiyuanzh/unimts/data.py pointer only (licence: NONE) · get_code("9b7182219787a9e4") |
| update_limits | Not yet run | xiyuanzh/unimts/utils.py pointer only (licence: NONE) · get_code("6178ce79acb84050") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Motion time series collected from mobile and wearable devices such as smartphones and smartwatches offer significant insights into human behavioral patterns, with wide applications in healthcare, automation, IoT, and AR/XR due to their lowpower, always-on nature. However, given security and privacy concerns, building large-scale motion time series datasets remains difficult, preventing the development of pre-trained models for human activity analysis. Typically, existing models are trained and tested on the same dataset, leading to poor generalizability across variations in device location, device mounting orientation and human activity type. In this paper, we introduce UniMTS 1 , the first unified pre-training procedure for motion time series that generalizes across diverse device latent factors and activities. Specifically, we employ a contrastive learning framework that aligns motion time series with text descriptions enriched by large language models. This helps the model learn the semantics of time series to generalize across activities. Given the absence of large-scale motion time series data, we derive and synthesize time series from existing motion skeleton data with all-joint coverage. Spatio-temporal graph networks are utilized to capture the relationships across joints for generalization across different device locations. We further design rotation-invariant augmentation to make the model agnostic to changes in device mounting orientations. Our model shows exceptional generalizability across 18 motion time series classification benchmark datasets, outperforming the best baselines by 340% in the zero-shot setting, 16.3% in the few-shot setting, and 9.2% in the full-shot setting.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2410.19818")
get_code_for_paper("2410.19818")
have("2410.19818")
Connect an agent — have() is free.