paper-with-me

홈 › Papers

Temporally Multi-Scale Sparse Self-Attention for Physical Activity Data Imputation

2024-06-27 · Hui Wei, Maxwell A. Xu, Colin Samplawski, James M. Rehg, Santosh Kumar, Benjamin M. Marlin

Wearable sensors enable health researchers to continuously collect data pertaining to the physiological state of individuals in real-world settings. However, such data can be subject to extensive missingness due to a complex combination of factors. In this work, we study the problem of imputation of missing step count data, one of the most ubiquitous forms of wearable sensor data. We construct a novel and large scale data set consisting of a training set with over 3 million hourly step count observations and a test set with over 2.5 million hourly step count observations. We propose a domain knowledge-informed sparse self-attention model for this task that captures the temporal multi-scale nature of step-count data. We assess the performance of the model relative to baselines and conduct ablation studies to verify our specific model designs.

📄 PDF Abstract BibTeX arXiv:2406.18848

Code (1)

reml-lab/allofus-imputation 공식 구현 pytorch

Tasks

Imputation

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Self-supervised Extraction of Human Motion Structures via Frame-wise Discrete Features

2023-09-12 · Tetsuya Abe, Ryusuke Sagawa, Ko Ayusawa, Wataru Takano

The present paper proposes an encoder-decoder model for extracting the structures of human motions represented by frame-wise discrete features in a self-supervised manner. In the proposed method, features are extracted a…

Clustering

LoViC: Efficient Long Video Generation with Context Compression

2025-07-17 · Jiaxiu Jiang, Wenbo Li, Jingjing Ren, Yuping Qiu 외

Despite recent advances in diffusion transformers (DiTs) for text-to-video generation, scaling to long-duration content remains challenging due to the quadratic complexity of self-attention. While prior efforts -- such a…

Text-to-Video GenerationVideo Generation

LoViT: Long Video Transformer for Surgical Phase Recognition

2023-05-15 · Yang Liu, Maxence Boels, Luis C. Garcia-Peraza-Herrera, Tom Vercauteren 외

Online surgical phase recognition plays a significant role towards building contextual tools that could quantify performance and oversee the execution of surgical workflows. Current approaches are limited since they trai…

Online surgical phase recognitionSurgical phase recognition

ESSENTIAL: Episodic and Semantic Memory Integration for Video Class-Incremental Learning

2025-08-14 · Jongseo Lee, Kyungho Bae, Kyle Min, Gyeong-Moon Park 외 arxiv

In this work, we tackle the problem of video classincremental learning (VCIL). Many existing VCIL methods mitigate catastrophic forgetting by rehearsal training with a few temporally dense samples stored in episodic memo…

class-incremental learningGeneral Knowledge

BSA: Ball Sparse Attention for Large-scale Geometries

2025-06-14 · Catalin E. Brita, Hieu Nguyen, Lohithsai Yadala Chanchu, Domonkos Nagy 외

Self-attention scales quadratically with input size, limiting its use for large-scale physical systems. Although sparse attention mechanisms provide a viable alternative, they are primarily designed for regular structure…