T
Tong Yu
Researcher at Carnegie Mellon University
Publications - 55
Citations - 969
Tong Yu is an academic researcher from Carnegie Mellon University. The author has contributed to research in topics: Activity recognition & Computer science. The author has an hindex of 15, co-authored 51 publications receiving 669 citations. Previous affiliations of Tong Yu include National Taiwan University & Samsung.
Papers
More filters
Proceedings ArticleDOI
Understanding and improving recurrent networks for human activity recognition by continuous attention
TL;DR: Wang et al. as mentioned in this paper proposed two attention models for human activity recognition, namely, temporal attention and sensor attention, which adaptively focus on important signals and sensor modalities.
Journal ArticleDOI
FootprintID: Indoor Pedestrian Identification through Ambient Structural Vibration Sensing
Shijia Pan,Tong Yu,Mostafa Mirshekari,Jonathon Fagert,Amelie Bonde,Ole J. Mengshoel,Hae Young Noh,Pei Zhang +7 more
TL;DR: This work utilizes the physical insight on how individual step signal changes with walking speeds and introduces an iterative transductive learning algorithm (ITSVM) to achieve robust classification with limited labeled training data.
Journal ArticleDOI
Big data small footprint: the design of a low-power classifier for detecting transportation modes
TL;DR: This paper presents a hardware-software co-design of a classifier for wearables to detect a person's transportation mode (i.e., still, walking, running, biking, and on a vehicle) that is able to drastically reduce power consumption by 99%, while maintaining competitive mode-detection accuracy.
Proceedings ArticleDOI
A Visual Dialog Augmented Interactive Recommender System
Tong Yu,Yilin Shen,Hongxia Jin +2 more
TL;DR: This paper proposes a novel dialog-based recommender system to interactively recommend a list of items with visual appearance, and proposes a variant of the cascading bandits, where the neural representations of the item images and user feedback in natural language are utilized.
Proceedings ArticleDOI
Semi-supervised convolutional neural networks for human activity recognition
TL;DR: In this article, semi-supervised methods based on convolutional neural networks (CNNs) are proposed to learn discriminative hidden features from both labeled and unlabeled data while also performing feature learning on raw sensor data.