Junsong Yuan

TL;DR: This paper addresses the problem of video-level object instance search, which aims to retrieve the videos in the database that contain a given query object instance, and proposes the Reconstruction-based Object SEarch (ROSE) method, which characterizes a huge corpus of features of possible spatial-temporal locations in the video into the parameters of the reconstruction model.

TL;DR: A person re-id framework designed for a network of multiple wearable devices is presented and an online scheme is proposed as a direct extension of the batch method to ensure its utility in practical applications where a large amount of observations are available every instant.

TL;DR: This paper proposes a novel addition-based vector quantization algorithm, Asymmetric Mapping Quantization (AMQ), to efficiently conduct ANN search and proposes Distributed Asymmetrical MappingQuantization (DAMQ) to enable AMQ to work on very large dataset by distributed learning.

TL;DR: An Augmented Reality solution to allow users to manipulate and inspect 3D virtual objects freely with their bare hands on wearable devices is presented and a unified framework to jointly recover the 6D palm pose and recognize the hand gesture from the depth images is proposed.

TL;DR: This paper proposes to describe 3D scene using height gradient information and proposes a new compact point cloud feature called Height Gradient Histogram (HIGH), which can well handle the intra-category variations of object class, and significantly improve class-average accuracy compared with the state-of-the-art results.