32 citations · 96 across the 9 of their papers we have counts for
10 papers
Towards Universal Backward-Compatible Representation Learning
Binjie Zhang, Yixiao Ge, Yantao Shen +6
Conventional model upgrades for visual search systems require offline refresh of gallery features by feeding gallery images into new models (dubbed as "backfill"), which is time-co…
Hot-Refresh Model Upgrades with Regression-Alleviating Compatible Training in Image Retrieval
Binjie Zhang, Yixiao Ge, Yantao Shen +5
The task of hot-refresh model upgrades of image retrieval systems plays an essential role in the industry but has never been investigated in academia before. Conventional cold-refr…
Printed Texts Tracking and Following for a Finger-Wearable Electro-Braille System Through Opto-electrotactile Feedback
Mehdi Rahimi, Yantao Shen, Zhiming Liu +1
This paper presents our recent development on a portable and refreshable text reading and sensory substitution system for the blind or visually impaired (BVI), called Finger-eye. T…
Towards Backward-Compatible Representation Learning
Yantao Shen, Yuanjun Xiong, Wei Xia +1
We propose a way to learn visual features that are compatible with previously computed ones even when they have different dimensions and are learned via different neural network ar…
A Comparison of Various Approaches to Reinforcement Learning Algorithms for Multi-robot Box Pushing
Mehdi Rahimi, Spencer Gibb, Yantao Shen +1
In this paper, a comparison of reinforcement learning algorithms and their performance on a robot box pushing task is provided. The robot box pushing problem is structured as both…
Improving Deep Visual Representation for Person Re-identification by Global and Local Image-language Association
Dapeng Chen, Hongsheng Li, Xihui Liu +3
Person re-identification is an important task that requires learning discriminative visual features for distinguishing different person identities. Diverse auxiliary information ha…
End-to-End Deep Kronecker-Product Matching for Person Re-identification
Yantao Shen, Tong Xiao, Hongsheng Li +2
Person re-identification aims to robustly measure similarities between person images. The significant variation of person poses and viewing angles challenges for accurate person re…
Deep Group-shuffling Random Walk for Person Re-identification
Yantao Shen, Hongsheng Li, Tong Xiao +3
Person re-identification aims at finding a person of interest in an image gallery by comparing the probe image of this person with all the gallery images. It is generally treated a…
Person Re-identification with Deep Similarity-Guided Graph Neural Network
Yantao Shen, Hongsheng Li, Shuai Yi +2
The person re-identification task requires to robustly estimate visual similarities between person images. However, existing person re-identification models mostly estimate the sim…
Learning Deep Neural Networks for Vehicle Re-ID with Visual-spatio-temporal Path Proposals
Yantao Shen, Tong Xiao, Hongsheng Li +2
Vehicle re-identification is an important problem and has many applications in video surveillance and intelligent transportation. It gains increasing attention because of the recen…