activity
20182023
most citedMulti-Domain Adversarial Feature Generalization for Person Re-Identification

72 citations · 73 across the 4 of their papers we have counts for

collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV2023

BAA-NGP: Bundle-Adjusting Accelerated Neural Graphics Primitives

Sainan Liu, Shan Lin, Jingpei Lu +2

Implicit neural representations have become pivotal in robotic perception, enabling robots to comprehend 3D environments from 2D images. Given a set of camera poses and associated…

cs.CV20231 cited

SemHint-MD: Learning from Noisy Semantic Labels for Self-Supervised Monocular Depth Estimation

Shan Lin, Yuheng Zhi, Michael C. Yip

Without ground truth supervision, self-supervised depth estimation can be trapped in a local minimum due to the gradient-locality issue of the photometric loss. In this paper, we p…

cs.CV202072 cited

Multi-Domain Adversarial Feature Generalization for Person Re-Identification

Shan Lin, Chang-Tsun Li, Alex C. Kot

With the assistance of sophisticated training methods applied to single labeled datasets, the performance of fully-supervised person re-identification (Person Re-ID) has been impro…

cs.CV2020

Multi-frame Feature Aggregation for Real-time Instrument Segmentation in Endoscopic Video

Shan Lin, Fangbo Qin, Haonan Peng +3

Deep learning-based methods have achieved promising results on surgical instrument segmentation. However, the high computation cost may limit the application of deep models to time…

cs.CV2020

Towards Better Surgical Instrument Segmentation in Endoscopic Vision: Multi-Angle Feature Aggregation and Contour Supervision

Fangbo Qin, Shan Lin, Yangming Li +3

Accurate and real-time surgical instrument segmentation is important in the endoscopic vision of robot-assisted surgery, and significant challenges are posed by frequent instrument…

cs.CV2018

Multi-task Mid-level Feature Alignment Network for Unsupervised Cross-Dataset Person Re-Identification

Shan Lin, Haoliang Li, Chang-Tsun Li +1

Most existing person re-identification (Re-ID) approaches follow a supervised learning framework, in which a large number of labelled matching pairs are required for training. Such…