activity
20142024
most citedRefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation

64 citations · 138 across the 28 of their papers we have counts for

collaborators

7 papers

cs.CV2022

CRCNet: Few-shot Segmentation with Cross-Reference and Region-Global Conditional Networks

Weide Liu, Chi Zhang, Guosheng Lin +1

Few-shot segmentation aims to learn a segmentation model that can be generalized to novel classes with only a few training images. In this paper, we propose a Cross-Reference and L…

cs.CV2022

Paired Cross-Modal Data Augmentation for Fine-Grained Image-to-Text Retrieval

Hao Wang, Guosheng Lin, Steven C. H. Hoi +1

This paper investigates an open research problem of generating text-image pairs to improve the training of fine-grained image-to-text cross-modal retrieval task, and proposes a nov…

cs.CV20225 cited

Dual Adaptive Transformations for Weakly Supervised Point Cloud Segmentation

Zhonghua Wu, Yicheng Wu, Guosheng Lin +2

Weakly supervised point cloud segmentation, i.e. semantically segmenting a point cloud with only a few labeled points in the whole 3D scene, is highly desirable due to the heavy bu…

cs.CV20223 cited

Few-shot Open-set Recognition Using Background as Unknowns

Nan Song, Chi Zhang, Guosheng Lin

Few-shot open-set recognition aims to classify both seen and novel images given only limited training data of seen classes. The challenge of this task is that the model is required…

cs.CV20161 cited

Sequential Person Recognition in Photo Albums with a Recurrent Network

Yao Li, Guosheng Lin, Bohan Zhuang +3

Recognizing the identities of people in everyday photos is still a very challenging problem for machine vision, due to non-frontal faces, changes in clothing, location, lighting an…

cs.CV201664 cited

RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation

Guosheng Lin, Anton Milan, Chunhua Shen +1

Recently, very deep convolutional neural networks (CNNs) have shown outstanding performance in object recognition and have also been the first choice for dense classification probl…