activity
20152023
most citedRefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation

64 citations · 463 across the 56 of their papers we have counts for

collaborators
Showing cs.CVShow all

81 papers · 1 filter

cs.CV2023★ 3 cited

LCReg: Long-Tailed Image Classification with Latent Categories based Recognition

Weide Liu, Zhonghua Wu, Yiming Wang +4

In this work, we tackle the challenging problem of long-tailed image recognition. Previous long-tailed recognition approaches mainly focus on data augmentation or re-balancing stra…

cs.CV2023

Neural Vector Fields: Generalizing Distance Vector Fields by Codebooks and Zero-Curl Regularization

Xianghui Yang, Guosheng Lin, Zhenghao Chen +1

Recent neural networks based surface reconstruction can be roughly divided into two categories, one warping templates explicitly and the other representing 3D surfaces implicitly.…

cs.CV2023★ 3 cited

Improving Video Violence Recognition with Human Interaction Learning on 3D Skeleton Point Clouds

Yukun Su, Guosheng Lin, Qingyao Wu

Deep learning has proved to be very effective in video action recognition. Video violence recognition attempts to learn the human multi-dynamic behaviours in more complex scenarios…

cs.CV2023★ 1 cited

Unlimited Knowledge Distillation for Action Recognition in the Dark

Ruibing Jin, Guosheng Lin, Min Wu +4

Dark videos often lose essential information, which causes the knowledge learned by networks is not enough to accurately recognize actions. Existing knowledge assembling methods re…

cs.CV2023★ 5 cited

Self-Calibrated Cross Attention Network for Few-Shot Segmentation

Qianxiong Xu, Wenting Zhao, Guosheng Lin +1

The key to the success of few-shot segmentation (FSS) lies in how to effectively utilize support samples. Most solutions compress support foreground (FG) features into prototypes,…

cs.CV2023

Weakly Supervised 3D Instance Segmentation without Instance-level Annotations

Shichao Dong, Guosheng Lin

3D semantic scene understanding tasks have achieved great success with the emergence of deep learning, but often require a huge amount of manually annotated training data. To allev…