Search Results for author: Liguang Zhou

Found 7 papers, 3 papers with code

Context-aware Mixture-of-Experts for Unbiased Scene Graph Generation

no code implementations15 Aug 2022 Liguang Zhou, Yuhongze Zhou, Tin Lun Lam, Yangsheng Xu

These methods often design the sophisticated context-encoder to extract the inherent relevance of scene context w. r. t the intrinsic predicates and complicated networks to improve the learning capabilities of the network model for highly imbalanced data distributions.

Graph Generation object-detection +2

View Blind-spot as Inpainting: Self-Supervised Denoising with Mask Guided Residual Convolution

no code implementations10 Sep 2021 Yuhongze Zhou, Liguang Zhou, Tin Lun Lam, Yangsheng Xu

Our MGRConv can be regarded as soft partial convolution and find a trade-off among partial convolution, learnable attention maps, and gated convolution.

Denoising

BORM: Bayesian Object Relation Model for Indoor Scene Recognition

1 code implementation1 Aug 2021 Liguang Zhou, Jun Cen, Xingchao Wang, Zhenglong Sun, Tin Lun Lam, Yangsheng Xu

First, we utilize an improved object model (IOM) as a baseline that enriches the object knowledge by introducing a scene parsing algorithm pretrained on the ADE20K dataset with rich object categories related to the indoor scene.

Scene Recognition

Object-to-Scene: Learning to Transfer Object Knowledge to Indoor Scene Recognition

1 code implementation1 Aug 2021 Bo Miao, Liguang Zhou, Ajmal Mian, Tin Lun Lam, Yangsheng Xu

The final results in this work show that OTS successfully extracts object features and learns object relations from the segmentation network.

Scene Recognition

Semantic-guided Automatic Natural Image Matting with Trimap Generation Network and Light-weight Non-local Attention

no code implementations31 Mar 2021 Yuhongze Zhou, Liguang Zhou, Tin Lun Lam, Yangsheng Xu

This paper presents a semantic-guided automatic natural image matting pipeline with Trimap Generation Network and light-weight non-local attention, which does not need trimap and background as input.

Image Matting

Cannot find the paper you are looking for? You can Submit a new open access paper.