Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

PanopticPartFormer++: A Unified and Decoupled View for Panoptic Part Segmentation


Jan 03, 2023
Xiangtai Li, Shilin Xu, Yibo Yang, Haobo Yuan, Guangliang Cheng, Yunhai Tong, Zhouchen Lin, Dacheng Tao

Add code

* Extension of PanopticPartFormer (ECCV 2022). Code: https://github.com/lxtGH/Panoptic-PartFormer. arXiv admin note: substantial text overlap with arXiv:2204.04655 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Betrayed by Captions: Joint Caption Grounding and Generation for Open Vocabulary Instance Segmentation


Jan 02, 2023
Jianzong Wu, Xiangtai Li, Henghui Ding, Xia Li, Guangliang Cheng, Yunhai Tong, Chen Change Loy

Add code

* Technical Report 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Label-Efficient Interactive Time-Series Anomaly Detection


Dec 30, 2022
Hong Guo, Yujing Wang, Jieyu Zhang, Zhengjie Lin, Yunhai Tong, Lei Yang, Luoxing Xiong, Congrui Huang

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Convolution-enhanced Evolving Attention Networks


Dec 16, 2022
Yujing Wang, Yaming Yang, Zhuo Li, Jiangang Bai, Mingliang Zhang, Xiangtai Li, Jing Yu, Ce Zhang, Gao Huang, Yunhai Tong

Add code

* Extension of the previous work (arXiv:2102.12895). arXiv admin note: text overlap with arXiv:2102.12895 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Towards Robust Referring Image Segmentation


Sep 20, 2022
Jianzong Wu, Xiangtai Li, Xia Li, Henghui Ding, Yunhai Tong, Dacheng Tao

Add code

* technical report 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

SFNet: Faster, Accurate, and Domain Agnostic Semantic Segmentation via Semantic Flow


Jul 10, 2022
Xiangtai Li, Jiangning Zhang, Yibo Yang, Guangliang Cheng, Kuiyuan Yang, Yunhai Tong, Dacheng Tao

Add code

* Extension of Previous work arXiv:2002.10120 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Multi-Task Learning with Multi-query Transformer for Dense Prediction


May 31, 2022
Yangyang Xu, Xiangtai Li, Haobo Yuan, Yibo Yang, Jing Zhang, Yunhai Tong, Lefei Zhang, Dacheng Tao

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentation


Apr 10, 2022
Xiangtai Li, Wenwei Zhang, Jiangmiao Pang, Kai Chen, Guangliang Cheng, Yunhai Tong, Chen Change Loy

Add code

* accepted by CVPR-2022(oral) 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Panoptic-PartFormer: Learning a Unified Model for Panoptic Part Segmentation


Apr 10, 2022
Xiangtai Li, Shilin Xu, Yibo Yang. Guangliang Cheng, Yunhai Tong, Dacheng Tao

Add code

* technical report 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Fashionformer: A simple, Effective and Unified Baseline for Human Fashion Segmentation and Recognition


Apr 10, 2022
Shilin Xu, Xiangtai Li, Jingbo Wang, Guangliang Cheng, Yunhai Tong, Dacheng Tao

Add code

* technical report 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
3
4
5
>>