Picture for Weilin Huang

Weilin Huang

Mixer: Image to Multi-Modal Retrieval Learning for Industrial Application

May 06, 2023
Zida Cheng, Shuai Xiao, Zhonghua Zhai, Xiaoyi Zeng, Weilin Huang

Access Paper or Ask Questions

Dynamic MDETR: A Dynamic Multimodal Transformer Decoder for Visual Grounding

Sep 28, 2022
Fengyuan Shi, Ruopeng Gao, Weilin Huang, Limin Wang

Figure 1 for Dynamic MDETR: A Dynamic Multimodal Transformer Decoder for Visual Grounding

Figure 2 for Dynamic MDETR: A Dynamic Multimodal Transformer Decoder for Visual Grounding

Figure 3 for Dynamic MDETR: A Dynamic Multimodal Transformer Decoder for Visual Grounding

Figure 4 for Dynamic MDETR: A Dynamic Multimodal Transformer Decoder for Visual Grounding

* Technical report

Access Paper or Ask Questions

Cross-Architecture Self-supervised Video Representation Learning

May 26, 2022
Sheng Guo, Zihua Xiong, Yujie Zhong, Limin Wang, Xiaobo Guo, Bing Han, Weilin Huang

Figure 1 for Cross-Architecture Self-supervised Video Representation Learning

Figure 2 for Cross-Architecture Self-supervised Video Representation Learning

Figure 3 for Cross-Architecture Self-supervised Video Representation Learning

Figure 4 for Cross-Architecture Self-supervised Video Representation Learning

* Accepted to CVPR2022

Access Paper or Ask Questions

InsCLR: Improving Instance Retrieval with Self-Supervision

Dec 02, 2021
Zelu Deng, Yujie Zhong, Sheng Guo, Weilin Huang

Figure 1 for InsCLR: Improving Instance Retrieval with Self-Supervision

Figure 2 for InsCLR: Improving Instance Retrieval with Self-Supervision

Figure 3 for InsCLR: Improving Instance Retrieval with Self-Supervision

Figure 4 for InsCLR: Improving Instance Retrieval with Self-Supervision

* Accepted by AAAI 2022

Access Paper or Ask Questions

End-to-End Dense Video Grounding via Parallel Regression

Sep 23, 2021
Fengyuan Shi, Limin Wang, Weilin Huang

Figure 1 for End-to-End Dense Video Grounding via Parallel Regression

Figure 2 for End-to-End Dense Video Grounding via Parallel Regression

Figure 3 for End-to-End Dense Video Grounding via Parallel Regression

Figure 4 for End-to-End Dense Video Grounding via Parallel Regression

* Technical report

Access Paper or Ask Questions

TOOD: Task-aligned One-stage Object Detection

Aug 28, 2021
Chengjian Feng, Yujie Zhong, Yu Gao, Matthew R. Scott, Weilin Huang

Figure 1 for TOOD: Task-aligned One-stage Object Detection

Figure 2 for TOOD: Task-aligned One-stage Object Detection

Figure 3 for TOOD: Task-aligned One-stage Object Detection

Figure 4 for TOOD: Task-aligned One-stage Object Detection

* ICCV2021 Oral

Access Paper or Ask Questions