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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox
Picture for Bei Liu

Bei Liu
Alert button

M3P: Learning Universal Representations via Multitask Multilingual Multimodal Pre-training


Jun 04, 2020
Haoyang Huang, Lin Su, Di Qi, Nan Duan, Edward Cui, Taroon Bharti, Lei Zhang, Lijuan Wang, Jianfeng Gao, Bei Liu, Jianlong Fu, Dongdong Zhang, Xin Liu, Ming Zhou

Add code
Alert button

Figure 1 for M3P: Learning Universal Representations via Multitask Multilingual Multimodal Pre-training
Figure 2 for M3P: Learning Universal Representations via Multitask Multilingual Multimodal Pre-training
Figure 3 for M3P: Learning Universal Representations via Multitask Multilingual Multimodal Pre-training
Figure 4 for M3P: Learning Universal Representations via Multitask Multilingual Multimodal Pre-training
* 10 pages,2 figures 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Transformers


Apr 02, 2020
Zhicheng Huang, Zhaoyang Zeng, Bei Liu, Dongmei Fu, Jianlong Fu

Add code
Alert button

Figure 1 for Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Transformers
Figure 2 for Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Transformers
Figure 3 for Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Transformers
Figure 4 for Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Transformers

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Neural Storyboard Artist: Visualizing Stories with Coherent Image Sequences


Nov 24, 2019
Shizhe Chen, Bei Liu, Jianlong Fu, Ruihua Song, Qin Jin, Pingping Lin, Xiaoyu Qi, Chunting Wang, Jin Zhou

Add code
Alert button

Figure 1 for Neural Storyboard Artist: Visualizing Stories with Coherent Image Sequences
Figure 2 for Neural Storyboard Artist: Visualizing Stories with Coherent Image Sequences
Figure 3 for Neural Storyboard Artist: Visualizing Stories with Coherent Image Sequences
Figure 4 for Neural Storyboard Artist: Visualizing Stories with Coherent Image Sequences
* ACM MM 2019 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Learning Rich Image Region Representation for Visual Question Answering


Oct 29, 2019
Bei Liu, Zhicheng Huang, Zhaoyang Zeng, Zheyu Chen, Jianlong Fu

Add code
Alert button

Figure 1 for Learning Rich Image Region Representation for Visual Question Answering
* Rank 2 in VQA Challenge 2019 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Gastroscopic Panoramic View: Application to Automatic Polyps Detection under Gastroscopy


Oct 19, 2019
Shi Chenfei, Yan Xue, Chuan Jiang, Hui Tian, Bei Liu

Add code
Alert button

Figure 1 for Gastroscopic Panoramic View: Application to Automatic Polyps Detection under Gastroscopy
Figure 2 for Gastroscopic Panoramic View: Application to Automatic Polyps Detection under Gastroscopy
Figure 3 for Gastroscopic Panoramic View: Application to Automatic Polyps Detection under Gastroscopy
Figure 4 for Gastroscopic Panoramic View: Application to Automatic Polyps Detection under Gastroscopy

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

WSOD^2: Learning Bottom-up and Top-down Objectness Distillation for Weakly-supervised Object Detection


Sep 11, 2019
Zhaoyang Zeng, Bei Liu, Jianlong Fu, Hongyang Chao, Lei Zhang

Add code
Alert button

Figure 1 for WSOD^2: Learning Bottom-up and Top-down Objectness Distillation for Weakly-supervised Object Detection
Figure 2 for WSOD^2: Learning Bottom-up and Top-down Objectness Distillation for Weakly-supervised Object Detection
Figure 3 for WSOD^2: Learning Bottom-up and Top-down Objectness Distillation for Weakly-supervised Object Detection
Figure 4 for WSOD^2: Learning Bottom-up and Top-down Objectness Distillation for Weakly-supervised Object Detection
* Accepted as a ICCV 2019 poster paper 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Activitynet 2019 Task 3: Exploring Contexts for Dense Captioning Events in Videos


Jul 11, 2019
Shizhe Chen, Yuqing Song, Yida Zhao, Qin Jin, Zhaoyang Zeng, Bei Liu, Jianlong Fu, Alexander Hauptmann

Add code
Alert button

Figure 1 for Activitynet 2019 Task 3: Exploring Contexts for Dense Captioning Events in Videos
Figure 2 for Activitynet 2019 Task 3: Exploring Contexts for Dense Captioning Events in Videos
Figure 3 for Activitynet 2019 Task 3: Exploring Contexts for Dense Captioning Events in Videos
Figure 4 for Activitynet 2019 Task 3: Exploring Contexts for Dense Captioning Events in Videos
* Winner solution in CVPR 2019 Activitynet Dense Video Captioning challenge 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Beyond Narrative Description: Generating Poetry from Images by Multi-Adversarial Training


Oct 10, 2018
Bei Liu, Jianlong Fu, Makoto P. Kato, Masatoshi Yoshikawa

Add code
Alert button

Figure 1 for Beyond Narrative Description: Generating Poetry from Images by Multi-Adversarial Training
Figure 2 for Beyond Narrative Description: Generating Poetry from Images by Multi-Adversarial Training
Figure 3 for Beyond Narrative Description: Generating Poetry from Images by Multi-Adversarial Training
Figure 4 for Beyond Narrative Description: Generating Poetry from Images by Multi-Adversarial Training

   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