Alert button
Picture for Bo Ren

Bo Ren

Alert button

On decoder-only architecture for speech-to-text and large language model integration

Jul 14, 2023
Jian Wu, Yashesh Gaur, Zhuo Chen, Long Zhou, Yimeng Zhu, Tianrui Wang, Jinyu Li, Shujie Liu, Bo Ren, Linquan Liu, Yu Wu

Figure 1 for On decoder-only architecture for speech-to-text and large language model integration
Figure 2 for On decoder-only architecture for speech-to-text and large language model integration
Figure 3 for On decoder-only architecture for speech-to-text and large language model integration
Viaarxiv icon

Visual Information Extraction in the Wild: Practical Dataset and End-to-end Solution

May 12, 2023
Jianfeng Kuang, Wei Hua, Dingkang Liang, Mingkun Yang, Deqiang Jiang, Bo Ren, Yu Zhou, Xiang Bai

Figure 1 for Visual Information Extraction in the Wild: Practical Dataset and End-to-end Solution
Figure 2 for Visual Information Extraction in the Wild: Practical Dataset and End-to-end Solution
Figure 3 for Visual Information Extraction in the Wild: Practical Dataset and End-to-end Solution
Figure 4 for Visual Information Extraction in the Wild: Practical Dataset and End-to-end Solution
Viaarxiv icon

Multi-Space Neural Radiance Fields

May 07, 2023
Ze-Xin Yin, Jiaxiong Qiu, Ming-Ming Cheng, Bo Ren

Figure 1 for Multi-Space Neural Radiance Fields
Figure 2 for Multi-Space Neural Radiance Fields
Figure 3 for Multi-Space Neural Radiance Fields
Figure 4 for Multi-Space Neural Radiance Fields
Viaarxiv icon

Looking Through the Glass: Neural Surface Reconstruction Against High Specular Reflections

Apr 18, 2023
Jiaxiong Qiu, Peng-Tao Jiang, Yifan Zhu, Ze-Xin Yin, Ming-Ming Cheng, Bo Ren

Figure 1 for Looking Through the Glass: Neural Surface Reconstruction Against High Specular Reflections
Figure 2 for Looking Through the Glass: Neural Surface Reconstruction Against High Specular Reflections
Figure 3 for Looking Through the Glass: Neural Surface Reconstruction Against High Specular Reflections
Figure 4 for Looking Through the Glass: Neural Surface Reconstruction Against High Specular Reflections
Viaarxiv icon

Collaborative Noisy Label Cleaner: Learning Scene-aware Trailers for Multi-modal Highlight Detection in Movies

Mar 26, 2023
Bei Gan, Xiujun Shu, Ruizhi Qiao, Haoqian Wu, Keyu Chen, Hanjun Li, Bo Ren

Figure 1 for Collaborative Noisy Label Cleaner: Learning Scene-aware Trailers for Multi-modal Highlight Detection in Movies
Figure 2 for Collaborative Noisy Label Cleaner: Learning Scene-aware Trailers for Multi-modal Highlight Detection in Movies
Figure 3 for Collaborative Noisy Label Cleaner: Learning Scene-aware Trailers for Multi-modal Highlight Detection in Movies
Figure 4 for Collaborative Noisy Label Cleaner: Learning Scene-aware Trailers for Multi-modal Highlight Detection in Movies
Viaarxiv icon

Turning a CLIP Model into a Scene Text Detector

Mar 01, 2023
Wenwen Yu, Yuliang Liu, Wei Hua, Deqiang Jiang, Bo Ren, Xiang Bai

Figure 1 for Turning a CLIP Model into a Scene Text Detector
Figure 2 for Turning a CLIP Model into a Scene Text Detector
Figure 3 for Turning a CLIP Model into a Scene Text Detector
Figure 4 for Turning a CLIP Model into a Scene Text Detector
Viaarxiv icon

SLAN: Self-Locator Aided Network for Cross-Modal Understanding

Dec 08, 2022
Jiang-Tian Zhai, Qi Zhang, Tong Wu, Xing-Yu Chen, Jiang-Jiang Liu, Bo Ren, Ming-Ming Cheng

Figure 1 for SLAN: Self-Locator Aided Network for Cross-Modal Understanding
Figure 2 for SLAN: Self-Locator Aided Network for Cross-Modal Understanding
Figure 3 for SLAN: Self-Locator Aided Network for Cross-Modal Understanding
Figure 4 for SLAN: Self-Locator Aided Network for Cross-Modal Understanding
Viaarxiv icon

FoPro: Few-Shot Guided Robust Webly-Supervised Prototypical Learning

Dec 01, 2022
Yulei Qin, Xingyu Chen, Chao Chen, Yunhang Shen, Bo Ren, Yun Gu, Jie Yang, Chunhua Shen

Figure 1 for FoPro: Few-Shot Guided Robust Webly-Supervised Prototypical Learning
Figure 2 for FoPro: Few-Shot Guided Robust Webly-Supervised Prototypical Learning
Figure 3 for FoPro: Few-Shot Guided Robust Webly-Supervised Prototypical Learning
Figure 4 for FoPro: Few-Shot Guided Robust Webly-Supervised Prototypical Learning
Viaarxiv icon