Qibin Hou的主页

Qibin Hou received his Ph.D. degree from Nankai University in 06/2019 under the supervision of Prof. Ming-Ming Cheng. From 08/2019 to 08/2021, I spent two wonderful years working with Dr. Jiashi Feng and Dr. Shuicheng Yan as a research fellow at National University of Singapore. Now, I am an associate professor at School of Computer Science, Nankai University, Tianjin, China. I am also with Nankai International Advanced Research Institute (Shenzhen Futian).

Research Interests：

My research covers a range of Computer Vision and Deep Learning. To be specific, my research concentrates on building AI models to help agents better see and understand the complex world.

Specific directions: Vision Foundation Models Visual Scene Understanding Visual Content Generation

See my recent publications for more details.

For prospective students

If you are interested in the research topics in my group, welcome to drop an email. Note that before contacting me, you are supposed to have read [the enrollment information] already.

News

Three papers accepted by NeurIPS’2024
Four papers accepted by TPAMI’2024
I am among the list of Highly Cited Chinese Researchers of 2023
Six papers accepted by CVPR’24 and ECCV’24
Three papers accepted by ICLR’24 and ICML’24
Three papers accepted by ICCV’23 and CVPR’23
Top 2% of Scientists on Stanford List for multiple times
Three papers published in TPAMI’2023

Group

Ph.D. Students

Zhaohui Zheng (Co-supervise with Ming-Ming Cheng, 2021-)
Jiabao Wang (Co-supervise with Ming-Ming Cheng, 2022-)
Hao Shao (2022-)
Xuying Zhang (Co-supervise with Ming-Ming Cheng, 2022-)
Bowen Yin (2023-)
Boyuan Sun (Co-supervise with Prof. Xiuli Shao, 2023-)
Yusong Hu (2023-)
Yunheng Li (Co-supervise with Ming-Ming Cheng, 2023-)
Yuming Chen (Co-supervise with Prof. Ming-Ming Cheng, 2024-)
Yupeng Zhou (2024-)

Master Students

Yuqi Yang (Co-supervise with Prof. Ming-Ming Cheng, 2022-)
Xinbin Yuan (2023-)

Preprint

“*” means authors contributed equally and “#” means corresponding author.

Yolo-ms: rethinking multi-scale representation learning for real-time object detection
_{Yuming Chen, Xinbin Yuan, Ruiqi Wu, Jiabao Wang, Qibin Hou#, Ming-Ming Cheng
Arxiv, 2023
[Arxiv] [Code]}

Selected Journal Publications (Google Scholar)

Conv2former: A simple transformer-style convnet for visual recognition
_{Qibin Hou, Cheng-Ze Lu, Ming-Ming Cheng#, Jiashi Feng
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024
[Arxiv] [Code]}

Camoformer: Masked separable attention for camouflaged object detection
_{Bowen Yin*, Xuying Zhang*, Deng-Ping Fan, Shaohui Jiao, Ming-Ming Cheng, Luc Van Gool, Qibin Hou#
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024
[Arxiv] [Code]}

Zone evaluation: Revealing spatial bias in object detection
_{Zhaohui Zheng, Yuming Chen, Qibin Hou#, Xiang Li, Ping Wang, Ming-Ming Cheng
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024
[Arxiv] [Code] [知乎]}

Vision permutator: A permutable mlp-like architecture for visual recognition
_{Qibin Hou, Zihang Jiang, Li Yuan, Ming-Ming Cheng, Shuicheng Yan, Jiashi Feng
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023
[Arxiv] [Code]}

Volo: Vision outlooker for visual recognition
_{Li Yuan*, Qibin Hou*, Zihang Jiang*, Jiashi Feng, Shuicheng Yan
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023
[Arxiv] [Code]}

Localization distillation for object detection
_{Zhaohui Zheng, Rongguang Ye, Qibin Hou#, Dongwei Ren, Ping Wang, Wangmeng Zuo, Ming-Ming Cheng
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023
[Arxiv] [Code]}

Deeply Supervised Salient Object Detection with Short Connections
_{Qibin Hou, Ming-Ming Cheng, Xiaowei Hu, Ali Borji, Zhuowen Tu, Philip Torr
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2019
[Arxiv] [Code]}

Selected Conference Publications (Google Scholar)

StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation
_{Yupeng Zhou, Daquan Zhou#, Ming-Ming Cheng, Jiashi Feng, Qibin Hou#
Neural Information Processing Systems (NeurIPS), 2024

[Arxiv] [Project] [Code]}

OPUS: Occupancy Prediction Using a Sparse Set
_{Jiabao Wang*, Zhaojiang Liu*, Qiang Meng, Liujiang Yan, Ke Wang, Jie Yang, Wei Liu, Qibin Hou#, Ming-Ming Cheng
Neural Information Processing Systems (NeurIPS), 2024
[Arxiv] [Code]}

Towards Stable 3D Object Detection
_{Jiabao Wang*, Qiang Meng*, Guochao Liu, Liujiang Yan, Ke Wang, Ming-Ming Cheng, Qibin Hou#
European Conference on Computer Vision (ECCV), 2024
[Arxiv] [Code]}

Cascade-CLIP: Cascaded Vision-Language Embeddings Alignment for Zero-Shot Semantic Segmentation
_{Yunheng Li, ZhongYu Li, Quansheng Zeng, Qibin Hou#, Ming-Ming Cheng
International Conference on Machine Learning (ICML), 2024
[Arxiv] [Code]}

CrossKD: Cross-Head Knowledge Distillation for Dense Object Detection
_{Jiabao Wang*, Yuming Chen*, Zhaohui Zheng, Xiang Li, Ming-Ming Cheng, Qibin Hou#
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024
[Arxiv] [Code]}

Dformer: Rethinking rgbd representation learning for semantic segmentation
_{Bowen Yin, Xuying Zhang, Zhongyu Li, Li Liu, Ming-Ming Cheng, Qibin Hou#
International Conference on Learning Representations (ICLR), 2024
[Arxiv] [Code]}

SRFormer: Permuted Self-Attention for Single Image Super-Resolution
_{Yupeng Zhou, Zhen Li, Chun-Le Guo, Song Bai, Ming-Ming Cheng, Qibin Hou#
IEEE International Conference on Computer Vision (ICCV), 2023

[Arxiv] [Code]}

Coordinate attention for efficient mobile network design
_{Qibin Hou, Daquan Zhou, Jiashi Feng
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021

[Arxiv] [Code]}

Strip Pooling: Rethinking Spatial Pooling for Scene Parsing
_{Qibin Hou, Li Zhang, Ming-Ming Cheng, Jiashi Feng
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020
[Arxiv] [Code]}

A Simple Pooling-Based Design for Real-Time Salient Object Detection
_{Jiang-Jiang Liu*, Qibin Hou*, Ming-Ming Cheng, Jiashi Feng, Jianmin Jiang
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019
[Arxiv] [Code]}

Academic Services

VALSE 2022 Expo Chair
VALSE 2023 Expo Chair
Reviewers for TPAMI/TIP/CVPR/ICCV/NeurIPS/ICML/ICLR etc.

Honors and Awards

First prize in natural science, Ministry of Education, 2022.
Second prize in nature science, CAAI, 2020.

Qibin Hou (侯淇彬)

Research Interests：

For prospective students

News

Group

Ph.D. Students

Master Students

Preprint

“*” means authors contributed equally and “#” means corresponding author.

Yolo-ms: rethinking multi-scale representation learning for real-time object detection

Selected Journal Publications (Google Scholar)

Conv2former: A simple transformer-style convnet for visual recognition

Camoformer: Masked separable attention for camouflaged object detection

Zone evaluation: Revealing spatial bias in object detection

Vision permutator: A permutable mlp-like architecture for visual recognition

Volo: Vision outlooker for visual recognition

Localization distillation for object detection

Deeply Supervised Salient Object Detection with Short Connections

Selected Conference Publications (Google Scholar)

StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation

OPUS: Occupancy Prediction Using a Sparse Set

Towards Stable 3D Object Detection

Cascade-CLIP: Cascaded Vision-Language Embeddings Alignment for Zero-Shot Semantic Segmentation

CrossKD: Cross-Head Knowledge Distillation for Dense Object Detection

Dformer: Rethinking rgbd representation learning for semantic segmentation

SRFormer: Permuted Self-Attention for Single Image Super-Resolution

Coordinate attention for efficient mobile network design

Strip Pooling: Rethinking Spatial Pooling for Scene Parsing

A Simple Pooling-Based Design for Real-Time Salient Object Detection

Academic Services

Honors and Awards