PeopleofSuperintelligence

Researcher

Qibin Hou

Also known as Andrew Hou, Qi-Bin Hou, 侯淇彬

Qibin Hou is a computer vision researcher whose network designs for image recognition, segmentation and generation include Coordinate Attention, VOLO, SegNeXt and StoryDiffusion. He completed a Ph.D. at Nankai University in 2019 under Ming-Ming Cheng, after presenting a saliency-detection method with short connections at CVPR 2017. A research fellowship at the National University of Singapore with Jiashi Feng and Shuicheng Yan ran from 2019 to 2021. In 2021, he coauthored VOLO, the first model above 87% top-1 accuracy on ImageNet-1K without extra training data, and in 2022 he received the first prize in natural science from China's Ministry of Education. He is an associate professor at the School of Computer Science at Nankai University.

Now at
Nankai University and Nankai International Advanced Research Institute (Shenzhen Futian)

Timeline

  1. 2017–2019

    Saliency work and a Nankai PhD

    With Ming-Ming Cheng and four other coauthors, he presents Deeply Supervised Salient Object Detection With Short Connections at CVPR 2017, adding short connections to the skip-layer structures of the HED architecture. He receives his Ph.D. from Nankai University in June 2019 under Cheng's supervision.

  2. August 2019–August 2021

    Research fellow at NUS

    From August 2019 to August 2021, he works as a research fellow at the National University of Singapore with Jiashi Feng and Shuicheng Yan.

  3. 2020–2022

    Two natural science prizes

    He receives a second prize in natural science from CAAI in 2020 and a first prize in natural science from China's Ministry of Education in 2022.

  4. 2021

    Coordinate Attention and VOLO

    His paper Coordinate Attention for Efficient Mobile Network Design, written with Daquan Zhou and Jiashi Feng, appears at CVPR 2021 and plugs into mobile networks such as MobileNetV2 and EfficientNet with almost no extra computation. In 2021, he also coauthors VOLO with Li Yuan, Zihang Jiang, Jiashi Feng and Shuicheng Yan; it reaches 87.1% top-1 accuracy on ImageNet-1K, the first model above 87% without extra training data.

  5. 2022

    SegNeXt and Conv2Former

    In 2022, he coauthors SegNeXt, a convolutional attention network for semantic segmentation that reaches 90.6% mIoU on the Pascal VOC 2012 test leaderboard with a tenth of the parameters of EfficientNet-L2 w/ NAS-FPN. As first author of Conv2Former, he builds a family of ConvNets on a convolutional modulation operation, and they outperform Swin Transformer and ConvNeXt on ImageNet classification, COCO detection and ADE20k segmentation.

  6. 2024

    StoryDiffusion for consistent images

    In 2024, he coauthors StoryDiffusion with Yupeng Zhou, Daquan Zhou, Ming-Ming Cheng and Jiashi Feng. Its Consistent Self-Attention keeps subjects consistent across images from pretrained diffusion-based text-to-image models in a zero-shot manner, and a Semantic Motion Predictor extends the images to long videos.

  7. As of October 2026

    Associate professor at Nankai

    He is an associate professor at the School of Computer Science at Nankai University in Tianjin, and he is also with the Nankai International Advanced Research Institute (Shenzhen Futian). His research builds AI models that help agents see and understand the complex world.

Career

  1. NowNankai UniversityAssociate Professor
  2. NowNankai International Advanced Research Institute (Shenzhen Futian)
  3. 2019–2021National University of SingaporeResearch Fellow

Education

  1. 2019Nankai UniversityPh.D.

From the biography.

  1. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes Nankai University. We estimate where the people shaping AI studied and where their careers led. Massachusetts Institute of Technology leads with 467 former students, including 291 recorded doctorates.
  2. The company share of AI researchers’ top papers was 31% in 2020–2024 and 8% in 1970–1974Includes Nankai University. We estimate where the people shaping AI worked when their most-cited papers appeared: the company share was 31% in 2020–2024 and 8% in 1970–1974, and Google led all organizations in 2020–2024.
  3. People shaping AI work at a median of 3 organizations over a career: 3 for university starters and institute and lab starters, versus 2 for company startersIncludes National University of Singapore. Across 6,853 people shaping AI with a dated work role, we estimate a median of 3 parent organizations over a career (mean 3.6), comparing role groups, starting sectors and starting decades from the 1950s to 2020–2026.
  4. The United States employs an estimated 48% of people shaping AIIncludes National University of Singapore. We estimate where the people shaping AI work today, how universities, companies and research institutes split across countries, and how country shares have changed since the 1960s.

Colleagues

People named in this biography, and people with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Qibin Hou yet. Send us a free-licensed photo.

  1. Qibin's Homepage - HVision @ Nankai houqb.github.io. Checked 22 October 2026.
  2. Deeply Supervised Salient Object Detection With Short Connections (CVPR 2017 Open Access Repository) openaccess.thecvf.com. Checked 22 October 2026.
  3. Awards - HVision @ Nankai houqb.github.io. Checked 22 October 2026.
  4. Coordinate Attention for Efficient Mobile Network Design (CVPR 2021 Open Access Repository) openaccess.thecvf.com. Checked 22 October 2026.
  5. VOLO: Vision Outlooker for Visual Recognition arxiv.org. Checked 22 October 2026.
  6. SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation arxiv.org. Checked 22 October 2026.
  7. Conv2Former: A Simple Transformer-Style ConvNet for Visual Recognition arxiv.org. Checked 22 October 2026.
  8. StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation arxiv.org. Checked 22 October 2026.
  9. Qibin (Andrew) Hou 侯淇彬 – 程明明个人主页 mmcheng.net. Checked 22 October 2026.