Qi-Hang Yu

Most-cited papers

TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation
Jieneng Chen, Yong-Yi Lu, Qi-Hang Yu, Xiang-De Luo +5 more
2021arXiv.org6,540 citations
Semantic Scholar
TransUNet: Rethinking the U-Net architecture design for medical image segmentation through the lens of transformers
Jieneng Chen, Jie-Ru Mei, Xianhang Li, Yong-Yi Lu +12 more
2024Medical Image Anal.1,502 citations Open access
Semantic Scholar
When Radiology Report Generation Meets Knowledge Graph
Yi-Xiao Zhang, Xiaosong Wang, Ziyue Xu, Qi-Hang Yu +2 more
2020AAAI Conference on Artificial Intelligence441 citations Open access
Semantic Scholar
An Image is Worth 32 Tokens for Reconstruction and Generation
Qi-Hang Yu, Mark Weber, Xue-Qing Deng, Xiaohui Shen +2 more
2024Neural Information Processing Systems341 citations
Semantic Scholar
Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP
Qi-Hang Yu, Ju He, Xue-Qing Deng, Xiao-Hui Shen +1 more
2023Neural Information Processing Systems295 citations Open access
Semantic Scholar
Recurrent Saliency Transformation Network: Incorporating Multi-stage Visual Cues for Small Organ Segmentation
Qi-Hang Yu, Ling-Xi Xie, Yan Wang, Yuyin Zhou +2 more
20172018 IEEE/CVF Conference on Computer Vision and Pattern Recognition234 citations Open access
Semantic Scholar
k-means Mask Transformer
Qi-Hang Yu, Huiyu Wang, Siyuan Qiao, Maxwell D. Collins +4 more
2022European Conference on Computer Vision175 citations Open access
Semantic Scholar
Mask Guided Matting via Progressive Refinement Network
Qi-Hang Yu, Jian-Ming Zhang, He Zhang, Yi-Lin Wang +4 more
2020Computer Vision and Pattern Recognition163 citations Open access
Semantic Scholar
PartImageNet: A Large, High-Quality Dataset of Parts
Ju He, Shuo Yang, Shaokang Yang, Adam Kortylewski +6 more
2021European Conference on Computer Vision155 citations Open access
Semantic Scholar
Randomized Autoregressive Visual Generation
Qi-Hang Yu, Ju He, Xue-Qing Deng, Xiaohui Shen +1 more
2024IEEE International Conference on Computer Vision135 citations Open access
Semantic Scholar
C2FNAS: Coarse-to-Fine Neural Architecture Search for 3D Medical Image Segmentation
Qi-Hang Yu, Dong Yang, Holger R. Roth, Yutong Bai +3 more
2019Computer Vision and Pattern Recognition129 citations Open access
Semantic Scholar
Shape-Texture Debiased Neural Network Training
Yingwei Li, Qi-Hang Yu, Mingxing Tan, Jie-Ru Mei +4 more
2020International Conference on Learning Representations128 citations
Semantic Scholar
CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation
Qi-Hang Yu, Huiyu Wang, Dahun Kim, Siyuan Qiao +5 more
2022Computer Vision and Pattern Recognition115 citations Open access
Semantic Scholar
MaskBit: Embedding-free Image Generation via Bit Tokens
Mark Weber, Li-Jun Yu, Qi-Hang Yu, Xue-Qing Deng +3 more
2024Trans. Mach. Learn. Res.102 citations
Semantic Scholar
3D TransUNet: Advancing Medical Image Segmentation through Vision Transformers
Jieneng Chen, Jie-Ru Mei, Xianhang Li, Yong-Yi Lu +11 more
2023arXiv.org96 citations Open access
Semantic Scholar
Glance-and-Gaze Vision Transformer
Qi-Hang Yu, Yingda Xia, Yutong Bai, Yong-Yi Lu +2 more
2021Neural Information Processing Systems92 citations
Semantic Scholar
Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generation
Su-Cheng Ren, Qi-Hang Yu, Ju He, Xiaohui Shen +2 more
2025IEEE International Conference on Computer Vision88 citations Open access
Semantic Scholar
MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models
Chenglin Yang, Siyuan Qiao, Qi-Hang Yu, Xiao-Ding Yuan +4 more
2022International Conference on Learning Representations87 citations Open access
Semantic Scholar
FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching
Su-Cheng Ren, Qi-Hang Yu, Ju He, Xiaohui Shen +2 more
2024arXiv.org86 citations
Semantic Scholar
Application of Deep Learning to Pancreatic Cancer Detection: Lessons Learned From Our Initial Experience.
L. Chu, Seyoun Park, S. Kawamoto, Yan Wang +17 more
2019Journal of the American College of Radiology77 citations
Semantic Scholar
Recurrent Saliency Transformation Network for Tiny Target Segmentation in Abdominal CT Scans
Ling-Xi Xie, Qi-Hang Yu, Yuyin Zhou, Yan Wang +2 more
2020IEEE Transactions on Medical Imaging74 citations
Semantic Scholar
ViTamin: Designing Scalable Vision Models in the Vision-Language Era
Jie-Neng Chen, Qi-Hang Yu, Xiaohui Shen, Alan L. Yuille +1 more
2024Computer Vision and Pattern Recognition70 citations Open access
Semantic Scholar
DeepLab2: A TensorFlow Library for Deep Labeling
Mark Weber, Huiyu Wang, Siyuan Qiao, Jun Xie +11 more
2021arXiv.org65 citations
Semantic Scholar
Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens
Dongwon Kim, Ju He, Qi-Hang Yu, Chenglin Yang +3 more
2025IEEE International Conference on Computer Vision58 citations Open access
Semantic Scholar
TubeFormer-DeepLab: Video Mask Transformer
Dahun Kim, Jun Xie, Huiyu Wang, Siyuan Qiao +5 more
2022Computer Vision and Pattern Recognition56 citations Open access
Semantic Scholar
Neural Architecture Search for Lightweight Non-Local Networks
Yingwei Li, Xiao-Jie Jin, Jie-Ru Mei, Xiaochen Lian +6 more
2020Computer Vision and Pattern Recognition55 citations Open access
Semantic Scholar
The FELIX Project: Deep Networks To Detect Pancreatic Neoplasms
Yingda Xia, Qi-Hang Yu, L. Chu, S. Kawamoto +24 more
2022medRxiv49 citations Open access
Semantic Scholar
Can Temporal Information Help with Contrastive Self-Supervised Learning?
Yutong Bai, Haoqi Fan, Ishan Misra, Ganesh Venkatesh +5 more
2020arXiv.org41 citations
Semantic Scholar
Alleviating Distortion in Image Generation via Multi-Resolution Diffusion Models
Qihao Liu, Zhan-Peng Zeng, Ju He, Qi-Hang Yu +2 more
2024Neural Information Processing Systems39 citations
Semantic Scholar
FlowTok: Flowing Seamlessly Across Text and Image Tokens
Ju He, Qi-Hang Yu, Qihao Liu, Liang-Chieh Chen
2025IEEE International Conference on Computer Vision37 citations Open access
Semantic Scholar
COCONut: Modernizing COCO Segmentation
Xue-Qing Deng, Qi-Hang Yu, Peng Wang, Xiaohui Shen +1 more
2024Computer Vision and Pattern Recognition34 citations Open access
Semantic Scholar
Thickened 2D Networks for Efficient 3D Medical Image Segmentation.
Qi-Hang Yu, Yingda Xia, Ling-Xi Xie, E. Fishman +1 more
201934 citations
Semantic Scholar
Video-kMaX: A Simple Unified Approach for Online and Near-Online Video Panoptic Segmentation
Inkyu Shin, Dahun Kim, Qi-Hang Yu, Jun Xie +5 more
2023IEEE Workshop/Winter Conference on Applications of Computer Vision29 citations Open access
Semantic Scholar
CancerUniT: Towards a Single Unified Model for Effective Detection, Segmentation, and Diagnosis of Eight Major Cancers Using a Large Collection of CT Scans
Jieneng Chen, Yingda Xia, Jiawen Yao, K. Yan +21 more
2023IEEE International Conference on Computer Vision23 citations Open access
Semantic Scholar
ReMaX: Relaxing for Better Training on Efficient Panoptic Segmentation
Shuyang Sun, Weijun Wang, Qi-Hang Yu, Andrew G. Howard +2 more
2023Neural Information Processing Systems23 citations Open access
Semantic Scholar
kMaX-DeepLab: k-means Mask Transformer
Qi-Hang Yu, Huiyu Wang, Siyuan Qiao, Maxwell D. Collins +4 more
202223 citations
Semantic Scholar
Detecting Pancreatic Ductal Adenocarcinoma in Multi-phase CT Scans via Alignment Ensemble
Yingda Xia, Qi-Hang Yu, Wei Shen, Yuyin Zhou +2 more
2020International Conference on Medical Image Computing and Computer-Assisted Intervention23 citations Open access
Semantic Scholar
Compositor: Bottom-Up Clustering and Compositing for Robust Part and Object Segmentation
Ju He, Jieneng Chen, Ming-Xian Lin, Qi-Hang Yu +1 more
2023Computer Vision and Pattern Recognition20 citations Open access
Semantic Scholar
Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers
Su-Cheng Ren, Qi-Hang Yu, Ju He, Alan L. Yuille +1 more
2025arXiv.org17 citations
Semantic Scholar
COCONut-PanCap: Joint Panoptic Segmentation and Grounded Captions for Fine-Grained Understanding and Generation
Xue-Qing Deng, Linjie Yang, Qi-Hang Yu, Ali Athar +4 more
2025Neural Information Processing Systems15 citations
Semantic Scholar
A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens
Tommie Kerssies, G. Berton, Ju He, Qi-Hang Yu +4 more
2026arXiv.org14 citations
Semantic Scholar
Autoregressive Image Generation with Masked Bit Modeling
Qi-Hang Yu, Qihao Liu, Ju He, Xinyang Zhang +3 more
2026arXiv.org12 citations
Semantic Scholar
A Study of Autoregressive Decoders for Multi-Tasking in Computer Vision
Lucas Beyer, Bo Wan, Gagan Madan, Filip Pavetic +8 more
2023arXiv.org12 citations Open access
Semantic Scholar
Thickened 2D Networks for 3D Medical Image Segmentation
Qi-Hang Yu, Yingda Xia, Ling-Xi Xie, E. Fishman +1 more
2019arXiv.org9 citations
Semantic Scholar
Towards Open-Ended Visual Recognition with Large Language Models
Qi-Hang Yu, Xiaohui Shen, Liang-Chieh Chen
2024European Conference on Computer Vision8 citations
Semantic Scholar
Towards Open-Ended Visual Recognition with Large Language Model
Qi-Hang Yu, Xiaohui Shen, Liang-Chieh Chen
2023arXiv.org8 citations
Semantic Scholar
Frequency-Aware Flow Matching for High-Quality Image Generation
Su-Cheng Ren, Qi-Hang Yu, Junnan He, Xiaohui Shen +2 more
2026arXiv.org6 citations
Semantic Scholar
ReVision: Refining Video Diffusion with Explicit 3D Motion Modeling
Qihao Liu, Ju He, Qi-Hang Yu, Liang-Chieh Chen +1 more
2025Trans. Mach. Learn. Res.5 citations
Semantic Scholar
Towards a Single Unified Model for Effective Detection, Segmentation, and Diagnosis of Eight Major Cancers Using a Large Collection of CT Scans
Jie-Neng Chen, Ying-Da Xia, Jiawen Yao, Ke Yan +21 more
2023arXiv.org5 citations Open access
Semantic Scholar
Enhancing Temporal Consistency in Video Editing by Reconstructing Videos with 3D Gaussian Splatting
Inkyu Shin, Qi-Hang Yu, Xiaohui Shen, In-So Kweon +2 more
2024Trans. Mach. Learn. Res.4 citations
Semantic Scholar