Every reference with a DOI in the deposited reference list resolved to a known
work in Crossref or DataCite at the dated check, and none carried a retraction,
withdrawal, or removal notice.
The 43 references without a DOI — listed, not checked
no DOI — not checkedDeep residual learning for image recognition
no DOI — not checkedSwin transformer: Hierarchical vision transformer using shifted windows
no DOI — not checkedref3
no DOI — not checkedUnified perceptual parsing for scene understanding
no DOI — not checkedFeature pyramid networks for object detection
no DOI — not checkedPath aggregation network for instance segmentation
no DOI — not checkedLearning scalable feature pyramid architecture for object detection
no DOI — not checkedEfficientdet: Scalable and efficient object detection
no DOI — not checkedA convnet for the 2020s
no DOI — not checkedSpinenet: Learning scale-permuted backbone for recognition and localization
no DOI — not checkedGiraffedet: A heavy-neck paradigm for object detection
no DOI — not checkedNeural architecture search with reinforcement learning
no DOI — not checkedStacked hourglass networks for human pose estimation
no DOI — not checkedU-net: Convolutional networks for biomedical image segmentation
no DOI — not checkedEncoder-decoder with atrous separable convolution for semantic image segmentation
no DOI — not checkedRASNet: Renal automatic segmentation using an improved U-Net with multi-scale perception and attention unit
no DOI — not checkedU2-net: Going deeper with nested u-structure for salient object detection
no DOI — not checked3D medical image segmentation using parallel transformers
no DOI — not checkedReversible column networks
no DOI — not checkedref21
no DOI — not checkedref22
no DOI — not checkedAdding conditional control to text-to-image diffusion models
no DOI — not checkedImageNet: A large-scale hierarchical image database
no DOI — not checkedMicrosoft COCO: Common objects in context
no DOI — not checkedFocal loss for dense object detection
no DOI — not checkedref27
no DOI — not checkedSimple copy-paste is a strong data augmentation method for instance segmentation
no DOI — not checkedDeformable {detr}: Deformable transformers for end-to-end object detection
no DOI — not checkedCascade r-cnn: Delving into high quality object detection
no DOI — not checkedDetectors: Detecting ob-jects with recursive feature pyramid and switchable atrous convolution
no DOI — not checkedFocal modulation networks
no DOI — not checkedInternimage: Exploring large-scale vision foundation models with deformable convolutions
no DOI — not checkedCbnet: A novel composite backbone network architecture for object detection
no DOI — not checkedMore convnets in the 2020s: Scaling up kernels beyond 51x51 using sparsity
no DOI — not checkedFocal self-attention for local-global interactions in vision transformers
no DOI — not checkedScene parsing through ade20k dataset
no DOI — not checkedref38
no DOI — not checkedCswin transformer: A general vision transformer backbone with cross-shaped windows
no DOI — not checkedHe is a Ph.D. student at Tsinghua University, China, from 2019 to now. His current interests primarily lie in deep learning and computer vision, especially object detection and image segmentation
no DOI — not checkedref41
no DOI — not checkedHis current interests primarily lie in deep learning and computer vision, especially object detection and image segmentation
no DOI — not checkedHe is currently an Associate Professor at Tsinghua University. His main research interests include image and video analysis and machine learning
no DOI — not checkedHe is now an Associate Professor at Tsinghua University. His research interests include deep learning and computational neuroscience
checked 2026-08-27 — re-checked daily as this page is visited;
titles and statuses come from Crossref and DataCite and are not part of the signed record
Both snippets point at the live badge image and link back to this page. The
badge re-renders from the daily check, so an embed never goes stale by more than a day of visits.