Get started
Author

Lei Ke

Observed names: Ke Lei, Ke, Lei
Institution: ETH Zurich
Observed institutions: Hong Kong University of Science and Technology, Tencent (China), ETH Zurich, Computer Vision Laboratory, Carnegie Mellon University, Stanford University, Tsinghua University
ORCID: 0000-0002-1978-2562
Observed ORCID: 0000-0002-1978-2562
OpenAlex ID: A5077165692
Memory-Attended Recurrent Network for Video Captioning
2019 · Wenjie Pei, Jiyuan Zhang, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 240
PDF
Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers
2021 · Lei Ke, Yu-Wing Tai, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 212
PDF
Gaussian Grouping: Segment and Edit Anything in 3D Scenes
2024 · Mingqiao Ye, Martin Danelljan, et al. · Lecture notes in computer science · 200
PDF
Cascaded Deep Monocular 3D Human Pose Estimation With Evolutionary Training Data
2020 · Shichao Li, Lei Ke, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 175
PDF
Mask Transfiner for High-Quality Instance Segmentation
2022 · Lei Ke, Martin Danelljan, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 164
PDF
Reflective Decoding Network for Image Captioning
2019 · Lei Ke, Wenjie Pei, et al. · IEEE/CVF International Conference on Computer Vision (ICCV) · 109
PDF
Segment Anything in High Quality
2023 · Ke, Lei, Ye, Mingqiao, et al. · arXiv (Cornell University) · 105
PDF
Segment Anything in High Quality
2023 · Lei Ke, Mingqiao Ye, et al. · neural information processing systems · 102
OVTrack: Open-Vocabulary Multiple Object Tracking
2023 · Siyuan Li, Tobias Fischer, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 71
Cascade-DETR: Delving into High-Quality Universal Object Detection
2023 · Mingqiao Ye, Lei Ke, et al. · IEEE/CVF International Conference on Computer Vision (ICCV) · 57
PDF
GSNet: Joint Vehicle Pose and Shape Reconstruction with Geometrical and Scene-Aware Supervision
2020 · Lei Ke, Shichao Li, et al. · Lecture notes in computer science · 51
PDF
Matching Anything by Segmenting Anything
2024 · Siyuan Li, Lei Ke, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 42
LLM-Seg: Bridging Image Segmentation and Large Language Model Reasoning
2024 · Junchi Wang, Lei Ke · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · 39
PDF
Occlusion-Aware Instance Segmentation Via BiLayer Network Architectures
2023 · Lei Ke, Yu-Wing Tai, et al. · IEEE Transactions on Pattern Analysis and Machine Intelligence · 37
PDF
Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation
2021 · Ke, Lei, Li, Xia, et al. · Repository for Publications and Research Data (ETH Zurich) · 35
Occlusion-Aware Video Object Inpainting
2021 · Lei Ke, Yu-Wing Tai, et al. · IEEE/CVF International Conference on Computer Vision (ICCV) · 31
PDF
Mask-Free Video Instance Segmentation
2023 · Lei Ke, Martin Danelljan, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 27
PDF
Commonality-Parsing Network Across Shape and Appearance for Partially Supervised Instance Segmentation
2020 · Qi Fan, Lei Ke, et al. · Lecture notes in computer science · 24
PDF
Video Mask Transfiner for High-Quality Video Instance Segmentation
2022 · Lei Ke, Henghui Ding, et al. · Lecture notes in computer science · 21
PDF
The First Visual Object Tracking Segmentation VOTS2023 Challenge Results
2023 · Matej Kristan, Jiří Matas, et al. · IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) · 19
DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos
2024 · Wen-Hsuan Chu, Lei Ke, et al. · neural information processing systems · 16
PDF
BiVM: Accurate Binarized Neural Network for Efficient Video Matting
2025 · Haotong Qin, Xianglong Liu, et al. · IEEE Transactions on Pattern Analysis and Machine Intelligence · 15
PDF
BiMatting: Efficient Video Matting via Binarization
2023 · Haotong Qin, Lei Ke, et al. · neural information processing systems · 14
SLAck: Semantic, Location, and Appearance Aware Open-Vocabulary Tracking
2024 · Siyuan Li, Lei Ke, et al. · Lecture notes in computer science · 7
TAPIP3D: Tracking Any Point in Persistent 3D Geometry
2025 · Bowei Zhang, Lei Ke, et al. · neural information processing systems · 6
Works count: 30
Citation count: 1,265
H-index: 16
I10-index: 18
Year
Topic
Type