← Authors

Lei Ke

27 papers · 2019–2025 · 6 conferences · across top CS/AI conferences

Achievements

🌈 Renaissance Researcher (6) 🐣 Hot Topic Early Bird πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (6) πŸƒ Academic Marathon (6) πŸ—ΊοΈ Taxonomy Completionist (50) 🐝 Cross-Pollinator (10) 🀝 Dynamic Duo (16) πŸ”₯ Unstoppable (7) πŸ’Ž Century Club (27) πŸ—ƒοΈ Keyword Collector (113) ⚑ Prolific Year (5)

Conferences

CVPR (11) ECCV (5) ICCV (4) NIPS (4) ICLR (2) WACV (1)

Top co-authors

Yu-Wing Tai (16) Chi-Keung Tang (14) Martin Danelljan (12) Fisher Yu (11) Siyuan Li (5) Mingqiao Ye (5) Katerina Fragkiadaki (3) Henghui Ding (3) Wenjie Pei (3) Luc Van Gool (2)

Keywords

zero-shot learning (4) instance segmentation (4) mask prediction (3) object tracking (3) video segmentation (2) diffusion model (2) occlusion handling (2) temporal consistency (2) point tracking (2) neural network (2) foundation model (2) object detection (2) semantic segmentation (2) transformer architecture (2) video instance segmentation (2) novel view synthesis (2) video captioning (1) video generation (1) image generation (1) image captioning (1)

Papers

Segment Anything Meets Point Tracking WACV 2025
ProReflow: Progressive Reflow with Decomposed Velocity CVPR 2025
EntitySAM: Segment Everything in Video CVPR 2025
Robust Multi-Object 4D Generation for In-the-wild Videos CVPR 2025
Video Depth without Video Models CVPR 2025
Multi-View 3D Point Tracking ICCV 2025
M^3PC: Test-time Model Predictive Control using Pretrained Masked Trajectory Model ICLR 2025
Stable Segment Anything Model ICLR 2025
Gaussian Grouping: Segment and Edit Anything in 3D Scenes ECCV 2024
"SLAck: Semantic, Location, and Appearance Aware Open-Vocabulary Tracking" ECCV 2024
Matching Anything by Segmenting Anything CVPR 2024
DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos NIPS 2024
Mask-Free Video Instance Segmentation CVPR 2023
Cascade-DETR: Delving into High-Quality Universal Object Detection ICCV 2023
BiMatting: Efficient Video Matting via Binarization NIPS 2023
Segment Anything in High Quality NIPS 2023
OVTrack: Open-Vocabulary Multiple Object Tracking CVPR 2023
Mask Transfiner for High-Quality Instance Segmentation CVPR 2022
Video Mask Transfiner for High-Quality Video Instance Segmentation ECCV 2022
Deep Occlusion-Aware Instance Segmentation With Overlapping BiLayers CVPR 2021
Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation NIPS 2021
Occlusion-Aware Video Object Inpainting ICCV 2021
GSNet: Joint Vehicle Pose and Shape Reconstruction with Geometrical and Scene-aware Supervision ECCV 2020
Commonality-Parsing Network across Shape and Appearance for Partially Supervised Instance Segmentation ECCV 2020
Cascaded Deep Monocular 3D Human Pose Estimation With Evolutionary Training Data CVPR 2020
Reflective Decoding Network for Image Captioning ICCV 2019
Memory-Attended Recurrent Network for Video Captioning CVPR 2019