Lei Ke
30 papers · 2019–2026 · 6 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (54) π Conference Polyglot Β· Silver π£ Hot Topic Early Bird π Academic Marathon Β· Sprint
π€
Dynamic Duo
(16)
β‘
Prolific Year Β· Productive
π₯
Unstoppable Β· Bronze
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(129)
Top co-authors
Research topics
Computer Vision
(23)
Deep Learning
(19)
Analysis
(12)
Machine Learning
(10)
Processing
(10)
Learning Types Β· Deep Learning
(9)
Models
(9)
Generation
(8)
Artificial Intelligence
(7)
Core AI
(6)
Architectures
(5)
Learning Types Β· Machine Learning
(5)
Techniques
(4)
Application Areas
(3)
Learning Paradigms
(3)
Keywords
zero-shot learning
(4)
instance segmentation
(4)
diffusion model
(3)
mask prediction
(3)
object tracking
(3)
object detection
(2)
transformer architecture
(2)
neural network
(2)
foundation model
(2)
occlusion handling
(2)
novel view synthesis
(2)
video segmentation
(2)
promptable segmentation
(2)
semantic segmentation
(2)
video instance segmentation
(2)
image segmentation
(2)
attention mechanism
(2)
flow matching
(2)
temporal consistency
(2)
point tracking
(2)
Papers
FlowSteer: Guiding Few-Step Image Synthesis with Authentic Trajectories
CVPR 2026
MotionEdit: Benchmarking and Learning Motion-Centric Image Editing
CVPR 2026
Stable and Efficient Single-Rollout RL for Multimodal Reasoning
CVPR 2026
EntitySAM: Segment Everything in Video
CVPR 2025
M^3PC: Test-time Model Predictive Control using Pretrained Masked Trajectory Model
ICLR 2025
Multi-View 3D Point Tracking
ICCV 2025
ProReflow: Progressive Reflow with Decomposed Velocity
CVPR 2025
Robust Multi-Object 4D Generation for In-the-wild Videos
CVPR 2025
Segment Anything Meets Point Tracking
WACV 2025
Stable Segment Anything Model
ICLR 2025
Video Depth without Video Models
CVPR 2025
DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos
NeurIPS 2024
Gaussian Grouping: Segment and Edit Anything in 3D Scenes
ECCV 2024
Matching Anything by Segmenting Anything
CVPR 2024
"SLAck: Semantic, Location, and Appearance Aware Open-Vocabulary Tracking"
ECCV 2024
BiMatting: Efficient Video Matting via Binarization
NeurIPS 2023
Cascade-DETR: Delving into High-Quality Universal Object Detection
ICCV 2023
Mask-Free Video Instance Segmentation
CVPR 2023
OVTrack: Open-Vocabulary Multiple Object Tracking
CVPR 2023
Segment Anything in High Quality
NeurIPS 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
Occlusion-Aware Video Object Inpainting
ICCV 2021
Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation
NeurIPS 2021
Cascaded Deep Monocular 3D Human Pose Estimation With Evolutionary Training Data
CVPR 2020
Commonality-Parsing Network across Shape and Appearance for Partially Supervised Instance Segmentation
ECCV 2020
GSNet: Joint Vehicle Pose and Shape Reconstruction with Geometrical and Scene-aware Supervision
ECCV 2020
Memory-Attended Recurrent Network for Video Captioning
CVPR 2019
Reflective Decoding Network for Image Captioning
ICCV 2019