Lei Ke

22

Papers

163

Total Citations

Papers (22)

GSNet: Joint Vehicle Pose and Shape Reconstruction with Geometrical and Scene-aware Supervision

Matching Anything by Segmenting Anything

Commonality-Parsing Network across Shape and Appearance for Partially Supervised Instance Segmentation

Video Depth without Video Models

SLAck: Semantic, Location, and Appearance Aware Open-Vocabulary Tracking

Multi-View 3D Point Tracking

Deep Occlusion-Aware Instance Segmentation With Overlapping BiLayers

Mask Transfiner for High-Quality Instance Segmentation

Mask-Free Video Instance Segmentation

Reflective Decoding Network for Image Captioning

Occlusion-Aware Video Object Inpainting

Cascade-DETR: Delving into High-Quality Universal Object Detection

Video Mask Transfiner for High-Quality Video Instance Segmentation

OVTrack: Open-Vocabulary Multiple Object Tracking

EntitySAM: Segment Everything in Video

Robust Multi-Object 4D Generation for In-the-wild Videos

ProReflow: Progressive Reflow with Decomposed Velocity

Memory-Attended Recurrent Network for Video Captioning

Cascaded Deep Monocular 3D Human Pose Estimation With Evolutionary Training Data

Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation

Segment Anything in High Quality

BiMatting: Efficient Video Matting via Binarization