[CVPR'23] Universal Instance Perception as Object Discovery and Retrieval
SAM-PT: Extending SAM to zero-shot video segmentation with point-based t...
[CVPR2024 Highlight]GLEE: General Object Foundation Model for Images and...
[CVPR2021 Oral] End-to-End Video Instance Segmentation with Transformers
Next-generation Video instance recognition framework on top of Detectron...
Prototypical Cross-Attention Networks for Multiple Object Tracking and S...
SipMask: Spatial Information Preservation for Fast Image and Video Insta...
SeqFormer: Sequential Transformer for Video Instance Segmentation (ECCV ...
Temporally Efficient Vision Transformer for Video Instance Segmentation,...
Code release for "UniVS: Unified and Universal Video Segmentation with P...
Code release for "STMask: Spatial Feature Calibration and Temporal Fusio...
Mask-Free Video Instance Segmentation [CVPR 2023]