4 papers · 1 filter
EGM: Efficient Visual Grounding Language Models
Guanqi Zhan, Changye Li, Zhijian Liu +4
Visual grounding is an essential capability of Visual Language Models (VLMs) to understand the real physical world. Previous state-of-the-art grounding visual language models usual…
Estimating 2D Camera Motion with Hybrid Motion Basis
Haipeng Li, Tianhao Zhou, Zhanglei Yang +6
Estimating 2D camera motion is a fundamental computer vision task that models the projection of 3D camera movements onto the 2D image plane. Current methods rely on either homograp…
PM-VIS+: High-Performance Video Instance Segmentation without Video Annotation
Zhangjing Yang, Dun Liu, Xin Wang +3
Video instance segmentation requires detecting, segmenting, and tracking objects in videos, typically relying on costly video annotations. This paper introduces a method that elimi…
PM-VIS: High-Performance Box-Supervised Video Instance Segmentation
Zhangjing Yang, Dun Liu, Wensheng Cheng +2
Labeling pixel-wise object masks in videos is a resource-intensive and laborious process. Box-supervised Video Instance Segmentation (VIS) methods have emerged as a viable solution…