research
∙
08/29/2023
NOVIS: A Case for End-to-End Near-Online Video Instance Segmentation
Until recently, the Video Instance Segmentation (VIS) community operated...
share
research
∙
06/20/2023
Data-Driven but Privacy-Conscious: Pedestrian Dataset De-identification via Full-Body Person Synthesis
The advent of data-driven technology solutions is accompanied by an incr...
research
∙
07/22/2022
DeVIS: Making Deformable Transformers Work for Video Instance Segmentation
Video Instance Segmentation (VIS) jointly tackles multi-object detection...
research
∙
01/07/2021
TrackFormer: Multi-Object Tracking with Transformers
We present TrackFormer, an end-to-end multi-object tracking and segmenta...
research
∙
12/03/2020
Make One-Shot Video Object Segmentation Efficient Again
Video object segmentation (VOS) describes the task of segmenting a set o...
research
∙
03/13/2019
Tracking without bells and whistles
The problem of tracking multiple objects in a video sequence poses sever...
research
∙
03/23/2018
Lifting Layers: Analysis and Applications
The great advances of learning-based approaches in image processing and ...
research
∙
04/11/2017