An Exploration of Target-Conditioned Segmentation Methods for Visual Object Trackers
arXiv:2008.00992 · doi:10.1007/978-3-030-68238-5_41
Abstract
Visual object tracking is the problem of predicting a target object's state in a video. Generally, bounding-boxes have been used to represent states, and a surge of effort has been spent by the community to produce efficient causal algorithms capable of locating targets with such representations. As the field is moving towards binary segmentation masks to define objects more precisely, in this paper we propose to extensively explore target-conditioned segmentation methods available in the computer vision community, in order to transform any bounding-box tracker into a segmentation tracker. Our analysis shows that such methods allow trackers to compete with recently proposed segmentation trackers, while performing quasi real-time.
arXiv commentEuropean Conference on Computer Vision (ECCV) 2020, Visual Object Tracking Challenge VOT2020 workshop
References in corpus (10)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Rethinking Atrous Convolution for Semantic Image Segmentation
- High-Speed Tracking with Kernelized Correlation Filters
- GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild
- Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking
- Discriminative Correlation Filter with Channel and Spatial Reliability
- YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark
- DCFNet: Discriminant Correlation Filters Network for Visual Tracking
- Visual Tracking by means of Deep Reinforcement Learning and an Expert Demonstrator
- BoLTVOS: Box-Level Tracking for Video Object Segmentation