An Empirical Study of Detection-Based Video Instance Segmentation
By Qiang Wang, Yi He, Xiaoyun Yang, Zhao Yang, Philip H. S. Torr. 2019
9 citations recorded by the source corpus.
Video instance segmentation (VIS) is a composite task that requires the joint detection, tracking, and segmentation of objects in a video. In this work, we introduce a complete framework for VIS, which integrates the strengths of instance segmentation and general object tracking in addressing the unique challenges of VIS. In developing the framework, we investigate effective ways of coordinating the two components for maximum benefits while thoroughly investigate their separate contributions. Our approach improves over the official baseline by an absolute 14.4% in mAP and achieves the second place in the 2019 YouTubeVIS challenge.
Subfields: Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Xinggang Wang
- Alan L. Yuille
- Philip H. S. Torr
- Xiang Bai
- Chunhua Shen
- Ming-Hsuan Yang
- Xiaogang Wang
Citations in the corpus
- Occluded Video Instance Segmentation: A Benchmark (2021, background): “Since the release of the YouTube-VIS dataset, video instance segmentation has attracted great attention in the computer vision community, arising a series of algorithms recently [49, 4, 1, 2, 27, 30, 41, 11].”
- STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos (2020, background): “State-of-the-art methods tackling these tasks [80, 83, 95] usually operate in a top-down fashion and follow the tracking-by-detection paradigm which is wellestablished in multi-object tracking (MOT) [8, 37, 47, 62].”
- Crossover Learning for Fast Online Video Instance Segmentation (2021, unknown): “With the introduction of YouTubeVIS-2019 dataset [68], tremendous progresses [19, 56, 37, 17] have been made in tackling this challenging task.”