LVOS: A Benchmark for Long-term Video Object Segmentation
This provides a benchmark for researchers to evaluate VOS methods in realistic, long-term scenarios, though it is incremental as it builds on existing VOS frameworks.
The authors tackled the lack of long-term video object segmentation (VOS) datasets by introducing LVOS, a benchmark with 220 videos averaging 1.59 minutes each, which is 20 times longer than existing datasets, and they proposed a DDMemory network that leverages temporal information to address challenges like object reappearance.
Existing video object segmentation (VOS) benchmarks focus on short-term videos which just last about 3-5 seconds and where objects are visible most of the time. These videos are poorly representative of practical applications, and the absence of long-term datasets restricts further investigation of VOS on the application in realistic scenarios. So, in this paper, we present a new benchmark dataset named \textbf{LVOS}, which consists of 220 videos with a total duration of 421 minutes. To the best of our knowledge, LVOS is the first densely annotated long-term VOS dataset. The videos in our LVOS last 1.59 minutes on average, which is 20 times longer than videos in existing VOS datasets. Each video includes various attributes, especially challenges deriving from the wild, such as long-term reappearing and cross-temporal similar objeccts.Based on LVOS, we assess existing video object segmentation algorithms and propose a Diverse Dynamic Memory network (DDMemory) that consists of three complementary memory banks to exploit temporal information adequately. The experimental results demonstrate the strength and weaknesses of prior methods, pointing promising directions for further study. Data and code are available at https://lingyihongfd.github.io/lvos.github.io/.