Wenyu Liu, Xinggang Wang, Yu Li, Yuxin Fang, Ying Shan, Shusheng Yang, Bin Feng, Chen Fang
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Modeling temporal visual context across frames is critical for video instance segmentation (VIS) and other video understanding tasks. In this paper, we propose a fast online VIS model termed CrossVIS. For temporal information modeling in VIS, we present a novel crossover learning scheme that uses the instance feature in the current frame to pixel-wisely localize the same instance in other frames. Different from previous schemes, crossover learning does not require any additional network parameters for feature enhancement. By integrating with the instance segmentation loss, crossover learning enables efficient crossframe instance-to-pixel relation learning and brings costfree improvement during inference. Besides, a global balanced instance embedding branch is proposed for better and more stable online instance association. We conduct extensive experiments on three challenging VIS benchmarks, i.e., YouTube-VIS-2019, OVIS, and YouTube-VIS-2021 to evaluate our methods. CrossVIS achieves state-ofthe-art online VIS performance and shows a decent tradeoff between latency and accuracy. Code is available at https://github.com/hustvl/CrossVIS.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2104.05970")
get_code_for_paper("2104.05970")
have("2104.05970")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2104.05970.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2104.05970)
Connect an agent — have() is free.