English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Semi-supervised video object segmentation (semi-VOS) is widely used in manyapplications. This task is tracking class-agnostic objects from a given targetmask. For doing this, various approaches have been developed based ononline-learning, memory networks, and optical flow. These methods show highaccuracy but are hard to be utilized in real-world applications due to slowinference time and tremendous complexity. To resolve this problem, templatematching methods are devised for fast processing speed but sacrificing lots ofperformance in previous models. We introduce a novel semi-VOS model based on atemplate matching method and a temporal consistency loss to reduce theperformance gap from heavy models while expediting inference time a lot. Ourtemplate matching method consists of short-term and long-term matching. Theshort-term matching enhances target object localization, while long-termmatching improves fine details and handles object shape-changing through thenewly proposed adaptive template attention module. However, the long-termmatching causes error-propagation due to the inflow of the past estimatedresults when updating the template. To mitigate this problem, we also propose atemporal consistency loss for better temporal coherence between neighboringframes by adopting the concept of a transition matrix. Our model obtains 79.5%J&F score at the speed of 73.8 FPS on the DAVIS16 benchmark. The code isavailable in https://github.com/HYOJINPARK/TTVOS.

TTVOS: Lightweight Video Object Segmentation with Adaptive Template Attention Module and Temporal Consistency Loss