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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Traditional convolutional neural networks have a limited receptive fieldwhile transformer-based networks are mediocre in constructing long-termdependency from the perspective of computational complexity. Such thebottleneck poses a significant challenge when processing long video sequencesin video analysis tasks. Very recently, the state space models (SSMs) withefficient hardware-aware designs, famous by Mamba, have exhibited impressiveachievements in long sequence modeling, which facilitates the development ofdeep neural networks on many vision tasks. To better capture available cues invideo frames, this paper presents a generic Video Vision Mamba-based frameworkfor medical video object segmentation tasks, named Vivim. Our Vivim caneffectively compress the long-term spatiotemporal representation into sequencesat varying scales by our designed Temporal Mamba Block. Compared to existingvideo-level Transformer-based methods, our model maintains excellentsegmentation results with better speed performance. Extensive experiments onthe breast US dataset demonstrate the effectiveness and efficiency of ourVivim. The code for Vivim is available at:https://github.com/scott-yjyang/Vivim.

Vivim: a Video Vision Mamba for Medical Video Object Segmentation