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

RGB-D semantic segmentation methods conventionally use two independentencoders to extract features from the RGB and depth data. However, there lacksan effective fusion mechanism to bridge the encoders, for the purpose of fullyexploiting the complementary information from multiple modalities. This paperproposes a novel bottom-up interactive fusion structure to model theinterdependencies between the encoders. The structure introduces an interactionstream to interconnect the encoders. The interaction stream not onlyprogressively aggregates modality-specific features from the encoders but alsocomputes complementary features for them. To instantiate this structure, thepaper proposes a residual fusion block (RFB) to formulate the interdependencesof the encoders. The RFB consists of two residual units and one fusion unitwith gate mechanism. It learns complementary features for the modality-specificencoders and extracts modality-specific features as well as cross-modalfeatures. Based on the RFB, the paper presents the deep multimodal networks forRGB-D semantic segmentation called RFBNet. The experiments on two datasetsdemonstrate the effectiveness of modeling the interdependencies and that theRFBNet achieved state-of-the-art performance.

RFBNet: Deep Multimodal Networks with Residual Fusion Blocks for RGB-D Semantic Segmentation