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/

Zendy Plus

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

Zendy Tools

Zendy Open

Depth information has proven to be a useful cue in the semantic segmentationof RGB-D images for providing a geometric counterpart to the RGBrepresentation. Most existing works simply assume that depth measurements areaccurate and well-aligned with the RGB pixels and models the problem as across-modal feature fusion to obtain better feature representations to achievemore accurate segmentation. This, however, may not lead to satisfactory resultsas actual depth data are generally noisy, which might worsen the accuracy asthe networks go deeper.  In this paper, we propose a unified and efficient Cross-modality GuidedEncoder to not only effectively recalibrate RGB feature responses, but also todistill accurate depth information via multiple stages and aggregate the tworecalibrated representations alternatively. The key of the proposedarchitecture is a novel Separation-and-Aggregation Gating operation thatjointly filters and recalibrates both representations before cross-modalityaggregation. Meanwhile, a Bi-direction Multi-step Propagation strategy isintroduced, on the one hand, to help to propagate and fuse information betweenthe two modalities, and on the other hand, to preserve their specificity alongthe long-term propagation process. Besides, our proposed encoder can be easilyinjected into the previous encoder-decoder structures to boost theirperformance on RGB-D semantic segmentation. Our model outperformsstate-of-the-arts consistently on both in-door and out-door challengingdatasets. Code of this work is available at https://charlescxk.github.io/

Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentation