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

3D vehicle detection based on multi-modal fusion is an important task of manyapplications such as autonomous driving. Although significant progress has beenmade, we still observe two aspects that need to be further improvement: First,the specific gain that camera images can bring to 3D detection is seldomexplored by previous works. Second, many fusion algorithms run slowly, which isessential for applications with high real-time requirements(autonomousdriving). To this end, we propose an end-to-end trainable single-stagemulti-modal feature adaptive network in this paper, which uses imageinformation to effectively reduce false positive of 3D detection and has a fastdetection speed. A multi-modal adaptive feature fusion module based on channelattention mechanism is proposed to enable the network to adaptively use thefeature of each modal. Based on the above mechanism, two fusion technologiesare proposed to adapt to different usage scenarios: PointAttentionFusion issuitable for filtering simple false positive and faster; DenseAttentionFusionis suitable for filtering more difficult false positive and has better overallperformance. Experimental results on the KITTI dataset demonstrate significantimprovement in filtering false positive over the approach using only pointcloud data. Furthermore, the proposed method can provide competitive resultsand has the fastest speed compared to the published state-of-the-artmulti-modal methods in the KITTI benchmark.

MAFF-Net: Filter False Positive for 3D Vehicle Detection with Multi-modal Adaptive Feature Fusion