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

Object detection with multimodal inputs can improve many safety-criticalsystems such as autonomous vehicles (AVs). Motivated by AVs that operate inboth day and night, we study multimodal object detection with RGB and thermalcameras, since the latter provides much stronger object signatures under poorillumination. We explore strategies for fusing information from differentmodalities. Our key contribution is a probabilistic ensembling technique,ProbEn, a simple non-learned method that fuses together detections frommulti-modalities. We derive ProbEn from Bayes' rule and first principles thatassume conditional independence across modalities. Through probabilisticmarginalization, ProbEn elegantly handles missing modalities when detectors donot fire on the same object. Importantly, ProbEn also notably improvesmultimodal detection even when the conditional independence assumption does nothold, e.g., fusing outputs from other fusion methods (both off-the-shelf andtrained in-house). We validate ProbEn on two benchmarks containing both aligned(KAIST) and unaligned (FLIR) multimodal images, showing that ProbEn outperformsprior work by more than 13% in relative performance!

Multimodal Object Detection via Probabilistic Ensembling