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

Event cameras detect changes in per-pixel intensity to generate asynchronous`event streams'. They offer great potential for accurate semantic map retrievalin real-time autonomous systems owing to their much higher temporal resolutionand high dynamic range (HDR) compared to conventional cameras. However,existing implementations for event-based segmentation suffer from sub-optimalperformance since these temporally dense events only measure the varyingcomponent of a visual signal, limiting their ability to encode dense spatialcontext compared to frames. To address this issue, we propose a hybridend-to-end learning framework HALSIE, utilizing three key concepts to reduceinference cost by up to $20\times$ versus prior art while retaining similarperformance: First, a simple and efficient cross-domain learning scheme toextract complementary spatio-temporal embeddings from both frames and events.Second, a specially designed dual-encoder scheme with Spiking Neural Network(SNN) and Artificial Neural Network (ANN) branches to minimize latency whileretaining cross-domain feature aggregation. Third, a multi-scale cue mixer tomodel rich representations of the fused embeddings. These qualities of HALSIEallow for a very lightweight architecture achieving state-of-the-artsegmentation performance on DDD-17, MVSEC, and DSEC-Semantic datasets with upto $33\times$ higher parameter efficiency and favorable inference cost (17.9mJper cycle). Our ablation study also brings new insights into effective designchoices that can prove beneficial for research across other vision tasks.

HALSIE: Hybrid Approach to Learning Segmentation by Simultaneously Exploiting Image and Event Modalities