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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

A long-standing challenge in scene analysis is the recovery of scenearrangements under moderate to heavy occlusion, directly from monocular video.While the problem remains a subject of active research, concurrent advanceshave been made in the context of human pose reconstruction from monocularvideo, including image-space feature point detection and 3D pose recovery.These methods, however, start to fail under moderate to heavy occlusion as theproblem becomes severely under-constrained. We approach the problemsdifferently. We observe that people interact similarly in similar scenes.Hence, we exploit the correlation between scene object arrangement and motionsperformed in that scene in both directions: first, typical motions performedwhen interacting with objects inform us about possible object arrangements; andsecond, object arrangements, in turn, constrain the possible motions.  We present iMapper, a data-driven method that focuses on identifyinghuman-object interactions, and jointly reasons about objects and human movementover space-time to recover both a plausible scene arrangement and consistenthuman interactions. We first introduce the notion of characteristicinteractions as regions in space-time when an informative human-objectinteraction happens. This is followed by a novel occlusion-aware matchingprocedure that searches and aligns such characteristic snapshots from aninteraction database to best explain the input monocular video. Throughextensive evaluations, both quantitative and qualitative, we demonstrate thatiMapper significantly improves performance over both dedicated state-of-the-artscene analysis and 3D human pose recovery approaches, especially under mediumto heavy occlusion.

iMapper: Interaction-guided Joint Scene and Human Motion Mapping from Monocular Videos