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

Human parsing has recently attracted a lot of research interests due to itshuge application potentials. However existing datasets have limited number ofimages and annotations, and lack the variety of human appearances and thecoverage of challenging cases in unconstrained environment. In this paper, weintroduce a new benchmark "Look into Person (LIP)" that makes a significantadvance in terms of scalability, diversity and difficulty, a contribution thatwe feel is crucial for future developments in human-centric analysis. Thiscomprehensive dataset contains over 50,000 elaborately annotated images with 19semantic part labels, which are captured from a wider range of viewpoints,occlusions and background complexity. Given these rich annotations we performdetailed analyses of the leading human parsing approaches, gaining insightsinto the success and failures of these methods. Furthermore, in contrast to theexisting efforts on improving the feature discriminative capability, we solvehuman parsing by exploring a novel self-supervised structure-sensitive learningapproach, which imposes human pose structures into parsing results withoutresorting to extra supervision (i.e., no need for specifically labeling humanjoints in model training). Our self-supervised learning framework can beinjected into any advanced neural networks to help incorporate rich high-levelknowledge regarding human joints from a global perspective and improve theparsing results. Extensive evaluations on our LIP and the publicPASCAL-Person-Part dataset demonstrate the superiority of our method.

Look into Person: Self-supervised Structure-sensitive Learning and A New Benchmark for Human Parsing