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

Fashion is a complex social phenomenon. People follow fashion styles fromdemonstrations by experts or fashion icons. However, for machine agent,learning to imitate fashion experts from demonstrations can be challenging,especially for complex styles in environments with high-dimensional, multimodalobservations. Most existing research regarding fashion outfit compositionutilizes supervised learning methods to mimic the behaviors of style icons.These methods suffer from distribution shift: because the agent greedilyimitates some given outfit demonstrations, it can drift away from one style toanother styles given subtle differences. In this work, we propose anadversarial inverse reinforcement learning formulation to recover rewardfunctions based on hierarchical multimodal representation (HM-AIRL) during theimitation process. The hierarchical joint representation can morecomprehensively model the expert composited outfit demonstrations to recoverthe reward function. We demonstrate that the proposed HM-AIRL model is able torecover reward functions that are robust to changes in multimodal observations,enabling us to learn policies under significant variation between differentstyles.

Imitation Learning for Fashion Style Based on Hierarchical Multimodal Representation