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-Object Interaction detection is a holistic visual recognition task thatentails object detection as well as interaction classification. Previous worksof HOI detection has been addressed by the various compositions of subsetpredictions, e.g., Image -> HO -> I, Image -> HI -> O. Recently, transformerbased architecture for HOI has emerged, which directly predicts the HOItriplets in an end-to-end fashion (Image -> HOI). Motivated by variousinference paths for HOI detection, we propose cross-path consistency learning(CPC), which is a novel end-to-end learning strategy to improve HOI detectionfor transformers by leveraging augmented decoding paths. CPC learning enforcesall the possible predictions from permuted inference sequences to beconsistent. This simple scheme makes the model learn consistentrepresentations, thereby improving generalization without increasing modelcapacity. Our experiments demonstrate the effectiveness of our method, and weachieved significant improvement on V-COCO and HICO-DET compared to thebaseline models. Our code is available at https://github.com/mlvlab/CPChoi.

Consistency Learning via Decoding Path Augmentation for Transformers in Human Object Interaction Detection