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/

Zendy Plus

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

Zendy Tools

Zendy Open

This paper presents a new vision Transformer, named Iwin Transformer, whichis specifically designed for human-object interaction (HOI) detection, adetailed scene understanding task involving a sequential process ofhuman/object detection and interaction recognition. Iwin Transformer is ahierarchical Transformer which progressively performs token representationlearning and token agglomeration within irregular windows. The irregularwindows, achieved by augmenting regular grid locations with learned offsets, 1)eliminate redundancy in token representation learning, which leads to efficienthuman/object detection, and 2) enable the agglomerated tokens to align withhumans/objects with different shapes, which facilitates the acquisition ofhighly-abstracted visual semantics for interaction recognition. Theeffectiveness and efficiency of Iwin Transformer are verified on the twostandard HOI detection benchmark datasets, HICO-DET and V-COCO. Results showour method outperforms existing Transformers-based methods by large margins(3.7 mAP gain on HICO-DET and 2.0 mAP gain on V-COCO) with fewer trainingepochs ($0.5 \times$).

Iwin: Human-Object Interaction Detection via Transformer with Irregular Windows