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

The key of Human-Object Interaction(HOI) recognition is to infer therelationship between human and objects. Recently, the image's Human-ObjectInteraction(HOI) detection has made significant progress. However, there isstill room for improvement in video HOI detection performance. Existingone-stage methods use well-designed end-to-end networks to detect a videosegment and directly predict an interaction.  It makes the model learning and further optimization of the network morecomplex. This paper introduces the Spatial Parsing and Dynamic Temporal Pooling(SPDTP) network, which takes the entire video as a spatio-temporal graph withhuman and object nodes as input. Unlike existing methods, our proposed networkpredicts the difference between interactive and non-interactive pairs throughexplicit spatial parsing, and then performs interaction recognition. Moreover,we propose a learnable and differentiable Dynamic Temporal Module(DTM) toemphasize the keyframes of the video and suppress the redundant frame.Furthermore, the experimental results show that SPDTP can pay more attention toactive human-object pairs and valid keyframes. Overall, we achievestate-of-the-art performance on CAD-120 dataset and Something-Else dataset.

Spatial Parsing and Dynamic Temporal Pooling networks for Human-Object Interaction detection