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

Recent one-stage transformer-based methods achieve notable gains in theHuman-object Interaction Detection (HOI) task by leveraging the detection ofDETR. However, the current methods redirect the detection target of the objectdecoder, and the box target is not explicitly separated from the queryembeddings, which leads to long and hard training. Furthermore, matching thepredicted HOI instances with the ground-truth is more challenging than objectdetection, simply adapting training strategies from the object detection makesthe training more difficult. To clear the ambiguity between human and objectdetection and share the prediction burden, we propose a novel one-stageframework (SOV), which consists of a subject decoder, an object decoder, and averb decoder. Moreover, we propose a novel Specific Target Guided (STG)DeNoising training strategy, which leverages learnable object and verb labelembeddings to guide the training and accelerate the training convergence. Inaddition, for the inference part, the label-specific information is directlyfed into the decoders by initializing the query embeddings from the learnablelabel embeddings. Without additional features or prior language knowledge, ourmethod (SOV-STG) achieves higher accuracy than the state-of-the-art method inone-third of training epochs. The code is available at thishttps://github.com/cjw2021/SOV-STG.

Focusing on what to decode and what to train: Efficient Training with HOI Split Decoders and Specific Target Guided DeNoising