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 (HOI) detection is a challenging computer visiontask that requires visual models to address the complex interactiverelationship between humans and objects and predict HOI triplets. Despite thechallenges posed by the numerous interaction combinations, they also offeropportunities for multimodal learning of visual texts. In this paper, wepresent a systematic and unified framework (RmLR) that enhances HOI detectionby incorporating structured text knowledge. Firstly, we qualitatively andquantitatively analyze the loss of interaction information in the two-stage HOIdetector and propose a re-mining strategy to generate more comprehensive visualrepresentation.Secondly, we design more fine-grained sentence- and word-levelalignment and knowledge transfer strategies to effectively address themany-to-many matching problem between multiple interactions and multipletexts.These strategies alleviate the matching confusion problem that ariseswhen multiple interactions occur simultaneously, thereby improving theeffectiveness of the alignment process. Finally, HOI reasoning by visualfeatures augmented with textual knowledge substantially improves theunderstanding of interactions. Experimental results illustrate theeffectiveness of our approach, where state-of-the-art performance is achievedon public benchmarks. We further analyze the effects of different components ofour approach to provide insights into its efficacy.

Re-mine, Learn and Reason: Exploring the Cross-modal Semantic Correlations for Language-guided HOI detection