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

Novel Categories Discovery (NCD) facilitates learning from a partiallyannotated label space and enables deep learning (DL) models to operate in anopen-world setting by identifying and differentiating instances of novelclasses based on the labeled data notions. One of the primary assumptions ofNCD is that the novel label space is perfectly disjoint and can beequipartitioned, but it is rarely realized by most NCD approaches in practice.To better align with this assumption, we propose a novel single-stage jointoptimization-based NCD method, Negative learning, Entropy, and Varianceregularization NCD (NEV-NCD). We demonstrate the efficacy of NEV-NCD inpreviously unexplored NCD applications of video action recognition (VAR) withthe public UCF101 dataset and a curated in-house partial action-space annotatedmulti-view video dataset. We perform a thorough ablation study by varying thecomposition of final joint loss and associated hyper-parameters. During ourexperiments with UCF101 and multi-view action dataset, NEV-NCD achieves ~ 83%classification accuracy in test instances of labeled data. NEV-NCD achieves ~70% clustering accuracy over unlabeled data outperforming both naive baselines(by ~ 40%) and state-of-the-art pseudo-labeling-based approaches (by ~ 3.5%)over both datasets. Further, we propose to incorporate optional view-invariantfeature learning with the multiview dataset to identify novel categories fromnovel viewpoints. Our additional view-invariance constraint improves thediscriminative accuracy for both known and unknown categories by ~ 10% fornovel viewpoints.

NEV-NCD: Negative Learning, Entropy, and Variance regularization based novel action categories discovery