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

Temporal cues in videos provide important information for recognizing actionsaccurately. However, temporal-discriminative features can hardly be extractedwithout using an annotated large-scale video action dataset for training. Thispaper proposes a novel Video-based Temporal-Discriminative Learning (VTDL)framework in self-supervised manner. Without labelled data for networkpretraining, temporal triplet is generated for each anchor video by usingsegment of the same or different time interval so as to enhance the capacityfor temporal feature representation. Measuring temporal information by timederivative, Temporal Consistent Augmentation (TCA) is designed to ensure thatthe time derivative (in any order) of the augmented positive is invariantexcept for a scaling constant. Finally, temporal-discriminative features arelearnt by minimizing the distance between each anchor and its augmentedpositive, while the distance between each anchor and its augmented negative aswell as other videos saved in the memory bank is maximized to enrich therepresentation diversity. In the downstream action recognition task, theproposed method significantly outperforms existing related works. Surprisingly,the proposed self-supervised approach is better than fully-supervised methodson UCF101 and HMDB51 when a small-scale video dataset (with only thousands ofvideos) is used for pre-training. The code has been made publicly available onhttps://github.com/FingerRec/Self-Supervised-Temporal-Discriminative-Representation-Learning-for-Video-Action-Recognition.

Self-supervised Temporal Discriminative Learning for Video Representation Learning