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

Visual-Language Models (VLMs) have significantly advanced action videorecognition. Supervised by the semantics of action labels, recent works adaptthe visual branch of VLMs to learn video representations. Despite theeffectiveness proved by these works, we believe that the potential of VLMs hasyet to be fully harnessed. In light of this, we exploit the semantic units (SU)hiding behind the action labels and leverage their correlations withfine-grained items in frames for more accurate action recognition. SUs areentities extracted from the language descriptions of the entire action set,including body parts, objects, scenes, and motions. To further enhance thealignments between visual contents and the SUs, we introduce a multi-regionmodule (MRA) to the visual branch of the VLM. The MRA allows the perception ofregion-aware visual features beyond the original global feature. Our methodadaptively attends to and selects relevant SUs with visual features of frames.With a cross-modal decoder, the selected SUs serve to decode spatiotemporalvideo representations. In summary, the SUs as the medium can boostdiscriminative ability and transferability. Specifically, in fully-supervisedlearning, our method achieved 87.8% top-1 accuracy on Kinetics-400. In K=2few-shot experiments, our method surpassed the previous state-of-the-art by+7.1% and +15.0% on HMDB-51 and UCF-101, respectively.

Video Action Recognition with Attentive Semantic Units