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

The Contrastive Language-Image Pre-training (CLIP) has recently shownremarkable generalization on "zero-shot" training and has applied to manydownstream tasks. We explore the adaptation of CLIP to achieve a more efficientand generalized action recognition method. We propose that the key lies inexplicitly modeling the motion cues flowing in video frames. To that end, wedesign a two-stream motion modeling block to capture motion and spatialinformation at the same time. And then, the obtained motion cues are utilizedto drive a dynamic prompts learner to generate motion-aware prompts, whichcontain much semantic information concerning human actions. In addition, wepropose a multimodal communication block to achieve a collaborative learningand further improve the performance. We conduct extensive experiments onHMDB-51, UCF-101, and Kinetics-400 datasets. Our method outperforms mostexisting state-of-the-art methods by a significant margin on "few-shot" and"zero-shot" training. We also achieve competitive performance on "closed-set"training with extremely few trainable parameters and additional computationalcosts.

Seeing in Flowing: Adapting CLIP for Action Recognition with Motion Prompts Learning