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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Referring video object segmentation (RVOS), as a supervised learning task,relies on sufficient annotated data for a given scene. However, in morerealistic scenarios, only minimal annotations are available for a new scene,which poses significant challenges to existing RVOS methods. With this in mind,we propose a simple yet effective model with a newly designed cross-modalaffinity (CMA) module based on a Transformer architecture. The CMA modulebuilds multimodal affinity with a few samples, thus quickly learning newsemantic information, and enabling the model to adapt to different scenarios.Since the proposed method targets limited samples for new scenes, we generalizethe problem as - few-shot referring video object segmentation (FS-RVOS). Tofoster research in this direction, we build up a new FS-RVOS benchmark based oncurrently available datasets. The benchmark covers a wide range and includesmultiple situations, which can maximally simulate real-world scenarios.Extensive experiments show that our model adapts well to different scenarioswith only a few samples, reaching state-of-the-art performance on thebenchmark. On Mini-Ref-YouTube-VOS, our model achieves an average performanceof 53.1 J and 54.8 F, which are 10% better than the baselines. Furthermore, weshow impressive results of 77.7 J and 74.8 F on Mini-Ref-SAIL-VOS, which aresignificantly better than the baselines. Code is publicly available athttps://github.com/hengliusky/Few_shot_RVOS.

Learning Cross-Modal Affinity for Referring Video Object Segmentation Targeting Limited Samples