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

Recently, video text detection, tracking, and recognition in natural scenesare becoming very popular in the computer vision community. However, mostexisting algorithms and benchmarks focus on common text cases (e.g., normalsize, density) and single scenario, while ignoring extreme video textchallenges, i.e., dense and small text in various scenarios. In this paper, weestablish a video text reading benchmark, named DSText V2, which focuses onDense and Small text reading challenges in the video with various scenarios.Compared with the previous datasets, the proposed dataset mainly include threenew challenges: 1) Dense video texts, a new challenge for video text spottersto track and read. 2) High-proportioned small texts, coupled with theblurriness and distortion in the video, will bring further challenges. 3)Various new scenarios, e.g., Game, Sports, etc. The proposed DSText V2 includes140 video clips from 7 open scenarios, supporting three tasks, i.e., video textdetection (Task 1), video text tracking (Task 2), and end-to-end video textspotting (Task 3). In this article, we describe detailed statisticalinformation of the dataset, tasks, evaluation protocols, and the resultssummaries. Most importantly, a thorough investigation and analysis targetingthree unique challenges derived from our dataset are provided, aiming toprovide new insights. Moreover, we hope the benchmark will promise video textresearch in the community. DSText v2 is built upon DSText v1, which waspreviously introduced to organize the ICDAR 2023 competition for dense andsmall video text.

DSText V2: A Comprehensive Video Text Spotting Dataset for Dense and Small Text