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

The ability to perceive how objects change over time is a crucial ingredientin human intelligence. However, current benchmarks cannot faithfully reflectthe temporal understanding abilities of video-language models (VidLMs) due tothe existence of static visual shortcuts. To remedy this issue, we presentVITATECS, a diagnostic VIdeo-Text dAtaset for the evaluation of TEmporalConcept underStanding. Specifically, we first introduce a fine-grained taxonomyof temporal concepts in natural language in order to diagnose the capability ofVidLMs to comprehend different temporal aspects. Furthermore, to disentanglethe correlation between static and temporal information, we generatecounterfactual video descriptions that differ from the original one only in thespecified temporal aspect. We employ a semi-automatic data collection frameworkusing large language models and human-in-the-loop annotation to obtainhigh-quality counterfactual descriptions efficiently. Evaluation ofrepresentative video-language understanding models confirms their deficiency intemporal understanding, revealing the need for greater emphasis on the temporalelements in video-language research.

VITATECS: A Diagnostic Dataset for Temporal Concept Understanding of Video-Language Models