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

This work proposes TimeChat, a time-sensitive multimodal large language modelspecifically designed for long video understanding. Our model incorporates twokey architectural contributions: (1) a timestamp-aware frame encoder that bindsvisual content with the timestamp of each frame, and (2) a sliding videoQ-Former that produces a video token sequence of varying lengths to accommodatevideos of various durations. Additionally, we construct an instruction-tuningdataset, encompassing 6 tasks and a total of 125K instances, to further enhanceTimeChat's instruction-following performance. Experiment results across variousvideo understanding tasks, such as dense captioning, temporal grounding, andhighlight detection, demonstrate TimeChat's strong zero-shot temporallocalization and reasoning capabilities. For example, it achieves +9.2 F1 scoreand +2.8 CIDEr on YouCook2, +5.8 HIT@1 on QVHighlights, and +27.5 R@1 (IoU=0.5)on Charades-STA, compared to state-of-the-art video large language models,holding the potential to serve as a versatile video assistant for long-formvideo comprehension tasks and satisfy realistic user requirements.

TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding