Jump to content

18694604. VIDEO-TEXT MODELING WITH ZERO-SHOT TRANSFER FROM CONTRASTIVE CAPTIONERS (GOOGLE LLC)

From WikiPatents

VIDEO-TEXT MODELING WITH ZERO-SHOT TRANSFER FROM CONTRASTIVE CAPTIONERS

Organization Name

GOOGLE LLC

Inventor(s)

Shen Yan of Seattle WA US

Tao Zhu of Los Altos CA US

Zirui Wang of Mountain View CA US

Yuan Cao of Mountain View CA US

Jiahui Yu of Seattle WA US

VIDEO-TEXT MODELING WITH ZERO-SHOT TRANSFER FROM CONTRASTIVE CAPTIONERS

This abstract first appeared for US patent application 18694604 titled 'VIDEO-TEXT MODELING WITH ZERO-SHOT TRANSFER FROM CONTRASTIVE CAPTIONERS

Original Abstract Submitted

Provided is an efficient approach to establish a foundational video-text model for tasks including open-vocabulary video classification, text-to-video retrieval, video captioning and video question-answering. Some example implementations include a model which can be referred to as VideoCoCa. Example implementations reuse a pretrained image-text contrastive captioner (CoCa) model and adapt it to video-text tasks with little or minimal extra training. While previous works adapt image-text models with various cross-frame fusion modules (for example, cross-frame attention layer or perceiver resampler) and finetune the modified architecture on video-text data, aspects of the present disclosure leverage findings that the generative attentional pooling and contrastive attentional pooling layers in the image-text CoCa design are instantly adaptable to “flattened frame embeddings”, yielding a strong zero-shot transfer baseline for many video-text tasks.

Cookies help us deliver our services. By using our services, you agree to our use of cookies.