ModelVerificadoExterno

Videoprism Lvt Public v1 Base

Fuentehuggingface.co/keras/videoprism_lvt_public_v1_base/tree/cb4bc976ddba97d9d23853f1697dadb4649dea04

TipoOtherVersiónRevision cb4bc97Publicador@kerasCcalidad

Fuente del modelo

Tipo: Other
Tamaño del archivo: 946 MB
Versión: vRevision cb4bc97
Actualizado: 7 oct 2026
Publicador: @keras
Descargas: 5
Fuente: Hugging Face

Descripción de la fuente

Model Overview

Model Summary

VideoPrism is a family of foundational video-encoder models from Google Research, designed to be a universal "prism" for understanding the diverse facets of video content. Built on a massive scale of 36 million high-quality video-caption pairs and 582 million video clips, VideoPrism is engineered to excel across a wide range of video understanding tasks, including classification, localization, retrieval, and captioning. VideoPrism models utilize a Vision Transformer (ViT) architecture and are pre-trained using a combination of video-text contrastive learning and masked video modeling. This dual approach allows the model to capture both global semantic meaning and fine-grained spatio-temporal details, making it a powerful backbone for state-of-the-art video AI applications.

Installation

Keras and KerasHub can be installed with:

pip install -U -q keras-hub
pip install -U -q keras>=3

JAX, TensorFlow, and Torch come pre-installed in Kaggle Notebooks. For instructions on installing them in another environment, see the Keras Getting Started page.

Presets

The following model checkpoints are provided by the Keras team. For the Video-Text (LvT) variants, both the video encoder and the text encoder are provided to enable multimodal tasks like zero-shot retrieval.

Preset name	Parameters	Description
`videoprism_public_v1_base`	114.00M	114 million parameter, 12-layer ViT-B, 16-frame, 288x288 resolution, video-only encoder for spatio-temporal representation.
`videoprism_public_v1_large`	354.00M	354 million parameter, 24-layer ViT-L, 16-frame, 288x288 resolution, video-only encoder for spatio-temporal representation.
`videoprism_lvt_public_v1_base`	248.00M	248 million parameter, 12-layer ViT-B video encoder + text encoder, 16-frame, 288x288 resolution, for multimodal video-language tasks.
`videoprism_lvt_public_v1_large`	580.00M	580 million parameter, 24-layer ViT-L video encoder + text encoder, 16-frame, 288x288 resolution, for multimodal video-language tasks.

Fuentes

1 fuente

Hugging FacePrincipalVersión cb4bc976ddba97d9d23853f1697dadb4649dea04

huggingface.co/keras/videoprism_lvt_public_v1_base/tree/cb4bc976ddba97d9d23853f1697dadb4649dea04

Verificado 26 ago

Artefactos del modelo

1 artefacto

model.weights.h5

h5 · 946 MB · SHA-256 0233e2365d7f…f178 · Hugging Face

Descargar

Extractos de fuentes

3 extractos

Readme11 julhuggingface.co/keras/videoprism_lvt_public_v1_base

--- library_name: keras-hub --- ### Model Overview # Model Summary VideoPrism is a family of foundational video-encoder models from Google Research, designed to be a universal "prism" for understanding the diverse facets of video content. Built on a massive scale of 36 million high-quality video-caption pairs and 582 million video clips, VideoPrism is engineered to excel across a wide range of video understanding tasks, including classification, localization, retrieval, and captioning. VideoPrism models utilize a Vision Transformer (ViT) architecture and are pre-trained using a combination of video-text contrastive learning and masked video modeling. This dual approach allows the model to capture both global semantic meaning and fine-grained spatio-temporal details, making it a powerful backbone for state-of-the-art video AI applications. ## Links * [VideoPrism Technical Paper](https://arxiv.org/abs/2402.13250) * [VideoPrism API Documentation](https://keras.io/api/keras_hub/models/videoprism/) * [VideoPrism on Hugging Face](https://huggingface.co/google/videoprism-base-f16r288) * [KerasHub Beginner Guide](https://keras.io/guides/keras_hub/getting_started/) * [KerasHub Model Publishing Guide](https://keras.io/guides/keras_hub/upload/) ## Installation Keras and KerasHub can be installed with: ``` pip install -U -q keras-hub pip install -U -q keras>=3 ``` JAX, TensorFlow, and Torch come pre-installed in Kaggle Notebooks. For instructions on installing them in another environment, see the [Keras Getting Started](https://keras.io/getting_started/) page. ## Presets The following model checkpoints are provided by the Keras team. For the Video-Text (LvT) variants, both the video encoder and the text encoder are provided to enable multimodal tasks like zero-shot retrieval. | Preset name | Parameters | Description | |---------------------------------|------------|--------------------------------------------------------------------------------------------------------------------------------------------------| | `videoprism_public_v1_base` | 114.00M | 114 million parameter, 12-layer ViT-B, 16-frame, 288x288 resolution, video-only encoder for spatio-temporal representation. | | `videoprism_public_v1_large` | 354.00M | 354 million parameter, 24-layer ViT-L, 16-frame, 288x288 resolution, video-only encoder for spatio-temporal representation. | | `videoprism_lv...

Note26 agohuggingface.co/keras/videoprism_lvt_public_v1_base

Source context: 5 downloads · 0 likes · Library keras-hub · Repo keras/videoprism_lvt_public_v1_base

Note17 julhuggingface.co/keras/videoprism_lvt_public_v1_base

Source context: 2 downloads · 0 likes · Library keras-hub · Repo keras/videoprism_lvt_public_v1_base