Video-Text Retrieval Embedding with BridgeFormer

author: Jinling Xu

Description

This operator extracts features for video or text with BridgeFormer which can generate embeddings for text and video by jointly training a video encoder and text encoder to maximize the cosine similarity.

Code Example

Load a video from path './demo_video.mp4' to generate a video embedding.

Read the text 'kids feeding and playing with the horse' to generate a text embedding.

• Encode video (default):

from towhee import pipe, ops, DataCollection

p = (
    pipe.input('video_path') \
        .map('video_path', 'video_frames', ops.video_decode.ffmpeg()) \
        .map('video_frames', 'vec', ops.video_text_embedding.bridge_former(model_name='frozen_model', modality='video')) \
        .output('video_path', 'video_frames', 'vec')
)

DataCollection(p('./demo_video.mp4')).show()

• Encode text:

from towhee import pipe, ops, DataCollection

p = (
    pipe.input('text') \
        .map('text', 'vec', ops.video_text_embedding.bridge_former(model_name='frozen_model', modality='text')) \
        .output('text', 'vec')
)

DataCollection(p('kids feeding and playing with the horse')).show()

Factory Constructor

Create the operator via the following factory method

bridge_former(model_name, modality, weight_path)

Parameters:

​ model_name: str

​ The model name of frozen in time. Supported model names:

• frozen_model
• clip_initialized_model

​ modality: str

​ Which modality(video or text) is used to generate the embedding.

​ weight_path: str

​ pretrained model weights path.

Interface

An video-text embedding operator takes a list of Towhee VideoFrame or string as input and generate an embedding in ndarray.

Parameters:

​ data: List[towhee.types.Image] or str

​ The data (list of Towhee VideoFrame (which is uniform subsampled from a video) or text based on specified modality) to generate embedding.

Returns: numpy.ndarray

​ The data embedding extracted by model.