data_juicer.ops.mapper.video_captioning_from_human_tracks_mapper module

class data_juicer.ops.mapper.video_captioning_from_human_tracks_mapper.VideoCaptioningFromHumanTracksMapper(*args, **kwargs)

基类：Mapper

Mapper to generate samples whose captions are generated based on a video-to-text model and sampled video frame.

Source: This operator is a part of HumanVBench (CVPR 2026).

__init__(human_track_query: str = "Descibe the person's apperance. Less than 80 words. ", trust_remote_code: bool = False, video_describe_model_path: str = 'DAMO-NLP-SG/VideoLLaMA3-7B', temp_video_path: str = None, tag_field_name_track_video_caption: str = 'track_video_caption', tag_field_name_video_track_is_child: str = 'video_track_is_child', *args, **kwargs)

Initialization method.

参数:

hf_video_blip -- video-blip model name on huggingface to generate caption

process_single(sample, rank=None)

For sample level, sample --> sample

参数:

sample -- sample to process

返回:

processed sample