Tencent AVS: A Holistic Ads Video Dataset for Multi-modal Scene Segmentation.

Jie Jiang Zhimin Li Jiangfeng Xiong Rongwei Quan Qinglin Lu Wei Liu

Published in: CoRR (2022)

Keyphrases

multi modal
scene segmentation
video dataset
video search
action recognition
video sequences
object tracking
video frames
video data
indoor scenes
keywords
video clips
high dimensional
visual information
audio visual
video streams
image features
image sequences