4D Effect Video Classification with Shot-Aware Frame Selection and Deep Neural Networks

A 4D effect video played at cinema or other designated places is a video annotated with physical effects such as motion, vibration, wind, flashlight, water spray, and scent. In order to automate the time-consuming and labor-intensive process of creating such videos, we propose a new method to classi...

Full description

Saved in:
Bibliographic Details
Main Authors: Siadari, Thomhert S., Mikyong Han, Hyunjin Yoon
Format: Conference Proceeding
Language:English
Subjects:
Motion pictures
Neural networks
Three-dimensional displays
Two dimensional displays
Vibrations
Visualization
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A 4D effect video played at cinema or other designated places is a video annotated with physical effects such as motion, vibration, wind, flashlight, water spray, and scent. In order to automate the time-consuming and labor-intensive process of creating such videos, we propose a new method to classify videos into 4D effect types with shot-aware frame selection and deep neural networks (DNNs). Shot-aware frame selection is a process of selecting video frames across multiple shots based on the shot length ratios to subsample every video down to a fixed number of frames for classification. For empirical evaluation, we collect a new dataset of 4D effect videos where most of the videos consist of multiple shots. Our extensive experiments show that the proposed method consistently outperforms DNNs without considering multi-shot aspect by up to 8.8% in terms of mean average precision.
ISSN:2473-9944
DOI:10.1109/ICCVW.2017.139