Generating Persuasive Visual Storylines for Promotional Videos

08/30/2019
by   Chang Liu, et al.
0

Video contents have become a critical tool for promoting products in E-commerce. However, the lack of automatic promotional video generation solutions makes large-scale video-based promotion campaigns infeasible. The first step of automatically producing promotional videos is to generate visual storylines, which is to select the building block footage and place them in an appropriate order. This task is related to the subjective viewing experience. It is hitherto performed by human experts and thus, hard to scale. To address this problem, we propose WundtBackpack, an algorithmic approach to generate storylines based on available visual materials, which can be video clips or images. It consists of two main parts, 1) the Learnable Wundt Curve to evaluate the perceived persuasiveness based on the stimulus intensity of a sequence of visual materials, which only requires a small volume of data to train; and 2) a clustering-based backpacking algorithm to generate persuasive sequences of visual materials while considering video length constraints. In this way, the proposed approach provides a dynamic structure to empower artificial intelligence (AI) to organize video footage in order to construct a sequence of visual stimuli with persuasive power. Extensive real-world experiments show that our approach achieves close to 10 by human testers, and 12.5 performing state-of-the-art approach.

READ FULL TEXT

page 8

page 9

research
12/17/2021

AI-Empowered Persuasive Video Generation: A Survey

Promotional videos are rapidly becoming a popular medium for persuading ...
research
05/03/2015

Sequence to Sequence -- Video to Text

Real-world videos often have complex dynamics; and methods for generatin...
research
09/13/2018

LiveBot: Generating Live Video Comments Based on Visual and Textual Contexts

We introduce the task of automatic live commenting. Live commenting, whi...
research
07/29/2018

Bridge the Gap Between VQA and Human Behavior on Omnidirectional Video: A Large-Scale Dataset and a Deep Learning Model

Omnidirectional video enables spherical stimuli with the 360 × 180^ ∘ vi...
research
03/28/2017

Towards Automatic Learning of Procedures from Web Instructional Videos

The potential for agents, whether embodied or software, to learn by obse...
research
11/23/2017

Deep Video Generation, Prediction and Completion of Human Action Sequences

Current deep learning results on video generation are limited while ther...
research
01/28/2021

HEMVIP: Human Evaluation of Multiple Videos in Parallel

In many research areas, for example motion and gesture generation, objec...

Please sign up or login with your details

Forgot password? Click here to reset