Tuesday, July 31, 2018

20th Century Fox researchers create AI model to predict audience for a movie


In a first, researchers from 20th Century Fox film studios have developed an Artificial Intelligence (AI)-powered model to predict what target audience will most likely see a movie. The prediction is done on the basis of the film’s trailer. Since video trailers are one of the most critical elements of marketing campaigns for new films, the model can provide an opportunity to filmmakers to make movies depending on the interests of general moviegoer population, easily communicate the plot of the movie to them, present the main characters, and reveal important hints about the story. 

This could also help them to understand what aspects of the movie the audience liked and what parts they did not. “These insights typically determine the strategy for the rest of the marketing campaign. In this paper we present a tool, which we call Merlin Video, that uses computer vision to create dense representations of the movie trailer, and uses those representations to predict customer behaviour. 

Movie studios have used computer vision before for video asset management and piracy detection. This is, to the extent of our knowledge, the first time that a studio uses low-level representation of movie trailers to extrapolate and predict customer interests,” the te researcher said.   Overview of Merlin Video’s hybrid recommendation model. 

The system extracts features such as colour, illumination, faces, objects and landscapes to achieve accurate attendance and audience prediction for existing movies, as well as yet-to-be-released films. “Using these prebuilt feature extractors, we are able to process hundreds of publicly available movie trailers, extract frame-by-frame low level features (e.g., a face, an object, etc) and create video-level representations. We use the video-level representations to train a hybrid Collaborative Filtering model that combines video features with historical movie attendance records. 

The trained model not only makes accurate attendance and audience prediction for existing movies, but also successfully profiles new movies six to eight months prior to their release,” the Fox researchers, including one of Indian-origin, wrote in their paper which has been published on ArXiv.org --  a repository of electronic preprints approved for publication after moderation. 

The team used NVIDIA Tesla P100 GPUs on the Google Cloud, with the cuDNN-accelerated TensorFlow deep learning framework to train their convolutional neural network on hundreds of movie trailers released over the last years, as well as millions of attendance records, the paper said. “By finding a suitable representation of these features, and by feeding them to a model that has access to historical movie attendance records, it is possible to find non-trivial associations between the video trailer features, and future audiences choices after the movie releases in theaters or on streaming services,” the researchers stated. Cover image courtesy: The3DLeopard

from Latest Technology News https://ift.tt/2NUw7yv

MAXIT INTERNET

BLOGGER

CD DVD RW

DELL

DOWNLOAD

FTP Server Linux

HACK

HARD DRIVE

HOW TO WORKIN

HARDWAER

INTERNET

INTERNET CAFE

LAPTOP

LENOVO

LINUX

Additional configuration for Samba Server (Part 2)  

BSNL/Airtel/Idea using Huawei E156G 3g Wireless USB Linux 5   

Basic File Extensions    CHANGING AN ACCOUNT EXPIRATION DATE   

Configure Linux as a Router   

Configure SAMBA Server (Part-1)   

Configure VNC server   

Configure Yum Server (Part-1)   

Configure yum server for Client machine (Part 3)   

Configuring Samba as a Standalone Server (Part 3)  

Connecting ftp Server with Anonymous User Part 5  

Create ftp account with Shared directory Part 3  

DHCP Server Configuration Part 2  

DHCP Server Configuration Part-1  

DHCP Server Configuration Part-3  

Enabling FTP Services in Yum Server (Part 5)  

FTP Server Configuration Part 1  

FTP Server How to Change In Primary DNS Server Part 2  

HTTP Client side configuration (Part 4)  

How to Vsftpd conf files Parameter Part 6   

LINUX FILE SYSTEM STRUCTURE  

Linux User Administrtion  

Linux as a Router configuration for Client Machine   

Linux client machine FileZilla FTP Client Part 4  

Local Yum Server (Part 2)  

Modifying Existing User Information  

Primary DNS Server Configuration Part-1  

Primary DNS Server Configuration Part-2    

Primary DNS Server Configuration Part-3  

Remove Linux From Your Pc Safely and restoring your MBR  

Sharing & Accessing Samba Share (Part 4)   

Speeding up your internet connection under Linux and Windows   

THE ROOT FILE SYSTEM   

VNC Server Configuration

LINUX LAB

Linux as a Router

MOTHERBOARD

Mobile

NETWORKING

REDHAT 5

REGISTRY EDTOR

RESET BIOS PASSWORD

SAMBA Server Linux

SERVER

SERVER CONFIG

SOFTWAER

VNC server Linux

Window 10

Window XP