Free Shipping on Order Over $60
AfterPay Available
Computational Methods for Integrating Vision and Language

Computational Methods for Integrating Vision and Language

by Kobus Barnard
Paperback
Publication Date: 30/04/2016
RRP  $108.90 $104.50
or 4 easy payments of $26.12 with
afterpay
This item qualifies for FREE delivery
Modeling data from visual and linguistic modalities together creates opportunities for better understanding of both, and supports many useful applications. Examples of dual visual-linguistic data includes images with keywords, video with narrative, and figures in documents. We consider two key task-driven themes: translating from one modality to another (e.g., inferring annotations for images) and understanding the data using all modalities, where one modality can help disambiguate information in another. The multiple modalities can either be essentially semantically redundant (e.g., keywords provided by a person looking at the image), or largely complementary (e.g., meta data such as the camera used). Redundancy and complementarity are two endpoints of a scale, and we observe that good performance on translation requires some redundancy, and that joint inference is most useful where some information is complementary.Computational methods discussed are broadly organized into ones for simple keywords, ones going beyond keywords toward natural language, and ones considering sequential aspects of natural language. Methods for keywords are further organized based on localization of semantics, going from words about the scene taken as whole, to words that apply to specific parts of the scene, to relationships between parts. Methods going beyond keywords are organized by the linguistic roles that are learned, exploited, or generated. These include proper nouns, adjectives, spatial and comparative prepositions, and verbs. More recent developments in dealing with sequential structure include automated captioning of scenes and video, alignment of video and text, and automated answering of questions about scenes depicted in images.
ISBN:
9781608451128
9781608451128
Category:
Computer vision
Format:
Paperback
Publication Date:
30-04-2016
Publisher:
Morgan & Claypool Publishers
Country of origin:
United States
Pages:
227
Dimensions (mm):
235x190x12mm
Weight:
0.4kg

This title is in stock with our Australian supplier and arrives at our Sydney warehouse within 7-10 working days of you placing an order.

Once received into our warehouse we will despatch it to you with a Shipping Notification which includes online tracking.

Please check the estimated delivery times below for your region, for after your order is despatched from our warehouse:

ACT Metro 2 working days

NSW Metro 2 working days 

NSW Rural 2-3 working days

NSW Remote 2-5 working days

NT Metro 3-6 working days

NT Remote 4-10 working days

QLD Metro 2-4 working days

QLD Rural 2-5 working days

QLD Remote 2-7 working days

SA Metro 2-5 working days

SA Rural 3-6 working days

SA Remote 3-7 working days

TAS Metro 3-6 working days

TAS Rural 3-6 working days

VIC Metro 2-3 working days

VIC Rural 2-4 working days

VIC Remote 2-5 working days

WA Metro 3-6 working days

WA Rural 4-8 working days

WA Remote 4-12 working days

You can find this item in:

Customer Reviews

Be the first to review Computational Methods for Integrating Vision and Language.