Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Vision01:24

Vision

53.5K
Vision is the result of light being detected and transduced into neural signals by the retina of the eye. This information is then further analyzed and interpreted by the brain. First, light enters the front of the eye and is focused by the cornea and lens onto the retina—a thin sheet of neural tissue lining the back of the eye. Because of refraction through the convex lens of the eye, images are projected onto the retina upside-down and reversed.
53.5K
Visual Agnosia01:12

Visual Agnosia

234
Visual agnosia is a condition characterized by the inability to recognize visually presented objects despite having normal vision. For instance, a person with visual agnosia can describe the shape and color of an object but cannot identify or name it. This impairment does not affect their visual field, acuity, color vision, brightness discrimination, language, or memory. An example of this condition in a social setting is someone at a dinner party asking for "that silver thing with a round...
234
Visual System01:26

Visual System

613
Light enters the eye through the cornea, a transparent, dome-shaped surface covering the surface of the eyeball that helps to direct and focus incoming light. This light is then channeled toward the pupil, an adjustable opening whose size is controlled by the iris. The iris, a pigmented muscle, regulates the amount of light entering the eye by contracting or dilating the pupil, thereby ensuring optimal light levels for clear vision.
Once through the pupil, the light passes through the lens, a...
613

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Functional differentiation and interactions among inferior, medial frontal and posterior temporal cortex in semantic control.

Communications biology·2025
Same author

Convergence of mRNA technology and chimeric antigen receptor therapy: targeted technology optimizing targeted therapy.

Journal of translational medicine·2025
Same author

Multidimensional dynamic optical imaging unveils anesthetic-driven hemispheric lateralization in blood-brain barrier homeostasis.

Science advances·2025
Same author

Association of triglyceride-glucose-related indexes with mortality risk in RA: a prospective cohort study using the NHANES database.

Rheumatology (Oxford, England)·2025
Same author

Effects of the α-ketoglutaric acid on the performance, hair follicle development and antioxidant capacity of Rex rabbits.

Animal nutrition (Zhongguo xu mu shou yi xue hui)·2025
Same author

The impact of PICCO monitoring on traumatic shock: a systematic review and meta-analysis.

Frontiers in medicine·2025

Related Experiment Video

Updated: Jul 16, 2025

Eye Tracking During Visually Situated Language Comprehension: Flexibility and Limitations in Uncovering Visual Context Effects
07:36

Eye Tracking During Visually Situated Language Comprehension: Flexibility and Limitations in Uncovering Visual Context Effects

Published on: November 30, 2018

15.8K

Visual question generation for explicit questioning purposes based on target objects.

Jiayuan Xie1, Jiali Chen2, Wenhao Fang2

  • 1School of Software Engineering, South China University of Technology, Guangzhou, China; Key Laboratory of Big Data and Intelligent Robot (South China University of Technology), Ministry of Education, China; Department of Computing, Hong Kong Polytechnic University, Hong Kong, China.

Neural Networks : the Official Journal of the International Neural Network Society
|September 17, 2023
PubMed
Summary

This study introduces a novel content-controlled question generation model for images. It overcomes limitations of answer-based object identification, enabling more accurate and specific visual question generation.

Keywords:
Questioning purposesTarget objectVisual question generation

More Related Videos

Stimulus-specific Cortical Visual Evoked Potential Morphological Patterns
09:42

Stimulus-specific Cortical Visual Evoked Potential Morphological Patterns

Published on: May 12, 2019

6.1K
Using the Visual World Paradigm to Study Sentence Comprehension in Mandarin-Speaking Children with Autism
06:15

Using the Visual World Paradigm to Study Sentence Comprehension in Mandarin-Speaking Children with Autism

Published on: October 3, 2018

7.8K

Related Experiment Videos

Last Updated: Jul 16, 2025

Eye Tracking During Visually Situated Language Comprehension: Flexibility and Limitations in Uncovering Visual Context Effects
07:36

Eye Tracking During Visually Situated Language Comprehension: Flexibility and Limitations in Uncovering Visual Context Effects

Published on: November 30, 2018

15.8K
Stimulus-specific Cortical Visual Evoked Potential Morphological Patterns
09:42

Stimulus-specific Cortical Visual Evoked Potential Morphological Patterns

Published on: May 12, 2019

6.1K
Using the Visual World Paradigm to Study Sentence Comprehension in Mandarin-Speaking Children with Autism
06:15

Using the Visual World Paradigm to Study Sentence Comprehension in Mandarin-Speaking Children with Autism

Published on: October 3, 2018

7.8K

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Natural Language Processing

Background:

  • Visual question generation (VQG) typically relies on answers to identify target objects.
  • Current VQG methods struggle with ambiguous answers or answers describing relationships between multiple objects.
  • This limits the accuracy and completeness of question generation based on specific image content.

Purpose of the Study:

  • To propose a content-controlled question generation model that generates questions based on a specified set of target objects from an image.
  • To address the limitations of answer-guided object extraction in existing VQG approaches.
  • To enable more precise and controllable visual question generation.

Main Methods:

  • Developed a content-controlled question generation model.
  • Designed a recurrent generative architecture to manage attention to different objects and their image information.
  • Implemented explicit control over object contributions during question generation.

Main Results:

  • The proposed model demonstrates superior performance compared to state-of-the-art methods on VQA v2.0 and Visual7w datasets.
  • The model successfully generates questions based on specified content, overcoming ambiguity issues.
  • Experimental results validate the effectiveness of the recurrent architecture for content control.

Conclusions:

  • The proposed content-controlled VQG model offers a significant advancement over answer-dependent methods.
  • The recurrent generative architecture effectively handles object contributions for controlled question generation.
  • This approach enhances the accuracy and controllability of generating questions about specific image content.