Jove
Visualize
Contact Us

Related Concept Videos

Multi-input and Multi-variable systems01:22

Multi-input and Multi-variable systems

275
Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence of...
275
Visual System01:26

Visual System

1.4K
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...
1.4K

You might also read

Related Articles

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

Sort by
Same author

Design and Implementation of a Novel IoT Architecture for Data Release System Between Multiple Platforms: Case of Smart Offshores.

Sensors (Basel, Switzerland)·2025
Same author

AC-YOLO: A lightweight ship detection model for SAR images based on YOLO11.

PloS one·2025
Same author

TBKIN: Threshold-based explicit selection for enhanced cross-modal semantic alignments.

PloS one·2025
Same author

A Video Target Tracking and Correction Model with Blockchain and Robust Feature Location.

Sensors (Basel, Switzerland)·2023
Same author

An effective spatial relational reasoning networks for visual question answering.

PloS one·2022
Same author

Pre-training Model Based on Parallel Cross-Modality Fusion Layer.

PloS one·2022
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 Experiment Video

Updated: Nov 28, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

824

Multi-Modal Explicit Sparse Attention Networks for Visual Question Answering.

Zihan Guo1, Dezhi Han1

  • 1College of Information Engineering, Shanghai Maritime University, Shanghai 201306, China.

Sensors (Basel, Switzerland)
|December 1, 2020
PubMed
Summary
This summary is machine-generated.

This study introduces Multi-modal Explicit Sparse Attention Networks (MESAN) for visual question answering (VQA). MESAN improves VQA accuracy by focusing attention on relevant image and text features, reducing distractions from irrelevant information.

Keywords:
attention mechanismcomputer visionnatural language processingsparse attentionvisual question answering

More Related Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

657

Related Experiment Videos

Last Updated: Nov 28, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

824
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

657

Area of Science:

  • Artificial Intelligence
  • Computer Vision
  • Natural Language Processing

Background:

  • Visual Question Answering (VQA) integrates computer vision and natural language processing.
  • Current VQA models use dense co-attention, which can lead to attention distraction from irrelevant information.
  • There is a need for more efficient attention mechanisms in VQA.

Purpose of the Study:

  • To propose a novel model, Multi-modal Explicit Sparse Attention Networks (MESAN), for VQA.
  • To address the issue of attention distraction in VQA models by explicitly selecting relevant features.
  • To enhance VQA performance through a sparse attention mechanism.

Main Methods:

  • Developed MESAN, a model employing explicit sparse attention.
  • Utilized a top-k selection method to concentrate attention on the most relevant input features.
  • Evaluated the model on the VQA v2 benchmark dataset.

Main Results:

  • Achieved 70.71% overall accuracy on the VQA v2 test-dev set and 71.08% on the test-std set with the best single model.
  • Demonstrated superior attended features compared to other advanced models via attention visualization.
  • Confirmed the effectiveness of sparse attention mechanisms in VQA.

Conclusions:

  • MESAN effectively reduces attention distraction by focusing on relevant features.
  • Sparse attention mechanisms can achieve competitive performance in VQA.
  • The proposed approach has the potential to advance VQA model development and AI applications.