Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Visual System

Visual System

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...

Vision

Vision

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.

You might also read

Related Articles

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

Sort by

Same author

A Randomized Controlled Trial of Yizhi Kaiqiao Formula Combined With Repetitive Transcranial Magnetic Stimulation on Neurocognitive and Social Outcomes in Preschool Children With Autism Spectrum Disorder.

Developmental neurobiology·2026

Same author

Advancing high-altitude medicine: a model for the future.

Signal transduction and targeted therapy·2026

Same author

<sup>68</sup>Ga-Labeled LLP2A for PET Imaging of Very Late Antigen-4 in Acute Cardiac Rejection.

Molecular pharmaceutics·2026

Same author

Deciphering Object Concepts: Hierarchical Cross-Modal Relational Reasoning for Mining Object-Attribute-Affordance Associations.

IEEE transactions on pattern analysis and machine intelligence·2026

Same author

Validating a gamified size perception task for identifying cognitive profiles in children: a latent profile analysis of executive function and sensory measures.

Frontiers in psychology·2026

Same author

DARS2 serves as an independent prognostic factor and participates in multiple biological processes in bladder urothelial carcinoma.

Translational andrology and urology·2026

Search research articles

Related Experiment Video

Updated: Dec 9, 2025

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

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

Published on: December 15, 2023

Progressive Cross-Modal Semantic Network for Zero-Shot Sketch-Based Image Retrieval.

Cheng Deng, Xinxun Xu, Hao Wang

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society

|September 11, 2020

Summary

This study introduces a new network for zero-shot sketch-based image retrieval (ZS-SBIR). The progressive cross-modal semantic network improves retrieval accuracy by decoupling feature alignment and projection.

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Cross-Modal Multivariate Pattern Analysis

Cross-Modal Multivariate Pattern Analysis

Published on: November 9, 2011

Related Experiment Videos

Last Updated: Dec 9, 2025

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

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

Published on: December 15, 2023

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Cross-Modal Multivariate Pattern Analysis

Cross-Modal Multivariate Pattern Analysis

Published on: November 9, 2011

Area of Science:

Computer Science
Artificial Intelligence
Machine Learning

Background:

Zero-shot sketch-based image retrieval (ZS-SBIR) is challenging due to the need for knowledge transfer from seen to unseen classes.
Existing methods often couple feature projection and semantic alignment, hindering performance.

Purpose of the Study:

To propose a novel progressive cross-modal semantic network for ZS-SBIR.
To improve zero-shot retrieval performance by decoupling projection and alignment processes.

Main Methods:

Explicitly aligning sketch and image features to semantic features before projection.
Utilizing cross-reconstruction loss for complete modal knowledge capture.
Employing multi-modal Euclidean loss to ensure similarity between sketch-image retrieval features.

Main Results:

The proposed network achieves significant performance gains over state-of-the-art methods.
Outperforms competitors by over 3% on the Sketchy dataset and 6% on the TU-Berlin dataset.

Conclusions:

The novel approach effectively enhances ZS-SBIR performance.
Decoupling alignment and projection is crucial for successful cross-modal retrieval in zero-shot scenarios.