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

Search research articles

Related Experiment Video

Updated: Mar 17, 2026

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

Scale-Aware Pixelwise Object Proposal Networks.

Zequn Jie, Xiaodan Liang, Jiashi Feng

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

|July 23, 2016

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

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

Sort by

Same author

Semantic Frame Interpolation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026

Same author

Aligning Perception, Reasoning, Modeling and Interaction: A Survey on Physical AI.

IEEE transactions on pattern analysis and machine intelligence·2026

Same author

MagicSeg: Open-World Segmentation Pretraining via Counterfactural Diffusion-Based Auto-Generation.

IEEE transactions on pattern analysis and machine intelligence·2026

Same author

Multifunctional composite microgels: From structural design to biomedical applications.

Materials today. Bio·2026

Same author

EvolveNav: Empowering LLM-Based Vision-Language Navigation via Self-Improving Embodied Reasoning.

IEEE transactions on pattern analysis and machine intelligence·2026

Same author

DrawMotion: Generating 3D Human Motions by Freehand Drawing.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

Through the Looking Glass: A Dual Perspective on Weakly-Supervised Few-Shot Segmentation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026

Same journal

Mask-guided Asymmetric Contrastive and Semantic Alignment for Unsupervised Person Re-Identification.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026

Same journal

Hyperbolic Cycle Alignment for Infrared-Visible Image Fusion.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026

Same journal

Learning Gaze Synthesizer via 3D-eye Controlled Diffusion and Cross-domain Feature Alignment.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026

Same journal

Underlying Semantic Diffusion for Effective and Efficient In-Context Learning.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026

Same journal

DiffRES: Unleashing Text-to-Image Diffusion Models for Generative Referring Expression Segmentation without Information Leakage.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026

See all related articles

This study introduces a scale-aware pixelwise object proposal network (SPOP-net) that improves object detection accuracy, especially for small objects. The novel SPOP-net achieves high recall and localization precision, outperforming existing methods.

Area of Science:

Computer Vision
Machine Learning
Deep Learning

Background:

Object proposal is crucial for object detection but current methods lack localization accuracy, particularly for small objects.
Small objects are common in real-world scenarios, posing a significant challenge for existing object proposal techniques.

Purpose of the Study:

To develop a novel scale-aware pixelwise object proposal network (SPOP-net) for enhanced object detection.
To address the limitations of existing methods in generating accurate object proposals, especially for small-scale objects.

Main Methods:

A fully convolutional network predicts object proposal locations for each pixel, creating an ensemble of pixelwise proposals.
Two specialized localization networks, employing a divide-and-conquer strategy, handle objects of different scales.

More Related Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Related Experiment Videos

Last Updated: Mar 17, 2026

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

A large-/small-size weighting network adaptively combines outputs from the localization networks for final proposal generation.

Main Results:

The SPOP-net generates proposals with high recall rates and average best overlap, even for small objects.
Evaluations on PASCAL VOC 2007 and COCO 2014 datasets demonstrate SPOP-net's superiority over state-of-the-art models.
High-quality proposals from SPOP-net significantly improve the mean average precision in object detection frameworks.

Conclusions:

The proposed SPOP-net effectively tackles the challenges of object proposal generation, particularly for small objects.
SPOP-net exhibits strong generalization capabilities, as evidenced by its performance on the ILSVRC 2013 validation set.
The SPOP-net offers a computationally efficient method for generating high-quality object proposals, advancing object detection research.