Semantic segmentation using regions and parts

We address the problem of segmenting and recognizing objects in real world images, focusing on challenging articulated categories such as humans and other animals. For this purpose, we propose a novel design for region-based object detectors that integrates efficiently top-down information from scanning-windows part models and global appearance cues. Our detectors produce class-specific scores for bottom-up regions, and then aggregate the votes of multiple overlapping candidates through pixel classification. We evaluate our approach on the PASCAL segmentation challenge, and report competitive performance with respect to current leading techniques. On VOC2010, our method obtains the best results in 6/20 categories and the highest performance on articulated objects.

• Publication year

  2012

• Venue

  2012 IEEE Conference on Computer Vision and Pattern Recognition

• Publication date

  2012-06-01

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1109/CVPR.2012.6248077
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Efficient Additive Kernels via Explicit Feature Maps

  2012cited by this paper
• Ensemble of exemplar-SVMs for object detection and beyond

  2011cited by this paper
• The truth about cats and dogs

  2011cited by this paper
• Object detection and segmentation from joint embedding of parts and pixels

  2011cited by this paper
• Contour Detection and Hierarchical Image Segmentation

  2011influential reference
• Object segmentation by alignment of poselet activations to image contours

  2011influential reference
• Smooth object retrieval using a bag of boundaries

  2011cited by this paper
• Object Recognition by Sequential Figure-Ground Ranking

  2011influential reference
• Efficient region search for object detection

  2011cited by this paper
• Semantic contours from inverse detectors

  2011cited by this paper
• Are spatial and global constraints really necessary for segmentation?

  2011cited by this paper
• Harmony Potentials

  2011cited by this paper
• Probabilistic Joint Image Segmentation and Labeling

  2011cited by this paper
• Segmentation as selective search for object recognition

  2011cited by this paper
• Image segmentation by figure-ground composition into maximal cliques

  2011cited by this paper
• Detecting People Using Mutually Consistent Poselet Activations

  2010cited by this paper
• Evaluating Color Descriptors for Object and Scene Recognition

  2010cited by this paper
• Object Detection with Discriminatively Trained Part Based Models

  2010cited by this paper
• Layered object detection for multi-class segmentation

  2010cited by this paper
• Category Independent Object Proposals

  2010cited by this paper
• What is an object?

  2010cited by this paper
• Energy minimization for linear envelope MRFs

  2010cited by this paper
• Graph Cut Based Inference with Co-occurrence Statistics

  2010cited by this paper
• Recognition using regions

  2009cited by this paper
• Poselets: Body part detectors trained using 3D human pose annotations

  2009cited by this paper
• Max-margin additive classifiers for detection

  2009cited by this paper
• Recognition by association via learning per-exemplar distances

  2008cited by this paper
• Combined Top-Down/Bottom-Up Segmentation

  2008cited by this paper
• Classification using intersection kernel support vector machines is efficient

  2008cited by this paper
• Connected Segmentation Tree — A joint representation of region layout and hierarchy

  2008cited by this paper
• The PASCAL Visual Object Classes Challenge

  2006cited by this paper
• Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories

  2006cited by this paper
• OBJ CUT

  2005cited by this paper
• Histograms of oriented gradients for human detection

  2005cited by this paper
• Learning a classification model for segmentation

  2003cited by this paper
• Robust Real-Time Face Detection

  2001cited by this paper
• Probabilistic Outputs for Support vector Machines and Comparisons to Regularized Likelihood Methods

  1999cited by this paper

• SHED Light on Segmentation for Dense Prediction

  2026cites this paper
• Taxonomy-Aware Representation Alignment for Hierarchical Visual Recognition with Large Multimodal Models

  2026cites this paper
• Generalized Event Partonomy Inference with Structured Hierarchical Predictive Learning

  2025cites this paper
• Geometric Feature Prompting of Image Segmentation Models

  2025cites this paper
• Vision LLMs Are Bad at Hierarchical Visual Understanding, and LLMs Are the Bottleneck

  2025cites this paper
• Robust Multi-Input Multi-Output Analysis for Crop Row Segmentation and Furrow Line Detection in Diverse Agricultural Fields

  2025cites this paper
• Autonomous Driving: Integration of Segmentation and Depth Camera in a Curriculum Learning Approach

  2025cites this paper
• Feasible Region Detection for Wheeled Climbing Robots Based on Lightweight Multi-Task Learning

  2025cites this paper
• A Review of Machine Learning and Deep Learning for Object Detection, Semantic Segmentation, and Human Action Recognition in Machine and Robotic Vision

  2024cites this paper
• RoVi-Aug: Robot and Viewpoint Augmentation for Cross-Embodiment Robot Learning

  2024cites this paper
• Uncertainty-Aware Source-Free Domain Adaptive Semantic Segmentation

  2023cites this paper
• Image Semantic Segmentation Used in Automatics

  2023cites this paper
• The Truth is Out There: Focusing on Smaller to Guess Bigger in Image Classification

  2023cites this paper
• Research on Positioning and dimension measurement of truck compartment based on Semantic segmentation in automatic loading system

  2023cites this paper
• Improved clothing segmentation algorithm based on Deeplabv3 + network

  2023cites this paper
• Segmentation of farmlands in aerial images by deep learning framework with feature fusion and context aggregation modules

  2023cites this paper
• Tunable Hybrid Proposal Networks for the Open World

  2022cites this paper
• A fast colorization method of grayscale image based on neural network

  2022cites this paper
• Semantically Enhanced Global Reasoning for Semantic Segmentation

  2022cites this paper
• Action recognition system

  2022cites this paper
• Framework-agnostic Semantically-aware Global Reasoning for Segmentation

  2022cites this paper
• Learnable Upsampling-Based Point Cloud Semantic Segmentation

  2022cites this paper
• Perceptual Grouping in Contrastive Vision-Language Models

  2022cites this paper
• RankSeg: Adaptive Pixel Classification with Image Category Ranking for Segmentation

  2022cites this paper
• GroupViT: Semantic Segmentation Emerges from Text Supervision

  2022cites this paper
• Based on DeepLab v3+ model to realize the road scene semantic segmentation

  2022cites this paper
• Object vs Pixel-based Flood/Drought Detection in Paddy Fields using Deep Learning

  2022cites this paper
• MLSeg: Image and Video Segmentation as Multi-Label Classification and Selected-Label Pixel Classification

  2022cites this paper
• AMICO: Amodal Instance Composition

  2022cites this paper
• Unsupervised Learning of the 4D Audio-Visual World from Sparse Unconstrained Real-World Samples

  2021cites this paper
• Optimizing Algorithms of Text Detection on Images for Mobile Device Using Structural Approaches

  2021cites this paper
• Research progress and trend analysis of computer vision based on cite space

  2021cites this paper
• Efficient Region Segmentation of PV Module in Infrared Imagery using Segnet

  2021cites this paper
• Learning Open-World Object Proposals without Learning to Classify

  2021cites this paper
• ACNet: Approaching-and-Centralizing Network for Zero-Shot Sketch-Based Image Retrieval

  2021cites this paper
• A comprehensive and systematic review on classical and deep learning based region proposal algorithms

  2021cites this paper
• Data Decomposition for Constrained Visual Learning

  2021influential citation
• Semantic segmentation of remote sensing image based on deep fusion networks and conditional random field

  2020cites this paper
• End-Face Localization and Segmentation of Steel Bar Based on Convolution Neural Network

  2020cites this paper
• A Stride-Based Convolution Decomposition Method to Stretch CNN Acceleration Algorithms for Efficient and Flexible Hardware Implementation

  2020cites this paper
• Application of Machine Learning in Computer Vision: A Brief Review

  2020cites this paper
• Collective Learning Ambiance of Human Pursuance with Intelligent Revival and Prediction Analysis

  2020cites this paper
• Few-Shot Learning With Geometric Constraints

  2020cites this paper
• Region Proposal Generation: A Hierarchical Merging Similarity-Based Algorithm

  2020cites this paper
• In-field detection of Alternaria solani in potato crops using hyperspectral imaging

  2020cites this paper
• Using ROC and Unlabeled Data for Increasing Low-Shot Transfer Learning Classification Accuracy

  2020cites this paper
• Motion-based object segmentation in video sequences

  2019cites this paper
• Visual attention for high speed driving

  2019cites this paper
• Quantifying the Presence of Graffiti in Urban Environments

  2019cites this paper
• Efficient Annotation and Knowledge Distillation for Semantic Segmentation

  2019cites this paper
• Figure-ground Image Segmentation via Semantic Information

  2019cites this paper
• Automated detection of third molars and mandibular nerve by deep learning

  2019cites this paper
• A Survey on Deep Learning-based Architectures for Semantic Segmentation on 2D Images

  2019cites this paper
• Learning Rich Representations For Structured Visual Prediction Tasks

  2019cites this paper
• Context-Enabled Extraction of Large-Scale Urban Functional Zones from Very-High-Resolution Images: A Multiscale Segmentation Approach

  2019cites this paper
• Object-Contextual Representations for Semantic Segmentation

  2019cites this paper
• TDCC: top-down semantic aggregation for colour constancy

  2019cites this paper
• Literature Review: Human Segmentation with Static Camera

  2019cites this paper
• Automating Interpretability: Discovering and Testing Visual Concepts Learned by Neural Networks

  2019cites this paper
• Region-based active learning for efficient labeling in semantic segmentation

  2019cites this paper
• Towards Automatic Concept-based Explanations

  2019cites this paper
• WRA: A 2.2-to-6.3 TOPS Highly Unified Dynamically Reconfigurable Accelerator Using a Novel Winograd Decomposition Algorithm for Convolutional Neural Networks

  2019cites this paper
• Computer vision for structural damage quantification: A novel residual deep learning based approach

  2018cites this paper
• Atmospheric Perspective Effect Transfer for Landscape Photographs

  2018cites this paper
• Rich Approach for Semantic Segmentation using Neuro-Fuzzy Technique

  2018cites this paper
• Graph-Based Semantic Segmentation

  2018cites this paper
• Image Annotation by a Hierarchical and Iterative Combination of Recognition and Segmentation

  2018cites this paper
• ANR HYEP ANR 14-CE22-0016-01Hyperspectral imagery forEnvironmental urban Planning HyepProgramme Mobilité et systèmes urbains 2014

  2018cites this paper
• Object Detection and Recognition Using Small Labeled Datasets

  2018cites this paper
• Modelling

  2018cites this paper
• FatRegion: A Fast Adaptive Tree-Structured Region Extraction Approach

  2018cites this paper
• Automated Data Generation for Training of Neural Networks by Recombining Previously Labeled Images

  2018cites this paper
• Automatic segmenting teeth in X-ray images: Trends, a novel data set, benchmarking and future perspectives

  2018cites this paper
• Normal Estimation of Surface in PointCloud Data for 3D Parts Segmentation

  2018cites this paper
• Figure-ground segmentation based on class-independent shape priors

  2018cites this paper
• Validating Few Contemporary Approaches in Image Segmentation – A Quantitative Approach

  2018cites this paper
• A Graph Theoretic Model for Semantic Annotation of Articulated Shape-Parts using Zernike Moment based Features

  2018cites this paper
• Fully convolutional network with cluster for semantic segmentation

  2018cites this paper
• Vision-Based High-Speed Driving With a Deep Dynamic Observer

  2018cites this paper
• Region Expansion Algorithm: A Well-Quality Region Proposal Generation

  2018cites this paper
• Beyond Grids: Learning Graph Representations for Visual Recognition

  2018cites this paper
• Image context for object detection, object context for part detection

  2018influential citation
• Hyperspectral Imagery for Environmental Urban Planning

  2018cites this paper
• Deep Learning for Generic Object Detection: A Survey

  2018cites this paper
• Representations for Visually Guided Actions

  2018cites this paper
• Identificação automática de pichação a partir de imagens urbanas

  2018cites this paper
• Improving Semantic Image Segmentation by Object Localization

  2018cites this paper
• A hybrid framework combining background subtraction and deep neural networks for rapid person detection

  2018influential citation
• Femur segmentation in DXA imaging using a machine learning decision tree

  2018cites this paper
• Utilization-based object recognition in confined spaces

  2017cites this paper
• Semantic annotation for complex video street views based on 2D-3D multi-feature fusion and aggregated boosting decision forests

  2017cites this paper
• An Efficient Evolutionary Based Method For Image Segmentation

  2017cites this paper
• Object shape extraction from cluttered bags

  2017cites this paper
• Tree-Structured Models for Efficient Multi-Cue Scene Labeling

  2017cites this paper
• Aggressive Deep Driving: Combining Convolutional Neural Networks and Model Predictive Control

  2017cites this paper
• Joint Multiple Visual Task Understanding from a Single Image via Deep Learning and Conditional Random Field

  2017cites this paper
• Severe-occluded 3D object identification via region-based descriptions

  2017cites this paper
• Aggressive Deep Driving: Model Predictive Control with a CNN Cost Model

  2017cites this paper
• Hierarchical joint-guided networks for semantic image segmentation

  2017cites this paper
• Exploring and Exploiting Diversity for Image Segmentation

  2017cites this paper