CoChat
Sign Up
Cited by 245Advanced Neural Network ApplicationsHuman Pose and Action RecognitionDomain Adaptation and Few-Shot Learning

The DOI matches its Crossref record; 34 of the 35 references it cites were found in a registry or an index.

Human Parsing with Contextualized Convolutional Neural Network

Liang, Xiaodan, Xu, Chunyan, Shen, Xiaohui, Yang, Jianchao, Liu, Si, Tang, Jinhui, Lin, Liang, Yan, Shuicheng·2015·2015 IEEE International Conference on Computer Vision (ICCV)
DOI 10.1109/iccv.2015.163
Open this paper in CoChat — free account

Abstract

In this work, we address the human parsing task with a novel Contextualized Convolutional Neural Network (Co-CNN) architecture, which well integrates the cross-layer context, global image-level context, within-super-pixel context and cross-super-pixel neighborhood context into a unified network. Given an input human image, Co-CNN produces the pixel-wise categorization in an end-to-end way. First, the cross-layer context is captured by our basic local-to-global-to-local structure, which hierarchically combines the global semantic structure and the local fine details within the cross-layers. Second, the global image-level label prediction is used as an auxiliary objective in the intermediate layer of the Co-CNN, and its outputs are further used for guiding the feature learning in subsequent convolutional layers to leverage the global image-level context. Finally, to further utilize the local super-pixel contexts, the within-super-pixel smoothing and cross-super-pixel neighbourhood voting are formulated as natural sub-components of the Co-CNN to achieve the local label consistency in both training and testing process. Comprehensive evaluations on two public datasets well demonstrate the significant superiority of our Co-CNN architecture over other state-of-the-arts for human parsing. In particular, the F-1 score on the large dataset [15] reaches 76.95% by Co-CNN, significantly higher than 62.81% and 64.38% by the state-of-the-art algorithms, M-CNN [21] and ATR [15], respectively.

Overview

Integrity signals

Registry

Crossref · 10.1109/iccv.2015.163

Cites

34 of 34 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Citations

Cites

Flagged first, then by citations

1 of the 35 references couldn’t be matched to a known paper.

Research works printed but not linked: 2

  1. george, 2015, Weakly-and semi-supervised learning of a denn for semantic image segmentation, ICCV
  2. george papandreou, 2015, Weakly- and semi-supervised learning of a denn for semantic image segmentation, I CCV

Cited by

Sorted by citations

See all 245

Related

See all

Metadata

Authors
Liang, X., Xu, C., Shen, X., Yang, J., Liu, S., Tang, J., Lin, L., & Yan, S.
Affiliations
  • Sun Yat-sen University (CN)
  • National University of Singapore (SG)
  • Adobe Systems (United States) (US)
  • Snap (United States) (US)
  • Chinese Academy of Sciences (CN)
  • Nanjing University of Science and Technology (CN)
ORCID
Venue
2015 IEEE International Conference on Computer Vision (ICCV)
Publisher
IEEE
Published
2015-12
Pages
1386-1394
DOI
10.1109/iccv.2015.163
OpenAlex
W2204578866
Cited by
245
References
35
Citations by year
2026: 6 · 2025: 8 · 2024: 22 · 2023: 16 · 2022: 28 · 2021: 28 · 2020: 26 · 2019: 38 · 2018: 28 · 2017: 31 · 2016: 13 · 2015: 1
FWCI
9.98
Type
conference paper
Language
en
Open access
closed
Locations
IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Human Pose and Action Recognition
  • Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
Keywords
human parsing, hierarchical feature learning

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review