computer-vision-5

Human Part Segmentation

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in human-part-segmentation-11

Trend

Dataset

Best Model

Actions

PASCAL-Part

CIHP

Human3.6M

Libraries

i

Use these libraries to find human-part-segmentation-11 models and implementations

Datasets

Human3.6M

PASCAL-Part

CIHP

MHP

Pascal Panoptic Parts

Cityscapes Panoptic Parts

Subtasks

No subtasks available.

Most implemented papers

Mask R-CNN

Kaiming He, Georgia Gkioxari, Ross B. Girshick, Piotr Dollár•Sun Mar 19 2017

This work presents a conceptually simple, flexible, and general framework for object instance segmentation, which extends Faster R-CNN by adding a branch for predicting an object mask in parallel with the existing branch for bounding box recognition.

30711

Content

MHP v2.0

PASCAL-Person-Part

ATR

0

Cityscapes-Panoptic-Parts and PASCAL-Panoptic-Parts datasets for Scene Understanding

Daan de Geus, Panagiotis Meletis, Chenyang Lu, Xiaoxiao Wen, Gijs Dubbelman•Wed Apr 15 2020

This report describes the format of the two datasets, the annotation protocols, the merging strategies, and presents the datasets statistics.

18 0

Paper Graph

Learning from Synthetic Humans

Gül Varol, I. Laptev, Michael J. Black, J. Romero, C. Schmid, Naureen Mahmood, Xavier Martin•Wed Jan 04 2017

This work presents SURREAL (Synthetic hUmans foR REAL tasks): a new large-scale dataset with synthetically-generated but realistic images of people rendered from 3D sequences of human motion capture data and shows that CNNs trained on this synthetic dataset allow for accurate human depth estimation and human part segmentation in real RGB images.

1025 0

Paper Graph

Parsing R-CNN for Instance-Level Human Analysis

Q. Song, Lu Yang, Zhihui Wang, Ming Jiang•Thu Nov 29 2018

This paper presents an end-to-end pipeline for solving the instance-level human analysis, named Parsing R-CNN, which processes a set of human instances simultaneously through comprehensive considering the characteristics of region-based approach and the appearance of a human, thus allowing representing the details of instances.

131 0

Paper Graph

Self-Correction for Human Parsing

Yunchao Wei, Yezhou Yang, Yunqiu Xu, Peike Li•Mon Oct 21 2019

This work introduces a noise-tolerant method, called Self-Correction for Human Parsing (SCHP), to progressively promote the reliability of the supervised labels as well as the learned models, and is model-agnostic and can be applied to any human parsing models for further enhancing their performance.

404 0

Paper Graph

Hulk: A Universal Knowledge Translator for Human-Centric Tasks

Wanli Ouyang, Shixiang Tang, Tong He, Yizhou Wang, Yixuan Wu, Weizhen He, Xun Guo, Feng Zhu, Lei Bai, Rui Zhao, Jian Wu•Sun Dec 03 2023

Hulk is presented, the first multimodal human-centric generalist model, capable of addressing 2D vision, 3D vision, skeleton-based, and vision-language tasks without task-specific finetuning, and achieving state-of-the-art performance on 12 benchmarks.

22 0

Paper Graph

Sapiens: Foundation for Human Vision Models

Timur M. Bagautdinov, Rawal Khirodkar, Julieta Martinez, Zhaoen Su, Austin James, Peter Selednik, Stuart Anderson, Shunsuke Saito•Wed Aug 21 2024

Sapiens is a family of models for four fundamental human-centric vision tasks -- 2D pose estimation, body-part segmentation, depth estimation, depth estimation, and surface normal prediction that consistently surpasses existing baselines across various human-centric benchmarks.

177 0

Paper Graph

Weakly and Semi Supervised Human Body Part Parsing via Pose-Guided Knowledge Transfer

Haoshu Fang, Yu-Wing Tai, Cewu Lu, Guansong Lu, Xiaolin Fang, Jianwen Xie•Thu May 10 2018

A novel method to generate synthetic human part segmentation data using easily-obtained human keypoint annotations to exploit the anatomical similarity among human to transfer the parsing results of a person to another person with similar pose.

127 0

Paper Graph

Adding a benchmark result helps the community track progress.