paper-with-me

Human Instance Segmentation

1개 벤치마크 · 논문 18편 · 이 태스크의 논문 보기 →

Benchmarks

OCHuman

결과 36개

Most implemented

Papers

SAM-pose2seg: Pose-Guided Human Instance Segmentation in Crowds

2026-01-13 · Constantin Kolomiiets, Miroslav Purkrabek, Jiri Matas arxiv

Segment Anything (SAM) provides an unprecedented foundation for human segmentation, but may struggle under occlusion, where keypoints may be partially or fully invisible. We adapt SAM 2.1 for pose-guided segmentation wit…

Human Instance Segmentation

Leveraging Multi-View Weak Supervision for Occlusion-Aware Multi-Human Parsing

2025-09-12 · Laura Bragagnolo, Matteo Terreran, Leonardo Barcellona, Stefano Ghidoni arxiv

Multi-human parsing is the task of segmenting human body parts while associating each part to the person it belongs to, combining instance-level and part-level information for fine-grained human understanding. In this wo…

Human Instance SegmentationMulti-Human Parsing

Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle

2024-12-02 · arXiv 2024 12 · Miroslav Purkrabek, Jiri Matas

Human pose estimation methods work well on separated people but struggle with multi-body scenarios. Recent work has addressed this problem by conditioning pose estimation with detected bounding boxes or bottom-up-estimat…

Human Instance SegmentationPose-Based Human Instance SegmentationPose EstimationSegmentation

Crowd-SAM: SAM as a Smart Annotator for Object Detection in Crowded Scenes

2024-07-16 · Zhi Cai, Yingjie Gao, Yaoyan Zheng, Nan Zhou 외

In computer vision, object detection is an important task that finds its application in many scenarios. However, obtaining extensive labels can be challenging, especially in crowded scenes. Recently, the Segment Anything…

Human Instance SegmentationInstance Segmentationobject-detectionObject Detection+1

You Only Learn One Query: Learning Unified Human Query for Single-Stage Multi-Person Multi-Task Human-Centric Perception

2023-12-09 · Sheng Jin, Shuhuai Li, Tong Li, Wentao Liu 외

Human-centric perception (e.g. detection, segmentation, pose estimation, and attribute analysis) is a long-standing problem for computer vision. This paper introduces a unified and versatile framework (HQNet) for single-…

AttributeHuman Instance SegmentationMulti-Task LearningPose Estimation

Object-Centric Multi-Task Learning for Human Instances

2023-03-13 · Hyeongseok Son, Sangil Jung, Solae Lee, Seongeun Kim 외

Human is one of the most essential classes in visual recognition tasks such as detection, segmentation, and pose estimation. Although much effort has been put into individual tasks, multi-task learning for these three ta…

Human DetectionHuman Instance SegmentationMulti-Task LearningObject+2

전체 18편 보기 →