Humans need not label more humans: Occlusion Copy & Paste for Occluded Human Instance Segmentation

7 October 2022

Papers citing "Humans need not label more humans: Occlusion Copy & Paste for Occluded Human Instance Segmentation"

4 / 4 papers shown

Title
ForAug: Recombining Foregrounds and Backgrounds to Improve Vision Transformer Training with Bias Mitigation Tobias Christian Nauen Brian B. Moser Federico Raue Stanislav Frolov Andreas Dengel ViT 55 0 0 12 Mar 2025
SocialGPT: Prompting LLMs for Social Relation Reasoning via Greedy Segment Optimization Wanhua Li Zibin Meng Jiawei Zhou D. Wei Chuang Gan Hanspeter Pfister LRM VLM 27 5 0 28 Oct 2024
Improving 2D Human Pose Estimation in Rare Camera Views with Synthetic Data Miroslav Purkrábek Jivrí Matas 17 2 0 13 Jul 2023
Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation Golnaz Ghiasi Yin Cui A. Srinivas Rui Qian Tsung-Yi Lin E. D. Cubuk Quoc V. Le Barret Zoph ISeg 223 966 0 13 Dec 2020