English
Related papers

Related papers: Global Adaptation meets Local Generalization: Unsu…

200 papers

Domain adaptation remains a challenge when there is significant manifold discrepancy between source and target domains. Although recent methods leverage manifold-aware adversarial perturbations to perform data augmentation, they often…

Computer Vision and Pattern Recognition · Computer Science 2025-05-22 Hana Satou , F Monkey

Recent advances in deep learning for medical image segmentation demonstrate expert-level accuracy. However, in clinically realistic environments, such methods have marginal performance due to differences in image domains, including…

Computer Vision and Pattern Recognition · Computer Science 2019-06-13 Ling Zhang , Xiaosong Wang , Dong Yang , Thomas Sanford , Stephanie Harmon , Baris Turkbey , Holger Roth , Andriy Myronenko , Daguang Xu , Ziyue Xu

Existing self-supervised 3D human pose estimation schemes have largely relied on weak supervisions like consistency loss to guide the learning, which, inevitably, leads to inferior results in real-world scenarios with unseen poses. In this…

Computer Vision and Pattern Recognition · Computer Science 2022-03-30 Kehong Gong , Bingbing Li , Jianfeng Zhang , Tao Wang , Jing Huang , Michael Bi Mi , Jiashi Feng , Xinchao Wang

The accuracy and robustness of 3D human pose estimation (HPE) are limited by 2D pose detection errors and 2D to 3D ill-posed challenges, which have drawn great attention to Multi-Hypothesis HPE research. Most existing MH-HPE methods are…

Computer Vision and Pattern Recognition · Computer Science 2024-05-06 Xianzhou Zeng , Hao Qin , Ming Kong , Luyuan Chen , Qiang Zhu

In this paper, we propose a pose grammar to tackle the problem of 3D human pose estimation. Our model directly takes 2D pose as input and learns a generalized 2D-3D mapping function. The proposed model consists of a base network which…

Computer Vision and Pattern Recognition · Computer Science 2018-01-08 Haoshu Fang , Yuanlu Xu , Wenguan Wang , Xiaobai Liu , Song-Chun Zhu

The goal of 2D human pose estimation (HPE) is to localize anatomical landmarks, given an image of a person in a pose. SOTA techniques make use of thousands of labeled figures (finetuning transformers or training deep CNNs), acquired using…

Computer Vision and Pattern Recognition · Computer Science 2023-11-07 Nobline Yoo , Olga Russakovsky

With a proliferation of generic domain-adaptation approaches, we report a simple yet effective technique for learning difficult per-pixel 2.5D and 3D regression representations of articulated people. We obtained strong sim-to-real domain…

Computer Vision and Pattern Recognition · Computer Science 2020-07-31 Tyler Zhu , Per Karlsson , Christoph Bregler

Preference tuning aligns pretrained language models to human judgments of quality, helpfulness, or safety by optimizing over explicit preference signals rather than likelihood alone. Prior work has shown that preference-tuning degrades…

Computation and Language · Computer Science 2026-01-12 Constantinos Karouzos , Xingwei Tan , Nikolaos Aletras

Recent progress of self-supervised visual representation learning has achieved remarkable success on many challenging computer vision benchmarks. However, whether these techniques can be used for domain adaptation has not been explored. In…

Computer Vision and Pattern Recognition · Computer Science 2019-12-12 Jiaolong Xu , Liang Xiao , Antonio M. Lopez

2D-to-3D human pose lifting is an ill-posed problem due to depth ambiguity and occlusion. Existing methods relying on spatial and temporal consistency alone are insufficient to resolve these problems especially in the presence of…

Computer Vision and Pattern Recognition · Computer Science 2025-11-13 Longyun Liao , Rong Zheng

Domain adaptation (DA) addresses the real-world image classification problem of discrepancy between training (source) and testing (target) data distributions. We propose an unsupervised DA method that considers the presence of only…

Computer Vision and Pattern Recognition · Computer Science 2018-12-03 Debasmit Das , C. S. George Lee

Most existing human pose estimation (HPE) methods exploit multi-scale information by fusing feature maps of four different spatial sizes, \ie $1/4$, $1/8$, $1/16$, and $1/32$ of the input image. There are two drawbacks of this strategy: 1)…

Computer Vision and Pattern Recognition · Computer Science 2021-07-23 Zhengxiong Luo , Zhicheng Wang , Yan Huang , Liang Wang , Tieniu Tan , Erjin Zhou

Adversarial example detection, which can be conveniently applied in many scenarios, is important in the area of adversarial defense. Unfortunately, existing detection methods suffer from poor generalization performance, because their…

Computer Vision and Pattern Recognition · Computer Science 2024-12-05 Heqi Peng , Yunhong Wang , Ruijie Yang , Beichen Li , Rui Wang , Yuanfang Guo

Deep learning models such as convolutional neural networks and transformers have been widely applied to solve 3D object detection problems in the domain of autonomous driving. While existing models have achieved outstanding performance on…

Computer Vision and Pattern Recognition · Computer Science 2024-08-26 Ruixiao Zhang , Juheon Lee , Xiaohao Cai , Adam Prugel-Bennett

Machine learning algorithms have revolutionized different fields, including natural language processing, computer vision, signal processing, and medical data processing. Despite the excellent capabilities of machine learning algorithms in…

Image and Video Processing · Electrical Eng. & Systems 2022-12-07 Gita Sarafraz , Armin Behnamnia , Mehran Hosseinzadeh , Ali Balapour , Amin Meghrazi , Hamid R. Rabiee

3D human pose estimation can be handled by encoding the geometric dependencies between the body parts and enforcing the kinematic constraints. Recently, Transformer has been adopted to encode the long-range dependencies between the joints…

Computer Vision and Pattern Recognition · Computer Science 2022-03-28 Mohammed Hassanin , Abdelwahed Khamiss , Mohammed Bennamoun , Farid Boussaid , Ibrahim Radwan

Domain adaptation (DA) attempts to transfer the knowledge from a labeled source domain to an unlabeled target domain that follows different distribution from the source. To achieve this, DA methods include a source classification objective…

Machine Learning · Computer Science 2021-12-10 Fangrui Lv , Jian Liang , Kaixiong Gong , Shuang Li , Chi Harold Liu , Han Li , Di Liu , Guoren Wang

Action coordination in human structure is indispensable for the spatial constraints of 2D joints to recover 3D pose. Usually, action coordination is represented as a long-range dependence among body parts. However, there are two main…

Computer Vision and Pattern Recognition · Computer Science 2025-06-04 Mingjie Wei , Xuemei Xie , Yutong Zhong , Guangming Shi

In this paper, we concern on the bottom-up paradigm in multi-person pose estimation (MPPE). Most previous bottom-up methods try to consider the relation of instances to identify different body parts during the post processing, while…

Computer Vision and Pattern Recognition · Computer Science 2023-03-28 Ruoqi Yin , Jianqin Yin

The current state-of-the-art in monocular 3D human pose estimation is heavily influenced by weakly supervised methods. These allow 2D labels to be used to learn effective 3D human pose recovery either directly from images or via 2D-to-3D…

Computer Vision and Pattern Recognition · Computer Science 2020-10-26 Nikolas Klug , Moritz Einfalt , Stephan Brehm , Rainer Lienhart