English
Related papers

Related papers: KPTransfer: improved performance and faster conver…

200 papers

Accurate recognition of personally identifiable information (PII) is central to automated text anonymization. This paper investigates the effectiveness of cross-domain model transfer, multi-domain data fusion, and sample-efficient learning…

Computation and Language · Computer Science 2026-01-13 Junhong Ye , Xu Yuan , Xinying Qiu

We explore the importance of spatial contextual information in human pose estimation. Most state-of-the-art pose networks are trained in a multi-stage manner and produce several auxiliary predictions for deep supervision. With this…

Computer Vision and Pattern Recognition · Computer Science 2019-01-08 Hong Zhang , Hao Ouyang , Shu Liu , Xiaojuan Qi , Xiaoyong Shen , Ruigang Yang , Jiaya Jia

Pre-training a deep neural network on the ImageNet dataset is a common practice for training deep learning models, and generally yields improved performance and faster training times. The technique of pre-training on one task and then…

Machine Learning · Computer Science 2020-01-03 Nishai Kooverjee , Steven James , Terence van Zyl

The task of 2D human pose estimation is challenging as the number of keypoints is typically large (~ 17) and this necessitates the use of robust neural network architectures and training pipelines that can capture the relevant features from…

Machine Learning · Computer Science 2022-04-22 Kaushik Balakrishnan , Devesh Upadhyay

Neural Machine Translation (NMT) is a new approach for automatic translation of text from one human language into another. The basic concept in NMT is to train a large Neural Network that maximizes the translation performance on a given…

Computation and Language · Computer Science 2016-12-22 Markus Freitag , Yaser Al-Onaizan

Marker-free human pose estimation (HPE) has found increasing applications in various fields. Current HPE suffers from occasional errors in keypoint recognition and random fluctuation in keypoint trajectories when analyzing kinematic human…

Computer Vision and Pattern Recognition · Computer Science 2025-07-16 Chang Peng , Yifei Zhou , Huifeng Xi , Shiqing Huang , Chuangye Chen , Jianming Yang , Bao Yang , Zhenyu Jiang

Domain shift is a well known problem where a model trained on a particular domain (source) does not perform well when exposed to samples from a different domain (target). Unsupervised methods that can adapt to domain shift are highly…

Computer Vision and Pattern Recognition · Computer Science 2021-08-04 Botos Csaba , Xiaojuan Qi , Arslan Chaudhry , Puneet Dokania , Philip Torr

In this paper, we present MultiPoseNet, a novel bottom-up multi-person pose estimation architecture that combines a multi-task model with a novel assignment method. MultiPoseNet can jointly handle person detection, keypoint detection,…

Computer Vision and Pattern Recognition · Computer Science 2018-07-12 Muhammed Kocabas , Salih Karagoz , Emre Akbas

Performance on benchmark datasets has drastically improved with advances in deep learning. Still, cross-dataset generalization performance remains relatively low due to the domain shift that can occur between two different datasets. This…

Computer Vision and Pattern Recognition · Computer Science 2019-01-08 Alexandra Carlson , Katherine A. Skinner , Ram Vasudevan , Matthew Johnson-Roberson

While originally designed for image generation, diffusion models have recently shown to provide excellent pretrained feature representations for semantic segmentation. Intrigued by this result, we set out to explore how well…

Computer Vision and Pattern Recognition · Computer Science 2023-07-06 Rui Gong , Martin Danelljan , Han Sun , Julio Delgado Mangas , Luc Van Gool

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

In this paper we present a new approach to content-based transfer learning for solving the data sparsity problem in cases when the users' preferences in the target domain are either scarce or unavailable, but the necessary information on…

Machine Learning · Computer Science 2013-05-16 Naseem Biadsy , Lior Rokach , Armin Shmilovici

In this paper, we propose a novel learning framework for the problem of domain transfer learning. We map the data of two domains to one single common space, and learn a classifier in this common space. Then we adapt the common classifier to…

Machine Learning · Computer Science 2016-08-17 Ru-Ze Liang , Wei Xie , Weizhi Li , Hongqi Wang , Jim Jing-Yan Wang , Lisa Taylor

Multi-frame human pose estimation in complicated situations is challenging. Although state-of-the-art human joints detectors have demonstrated remarkable results for static images, their performances come short when we apply these models to…

Computer Vision and Pattern Recognition · Computer Science 2021-03-22 Zhenguang Liu , Haoming Chen , Runyang Feng , Shuang Wu , Shouling Ji , Bailin Yang , Xun Wang

In this paper, we propose a new method called ProfWeight for transferring information from a pre-trained deep neural network that has a high test accuracy to a simpler interpretable model or a very shallow network of low complexity and a…

Machine Learning · Computer Science 2018-11-20 Amit Dhurandhar , Karthikeyan Shanmugam , Ronny Luss , Peder Olsen

Domain shift in digital histopathology can occur when different stains or scanners are used, during stain translation, etc. A deep neural network trained on source data may not generalise well to data that has undergone some domain shift.…

Image and Video Processing · Electrical Eng. & Systems 2022-05-10 Zeeshan Nisar , Jelica Vasiljević , Pierre Gançarski , Thomas Lampert

The absence of well-structured large datasets in medical computer vision results in decreased performance of automated systems and, especially, of deep learning models. Domain generalization techniques aim to approach unknown domains from a…

Image and Video Processing · Electrical Eng. & Systems 2024-06-04 Nikolaos Spanos , Anastasios Arsenos , Paraskevi-Antonia Theofilou , Paraskevi Tzouveli , Athanasios Voulodimos , Stefanos Kollias

We develop a robust multi-scale structure-aware neural network for human pose estimation. This method improves the recent deep conv-deconv hourglass models with four key improvements: (1) multi-scale supervision to strengthen contextual…

Computer Vision and Pattern Recognition · Computer Science 2018-09-18 Lipeng Ke , Ming-Ching Chang , Honggang Qi , Siwei Lyu

We introduce an approach for image segmentation based on sparse correspondences between keypoints in testing and training images. Keypoints represent automatically identified distinctive image locations, where each keypoint correspondence…

Computer Vision and Pattern Recognition · Computer Science 2018-06-25 Christian Wachinger , Matthew Toews , Georg Langs , William Wells , Polina Golland

In the presence of large sets of labeled data, Deep Learning (DL) has accomplished extraordinary triumphs in the avenue of computer vision, particularly in object classification and recognition tasks. However, DL cannot always perform well…

Computer Vision and Pattern Recognition · Computer Science 2019-01-03 Mohammad Mahfujur Rahman , Clinton Fookes , Mahsa Baktashmotlagh , Sridha Sridharan