English
Related papers

Related papers: TransPose: Keypoint Localization via Transformer

200 papers

Convolution neural networks (CNNs) have succeeded in compressive image sensing. However, due to the inductive bias of locality and weight sharing, the convolution operations demonstrate the intrinsic limitations in modeling the long-range…

Image and Video Processing · Electrical Eng. & Systems 2022-01-03 Dongjie Ye , Zhangkai Ni , Hanli Wang , Jian Zhang , Shiqi Wang , Sam Kwong

Although many approaches for multi-human pose estimation in videos have shown profound results, they require densely annotated data which entails excessive man labor. Furthermore, there exists occlusion and motion blur that inevitably lead…

Computer Vision and Pattern Recognition · Computer Science 2022-07-29 Kyung-Min Jin , Gun-Hee Lee , Seong-Whan Lee

This paper addresses the problem of cross-dataset generalization of 3D human pose estimation models. Testing a pre-trained 3D pose estimator on a new dataset results in a major performance drop. Previous methods have mainly addressed this…

Computer Vision and Pattern Recognition · Computer Science 2022-03-17 Mohsen Gholami , Bastian Wandt , Helge Rhodin , Rabab Ward , Z. Jane Wang

Transformers have proven superior performance for a wide variety of tasks since they were introduced. In recent years, they have drawn attention from the vision community in tasks such as image classification and object detection. Despite…

Computer Vision and Pattern Recognition · Computer Science 2022-10-03 Yihong Xu , Yutong Ban , Guillaume Delorme , Chuang Gan , Daniela Rus , Xavier Alameda-Pineda

Place recognition is a cornerstone of vehicle navigation and mapping, which is pivotal in enabling systems to determine whether a location has been previously visited. This capability is critical for tasks such as loop closure in…

Computer Vision and Pattern Recognition · Computer Science 2025-06-06 Zhenyu Li , Tianyi Shang , Pengjie Xu , Zhaojun Deng

Estimating the 6-DoF pose of a rigid object from a single RGB image is a crucial yet challenging task. Recent studies have shown the great potential of dense correspondence-based solutions, yet improvements are still needed to reach…

Computer Vision and Pattern Recognition · Computer Science 2023-08-15 Ruyi Lian , Haibin Ling

We present a deep learning-based multi-task approach for head pose estimation in images. We contribute with a network architecture and training strategy that harness the strong dependencies among face pose, alignment and visibility, to…

Computer Vision and Pattern Recognition · Computer Science 2022-02-07 Roberto Valle , José Miguel Buenaposada , Luis Baumela

We present a vehicle self-localization method using point-based deep neural networks. Our approach processes measurements and point features, i.e. landmarks, from a high-definition digital map to infer the vehicle's pose. To learn the best…

Computer Vision and Pattern Recognition · Computer Science 2021-07-19 Nico Engel , Vasileios Belagiannis , Klaus Dietmayer

We propose the first direct end-to-end multi-person pose estimation framework, termed DirectPose. Inspired by recent anchor-free object detectors, which directly regress the two corners of target bounding-boxes, the proposed framework…

Computer Vision and Pattern Recognition · Computer Science 2019-11-26 Zhi Tian , Hao Chen , Chunhua Shen

Local feature matching is a computationally intensive task at the subpixel level. While detector-based methods coupled with feature descriptors struggle in low-texture scenes, CNN-based methods with a sequential extract-to-match pipeline,…

Computer Vision and Pattern Recognition · Computer Science 2022-09-27 Qing Wang , Jiaming Zhang , Kailun Yang , Kunyu Peng , Rainer Stiefelhagen

Next-step location prediction plays a pivotal role in modeling human mobility, underpinning applications from personalized navigation to strategic urban planning. However, approaches that assume a closed world - restricting choices to a…

Artificial Intelligence · Computer Science 2025-08-05 Zhehong Ren , Tianluo Zhang , Yiheng Lu , Yushen Liang , Promethee Spathis

Recently, multi-resolution networks (such as Hourglass, CPN, HRNet, etc.) have achieved significant performance on pose estimation by combining feature maps of various resolutions. In this paper, we propose a Resolution-wise Attention…

Computer Vision and Pattern Recognition · Computer Science 2020-12-15 Kun Zhang , Peng He , Ping Yao , Ge Chen , Rui Wu , Min Du , Huimin Li , Li Fu , Tianyao Zheng

We introduce YOLO-pose, a novel heatmap-free approach for joint detection, and 2D multi-person pose estimation in an image based on the popular YOLO object detection framework. Existing heatmap based two-stage approaches are sub-optimal as…

Computer Vision and Pattern Recognition · Computer Science 2022-04-15 Debapriya Maji , Soyeb Nagori , Manu Mathew , Deepak Poddar

We aim to model the top-down attention of a Convolutional Neural Network (CNN) classifier for generating task-specific attention maps. Inspired by a top-down human visual attention model, we propose a new backpropagation scheme, called…

Computer Vision and Pattern Recognition · Computer Science 2016-08-02 Jianming Zhang , Zhe Lin , Jonathan Brandt , Xiaohui Shen , Stan Sclaroff

Transformer architectures have become the model of choice in natural language processing and are now being introduced into computer vision tasks such as image classification, object detection, and semantic segmentation. However, in the…

Computer Vision and Pattern Recognition · Computer Science 2021-08-24 Ce Zheng , Sijie Zhu , Matias Mendieta , Taojiannan Yang , Chen Chen , Zhengming Ding

Anticipating human actions in front of autonomous vehicles is a challenging task. Several papers have recently proposed model architectures to address this problem by combining multiple input features to predict pedestrian crossing actions.…

Computer Vision and Pattern Recognition · Computer Science 2023-05-30 Lina Achaji , Julien Moreau , François Aioun , François Charpillet

Transformers have gained increasing popularity in a wide range of applications, including Natural Language Processing (NLP), Computer Vision and Speech Recognition, because of their powerful representational capacity. However, harnessing…

This paper presents a novel Kinematics and Trajectory Prior Knowledge-Enhanced Transformer (KTPFormer), which overcomes the weakness in existing transformer-based methods for 3D human pose estimation that the derivation of Q, K, V vectors…

Computer Vision and Pattern Recognition · Computer Science 2024-04-03 Jihua Peng , Yanghong Zhou , P. Y. Mok

Transformer-based models have gained considerable attention in the field of physiological signal analysis. They leverage long-range dependencies and complex patterns in temporal signals, allowing them to achieve performance superior to…

Machine Learning · Computer Science 2025-12-01 Merey Orazaly , Fariza Temirkhanova , Jurn-Gyu Park

Human pose information is a critical component in many downstream image processing tasks, such as activity recognition and motion tracking. Likewise, a pose estimator for the illustrated character domain would provide a valuable prior for…

Computer Vision and Pattern Recognition · Computer Science 2021-12-02 Shuhong Chen , Matthias Zwicker