English
Related papers

Related papers: Spectral Compression Transformer with Line Pose Gr…

200 papers

Electroencephalogram (EEG) data compression is necessary for wireless recording applications to reduce the amount of data that needs to be transmitted. In this paper, an asymmetrical sparse autoencoder with a discrete cosine transform (DCT)…

Signal Processing · Electrical Eng. & Systems 2023-09-22 Xin Zhu , Hongyi Pan , Shuaiang Rong , Ahmet Enis Cetin

There has been a recent surge of interest in introducing transformers to 3D human pose estimation (HPE) due to their powerful capabilities in modeling long-term dependencies. However, existing transformer-based methods treat body joints as…

Computer Vision and Pattern Recognition · Computer Science 2023-02-16 Han Li , Bowen Shi , Wenrui Dai , Hongwei Zheng , Botao Wang , Yu Sun , Min Guo , Chenlin Li , Junni Zou , Hongkai Xiong

While Convolutional Neural Networks (CNNs) have been widely successful in 2D human pose estimation, Vision Transformers (ViTs) have emerged as a promising alternative to CNNs, boosting state-of-the-art performance. However, the quadratic…

Computer Vision and Pattern Recognition · Computer Science 2023-11-23 Kaleab A. Kinfu , Rene Vidal

Vision Transformer (ViT)-based sparse multi-view 3D object detectors have achieved remarkable accuracy but still suffer from high inference latency due to heavy token processing. To accelerate these models, token compression has been widely…

Computer Vision and Pattern Recognition · Computer Science 2026-04-17 Mingqian Ji , Shanshan Zhang , Jian Yang

Transformer-based approaches have revolutionized image super-resolution by modeling long-range dependencies. However, the quadratic computational complexity of vanilla self-attention mechanisms poses significant challenges, often leading to…

Computer Vision and Pattern Recognition · Computer Science 2026-04-13 Dinh Phu Tran , Thao Do , Saad Wazir , Seongah Kim , Seon Kwon Kim , Daeyoung Kim

Monocular 3D human pose estimation technologies have the potential to greatly increase the availability of human movement data. The best-performing models for single-image 2D-3D lifting use graph convolutional networks (GCNs) that typically…

Computer Vision and Pattern Recognition · Computer Science 2022-08-09 Sebastian Lutz , Richard Blythman , Koustav Ghosal , Matthew Moynihan , Ciaran Simms , Aljosa Smolic

Reconstructing 3D clothed humans from monocular camera data is highly challenging due to viewpoint limitations and image ambiguity. While implicit function-based approaches, combined with prior knowledge from parametric models, have made…

Computer Vision and Pattern Recognition · Computer Science 2024-10-23 Yong Deng , Baoxing Li , Xu Zhao

3D Human Pose Estimation (HPE) is the task of locating keypoints of the human body in 3D space from 2D or 3D representations such as RGB images, depth maps or point clouds. Current HPE methods from depth and point clouds predominantly rely…

Computer Vision and Pattern Recognition · Computer Science 2024-09-04 Irene Ballester , Ondřej Peterka , Martin Kampel

In this paper we present a novel approach for bottom-up multi-person 3D human pose estimation from monocular RGB images. We propose to use high resolution volumetric heatmaps to model joint locations, devising a simple and effective…

Computer Vision and Pattern Recognition · Computer Science 2020-04-02 Matteo Fabbri , Fabio Lanzi , Simone Calderara , Stefano Alletto , Rita Cucchiara

Transformer-based methods have recently achieved significant success in 3D human pose estimation, owing to their strong ability to model long-range dependencies. However, relying solely on the global attention mechanism is insufficient for…

Computer Vision and Pattern Recognition · Computer Science 2024-12-30 Guangsheng Xu , Guoyi Zhang , Lejia Ye , Shuwei Gan , Xiaohu Zhang , Xia Yang

This paper presents a method for estimating significant wave height (Hs) from sparse S_pectral P_oint using a T_ransformer-based approach (SPT). Based on empirical observations that only a minority of spectral points with strong power…

Signal Processing · Electrical Eng. & Systems 2026-01-09 Yi Zhou , Li Wang , Hang Su , Tian Wang

Nowadays, Transformers and Graph Convolutional Networks (GCNs) are the prevailing techniques for 3D human pose estimation. However, Transformer-based methods either ignore the spatial neighborhood relationships between the joints when used…

Computer Vision and Pattern Recognition · Computer Science 2025-05-05 Kamel Aouaidjia , Aofan Li , Wenhao Zhang , Chongsheng Zhang

Current 3DGS compression methods largely forego the neural analysis-synthesis transform, which is a crucial component in learned signal compression systems. As a result, redundancy removal is left solely to the entropy coder, overburdening…

Computer Vision and Pattern Recognition · Computer Science 2026-02-25 Hao Xu , Xiaolin Wu , Xi Zhang

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

Monocular 3D human pose estimation (HPE) methods estimate the 3D positions of joints from individual images. Existing 3D HPE approaches often use the cropped image alone as input for their models. However, the relative depths of joints…

Computer Vision and Pattern Recognition · Computer Science 2025-08-27 Xiaoyang Hao , Han Li

This paper proposes low tensor-train (TT) rank and low multilinear (ML) rank approximations for de-speckling and compression of 3D optical coherence tomography (OCT) images for a given compression ratio (CR). To this end, we derive the…

Numerical Analysis · Mathematics 2020-08-31 Ivica Kopriva , Fei Shi , Mingying Lai , Marija Štanfel , Haoyu Chen , Xinjian Chen

The transformer model is known to be computationally demanding, and prohibitively costly for long sequences, as the self-attention module uses a quadratic time and space complexity with respect to sequence length. Many researchers have…

Computation and Language · Computer Science 2025-05-19 Ziwei He , Meng Yang , Minwei Feng , Jingcheng Yin , Xinbing Wang , Jingwen Leng , Zhouhan Lin

In this research, we address the challenge faced by existing deep learning-based human mesh reconstruction methods in balancing accuracy and computational efficiency. These methods typically prioritize accuracy, resulting in large network…

Computer Vision and Pattern Recognition · Computer Science 2023-02-01 Ayman Ali , Ekkasit Pinyoanuntapong , Pu Wang , Mohsen Dorodchi

Finding effective representations for time series data is a useful but challenging task. Several works utilize self-supervised or unsupervised learning methods to address this. However, there still remains the open question of how to…

Machine Learning · Computer Science 2024-03-19 Yuansan Liu , Sudanthi Wijewickrema , Christofer Bester , Stephen O'Leary , James Bailey

Recently, fully-transformer architectures have replaced the defacto convolutional architecture for the 3D human pose estimation task. In this paper we propose \textbf{\textit{ConvFormer}}, a novel convolutional transformer that leverages a…

Computer Vision and Pattern Recognition · Computer Science 2023-04-06 Alec Diaz-Arias , Dmitriy Shin