English
Related papers

Related papers: Distilling Token-Pruned Pose Transformer for 2D Hu…

200 papers

In this paper, we propose a two-stage depth ranking based method (DRPose3D) to tackle the problem of 3D human pose estimation. Instead of accurate 3D positions, the depth ranking can be identified by human intuitively and learned using the…

Computer Vision and Pattern Recognition · Computer Science 2018-05-25 Min Wang , Xipeng Chen , Wentao Liu , Chen Qian , Liang Lin , Lizhuang Ma

IoT devices suffer from resource limitations, such as processor, RAM, and disc storage. These limitations become more evident when handling demanding applications, such as deep learning, well-known for their heavy computational…

3D human pose estimation has wide applications in fields such as intelligent surveillance, motion capture, and virtual reality. However, in real-world scenarios, issues such as occlusion, noise interference, and missing viewpoints can…

Computer Vision and Pattern Recognition · Computer Science 2025-02-25 Jianbin Jiao , Xina Cheng , Kailun Yang , Xiangrong Zhang , Licheng Jiao

Transformer-based models have achieved dominant performance in numerous NLP tasks. Despite their remarkable successes, pre-trained transformers such as BERT suffer from a computationally expensive self-attention mechanism that interacts…

Computation and Language · Computer Science 2024-06-04 Jungmin Yun , Mihyeon Kim , Youngbin Kim

We propose a novel generative approach for 3D human pose estimation. 3D human pose estimation poses several key challenges due to the complex geometry of the human body, self-occluding joints, and the requirement for large-scale real-world…

Computer Vision and Pattern Recognition · Computer Science 2025-12-12 Hyunsoo Lee , Daeum Jeon , Hyeokjae Oh

Visual token compression is critical for Large Vision-Language Models (LVLMs) to efficiently process high-resolution inputs. Existing methods that typically adopt fixed compression ratios cannot adapt to scenes of varying complexity, often…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Quan-Sheng Zeng , Yunheng Li , Qilong Wang , Peng-Tao Jiang , Zuxuan Wu , Ming-Ming Cheng , Qibin Hou

Reconstructing 3D poses from 2D poses lacking depth information is particularly challenging due to the complexity and diversity of human motion. The key is to effectively model the spatial constraints between joints to leverage their…

Computer Vision and Pattern Recognition · Computer Science 2023-08-11 Hongbo Kang , Yong Wang , Mengyuan Liu , Doudou Wu , Peng Liu , Wenming Yang

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

In this paper, we address the problem of estimating a 3D human pose from a single image, which is important but difficult to solve due to many reasons, such as self-occlusions, wild appearance changes, and inherent ambiguities of 3D…

Computer Vision and Pattern Recognition · Computer Science 2019-10-08 Geonho Cha , Minsik Lee , Jungchan Cho , Songhwai Oh

Existing human pose estimation approaches often only consider how to improve the model generalisation performance, but putting aside the significant efficiency problem. This leads to the development of heavy models with poor scalability and…

Computer Vision and Pattern Recognition · Computer Science 2019-04-03 Feng Zhang , Xiatian Zhu , Mao Ye

Transformer-based 3D human pose estimation methods suffer from high computational costs due to the quadratic complexity of self-attention with respect to sequence length. Additionally, pose sequences often contain significant redundancy…

Computer Vision and Pattern Recognition · Computer Science 2025-10-10 Zenghao Zheng , Lianping Yang , Hegui Zhu , Mingrui Ye

The choice of data representation is a key factor in the success of deep learning in geometric tasks. For instance, DUSt3R recently introduced the concept of viewpoint-invariant point maps, generalizing depth prediction and showing that all…

Computer Vision and Pattern Recognition · Computer Science 2025-08-15 Ben Kaye , Tomas Jakab , Shangzhe Wu , Christian Rupprecht , Andrea Vedaldi

Large Vision Language Models show impressive performance across image and video understanding tasks, yet their computational cost grows rapidly with the number of visual tokens. Existing token pruning methods mitigate this issue through…

Computer Vision and Pattern Recognition · Computer Science 2026-04-02 Dong-Jae Lee , Sunghyun Baek , Junmo Kim

We present a novel method to fuse the power of deep networks with the computational efficiency of geometric and probabilistic localization algorithms. In contrast to other methods that completely replace a classical visual estimator with a…

Computer Vision and Pattern Recognition · Computer Science 2022-07-06 Valentin Peretroukhin , Jonathan Kelly

Multi-head self-attention forms the core of Transformer networks. However, their quadratically growing complexity with respect to the input sequence length impedes their deployment on resource-constrained edge devices. We address this…

Computation and Language · Computer Science 2022-04-08 Zuzana Jelčicová , Marian Verhelst

Human 3D pose estimation from a single image is a challenging task with numerous applications. Convolutional Neural Networks (CNNs) have recently achieved superior performance on the task of 2D pose estimation from a single image, by…

Computer Vision and Pattern Recognition · Computer Science 2017-01-06 Wenzheng Chen , Huan Wang , Yangyan Li , Hao Su , Zhenhua Wang , Changhe Tu , Dani Lischinski , Daniel Cohen-Or , Baoquan Chen

We propose to leverage Transformer architectures for non-autoregressive human motion prediction. Our approach decodes elements in parallel from a query sequence, instead of conditioning on previous predictions such as instate-of-the-art…

Computer Vision and Pattern Recognition · Computer Science 2021-09-17 Angel Martínez-González , Michael Villamizar , Jean-Marc Odobez

We present MoVNect, a lightweight deep neural network to capture 3D human pose using a single RGB camera. To improve the overall performance of the model, we apply the teacher-student learning method based knowledge distillation to 3D human…

Computer Vision and Pattern Recognition · Computer Science 2020-01-16 Dong-Hyun Hwang , Suntae Kim , Nicolas Monet , Hideki Koike , Soonmin Bae

Human pose estimation aims to locate the human body parts and build human body representation (e.g., body skeleton) from input data such as images and videos. It has drawn increasing attention during the past decade and has been utilized in…

Computer Vision and Pattern Recognition · Computer Science 2023-07-06 Ce Zheng , Wenhan Wu , Chen Chen , Taojiannan Yang , Sijie Zhu , Ju Shen , Nasser Kehtarnavaz , Mubarak Shah

In this paper, we present a method for real-time multi-person human pose estimation from video by utilizing convolutional neural networks. Our method is aimed for use case specific applications, where good accuracy is essential and…

Computer Vision and Pattern Recognition · Computer Science 2016-09-26 Marko Linna , Juho Kannala , Esa Rahtu