English
Related papers

Related papers: Multi-direction and Multi-scale Pyramid in Transfo…

200 papers

Extracting robust feature representation is one of the key challenges in object re-identification (ReID). Although convolution neural network (CNN)-based methods have achieved great success, they only process one local neighborhood at a…

Computer Vision and Pattern Recognition · Computer Science 2021-03-29 Shuting He , Hao Luo , Pichao Wang , Fan Wang , Hao Li , Wei Jiang

In this paper, we propose an attention pyramid method for person re-identification. Unlike conventional attention-based methods which only learn a global attention map, our attention pyramid exploits the attention regions in a multi-scale…

Computer Vision and Pattern Recognition · Computer Science 2021-09-22 Guangyi Chen , Tianpei Gu , Jiwen Lu , Jin-An Bao , Jie Zhou

Recently, a significant improvement in the accuracy of 3D human pose estimation has been achieved by combining convolutional neural networks (CNNs) with pyramid grid alignment feedback loops. Additionally, innovative breakthroughs have been…

Computer Vision and Pattern Recognition · Computer Science 2026-05-27 Zongyou Yang , Jonathan Loo , Yinghan Hou

Pedestrian attribute recognition (PAR) has received increasing attention because of its wide application in video surveillance and pedestrian analysis. Extracting robust feature representation is one of the key challenges in this task. The…

Computer Vision and Pattern Recognition · Computer Science 2023-04-17 Xinwen Fan , Yukang Zhang , Yang Lu , Hanzi Wang

The analysis of patterns of walking is an important area of research that has numerous applications in security, healthcare, sports and human-computer interaction. Lately, walking patterns have been regarded as a unique fingerprinting…

Computer Vision and Pattern Recognition · Computer Science 2024-01-25 Andy Catruna , Adrian Cosma , Emilian Radoi

Currently, in the field of video-text retrieval, there are many transformer-based methods. Most of them usually stack frame features and regrade frames as tokens, then use transformers for video temporal modeling. However, they commonly…

Computer Vision and Pattern Recognition · Computer Science 2024-06-25 Ni Wang , Dongliang Liao , Xing Xu

Part-level representations are essential for robust person re-identification. However, common errors that arise during pedestrian detection frequently result in severe misalignment problems for body parts, which degrade the quality of part…

Computer Vision and Pattern Recognition · Computer Science 2019-12-16 Kan Wang , Changxing Ding , Stephen J. Maybank , Dacheng Tao

Transformer has achieved great success in computer vision, while how to split patches in an image remains a problem. Existing methods usually use a fixed-size patch embedding which might destroy the semantics of objects. To address this…

Computer Vision and Pattern Recognition · Computer Science 2021-08-02 Zhiyang Chen , Yousong Zhu , Chaoyang Zhao , Guosheng Hu , Wei Zeng , Jinqiao Wang , Ming Tang

This paper presents a novel approach for video-based person re-identification using multiple Convolutional Neural Networks (CNNs). Unlike previous work, we intend to extract a compact yet discriminative appearance representation from…

Computer Vision and Pattern Recognition · Computer Science 2019-09-23 Wei Zhang , Shengnan Hu , Kan Liu , Zhengjun Zha

Multi-task dense scene understanding is a thriving research domain that requires simultaneous perception and reasoning on a series of correlated tasks with pixel-wise prediction. Most existing works encounter a severe limitation of modeling…

Computer Vision and Pattern Recognition · Computer Science 2022-11-08 Hanrong Ye , Dan Xu

Understanding and predicting pedestrian crossing behavioral intention is crucial for the driving safety of autonomous vehicles. Nonetheless, challenges emerge when using promising images or environmental context masks to extract various…

Computer Vision and Pattern Recognition · Computer Science 2025-05-13 Chen Xie , Ciyun Lin , Xiaoyu Zheng , Bowen Gong , Antonio M. López

Vision Transformer (ViT) extends the application range of transformers from language processing to computer vision tasks as being an alternative architecture against the existing convolutional neural networks (CNN). Since the…

Computer Vision and Pattern Recognition · Computer Science 2021-08-19 Byeongho Heo , Sangdoo Yun , Dongyoon Han , Sanghyuk Chun , Junsuk Choe , Seong Joon Oh

We propose Physics-Informed Tracking (PIT), a video-based framework for tracking a single particle from video, where a neural network autoencoder localizes a particle as a heatmap peak (landmark) and a differentiable physics module embedded…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Emil Hovad , Allan Peter Engsig-Karup

Robust environment perception for autonomous vehicles is a tremendous challenge, which makes a diverse sensor set with e.g. camera, lidar and radar crucial. In the process of understanding the recorded sensor data, 3D semantic segmentation…

Computer Vision and Pattern Recognition · Computer Science 2022-05-30 Hannah Schieber , Fabian Duerr , Torsten Schoen , Jürgen Beyerer

Person Re-identification (re-id) aims to match people across non-overlapping camera views in a public space. It is a challenging problem because many people captured in surveillance videos wear similar clothes. Consequently, the differences…

Computer Vision and Pattern Recognition · Computer Science 2017-09-18 Xuelin Qian , Yanwei Fu , Yu-Gang Jiang , Tao Xiang , Xiangyang Xue

Recently, video-based person re-identification (re-ID) has drawn increasing attention in compute vision community because of its practical application prospects. Due to the inaccurate person detections and pose changes, pedestrian…

Computer Vision and Pattern Recognition · Computer Science 2021-03-23 Guoqing Zhang , Yuhao Chen , Yang Dai , Yuhui Zheng , Yi Wu

Image pyramids are widely adopted in top-performing methods to obtain multi-scale features for precise visual perception and understanding. However, current image pyramids use the same large-scale model to process multiple resolutions of…

Computer Vision and Pattern Recognition · Computer Science 2025-07-28 Zhaokai Wang , Xizhou Zhu , Xue Yang , Gen Luo , Hao Li , Changyao Tian , Wenhan Dou , Junqi Ge , Lewei Lu , Yu Qiao , Jifeng Dai

Multiview detection uses multiple calibrated cameras with overlapping fields of views to locate occluded pedestrians. In this field, existing methods typically adopt a ``human modeling - aggregation'' strategy. To find robust pedestrian…

Computer Vision and Pattern Recognition · Computer Science 2023-01-09 Jiahao Ma , Zicheng Duan , Liang Zheng , Chuong Nguyen

Recently, occluded person re-identification(Re-ID) remains a challenging task that people are frequently obscured by other people or obstacles, especially in a crowd massing situation. In this paper, we propose a self-supervised deep…

Computer Vision and Pattern Recognition · Computer Science 2022-02-11 Mi Zhou , Hongye Liu , Zhekun Lv , Wei Hong , Xiai Chen

Pedestrian detection methods have been significantly improved with the development of deep convolutional neural networks. Nevertheless, robustly detecting pedestrians with a large variant on sizes and with occlusions remains a challenging…

Computer Vision and Pattern Recognition · Computer Science 2020-05-20 Tianrui Liu , Jun-Jie Huang , Tianhong Dai , Guangyu Ren , Tania Stathaki