检索结果-内蒙古大学图书馆

38th Conference on Neural Information processing Systems, NeurIPS 2024

作者： Balaji, Bavesh Bright, Jerrin Chen, Yuhao Rambhatla, Sirisha Zelek, John S. Clausi, David Anthony Critical ML Lab Vision and Image Processing Lab University of Waterloo Canada

Accurate estimation of human pose and the pose of interacting objects, like a hockey stick, is crucial for action recognition and performance analysis, particularly in sports. Existing methods capture the object along with the human in the bounding boxes, assuming all keypoints are visible within the bounding box. This necessitates larger bounding boxes to capture the object, introducing unnecessary visual features and hindering performance in real-world cluttered environments. We propose a simple image and text-based multimodal solution TokenCLIPose that addresses this limitation. Our approach focuses solely on human keypoints within the bounding box, treating objects as unseen. TokenCLIPose leverages the rich semantic representations endowed by language for inducing keypoint-specific context, even for occluded keypoints. We evaluate the performance of TokenCLIPose on a real-world ice hockey dataset, and demonstrate its generalizability through zero-shot transfer to a smaller Lacrosse dataset. Additionally, we showcase its flexibility on CrowdPose, a popular occlusion benchmark with keypoints within the bounding box. Our method significantly improves over state-of-the-art approaches on ice hockey, Lacrosse, and CrowdPose datasets, with gains of 4.36%, 2.35%, and 3.8%, respectively. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improved YOLOv5 Algorithm for Small Object Detection in Drone images 12th

Improved YOLOv5 Algorithm for Small Object Detection in Dr...

引用

12th International Conference on Computational Visual Media, CVM 2024

作者： Lin, Yitong Liu, Yiguang Vision and Image Processing Lab College of Computer Science Sichuan University Chengdu610065 China

ISBN: (纸本)9789819720910

The object detection in the context of drone is a hot topic in the field of computer vision in recent years. In response to the challenge of limited image feature information and the presence of numerous small and densely packed objects in drone-captured images, this paper proposes a novel feature fusion detection model, HTH-YOLOv5, based on YOLOv5. Firstly, we enhance the detection capability of small objects by adding a detection channel from high-resolution feature maps and propose a Hybrid Transformer Head (HTH) that incorporates a hybrid Transformer module, aiming to improve the network’s focus on small objects by fusing global and local feature information. Secondly, we introduce a Convolutional Attention Feature Fusion module (CA-FF) based on CBAM. This module dynamically adjusts attention weights for the allocation of original feature maps in both channel and spatial dimensions, aiming to enhance the feature extraction capability for small objects. Finally, to better capture global and contextual information, we introduce the Hybrid Transformer module into the backbone and enhance its original feature fusion method using the CA-FF module. Experiments on the Vis-Drone 2021 dataset demonstrate that, compared to the baseline YOLOv5s model, the improved model shows an increase of 7.2% in mAP50 and 6.3% in mAP75. The model trained with an input resolution of 1540×1540 achieves an mAP50 of 57.1%, marking a 12.4% improvement over YOLOv5. The improved HTH-YOLOv5 achieves increased accuracy while maintaining a detection speed of 45 FPS, making it more suitable for small object detection in drone scenarios. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Seeing beyond the crop: using language priors for out-of-bounding box keypoint prediction 24

Seeing beyond the crop: using language priors for out-of-bou...

引用

Proceedings of the 38th International Conference on Neural Information processing Systems

作者： Bavesh Balaji Jerrin Bright Yuhao Chen Sirisha Rambhatla John S. Zelek David Anthony Clausi Critical ML Lab and Vision and Image Processing Lab and University of Waterloo Vision and Image Processing Lab and University of Waterloo Critical ML Lab and University of Waterloo

ISBN: (纸本)9798331314385

Accurate estimation of human pose and the pose of interacting objects, like a hockey stick, is crucial for action recognition and performance analysis, particu larly in sports. Existing methods capture the object along with the human in the bounding boxes, assuming all keypoints are visible within the bounding box. This necessitates larger bounding boxes to capture the object, introducing unnecessary visual features and hindering performance in real-world cluttered environments. We propose a simple image and text-based multimodal solution TokenCLIPose that addresses this limitation. Our approach focuses solely on human keypoints within the bounding box, treating objects as unseen. TokenCLIPose leverages the rich semantic representations endowed by language for inducing keypoint-specific con text, even for occluded keypoints. We evaluate the performance of TokenCLIPose on a real-world ice hockey dataset, and demonstrate its generalizability through zero-shot transfer to a smaller Lacrosse dataset. Additionally, we showcase its flexibility on CrowdPose, a popular occlusion benchmark with keypoints within the bounding box. Our method significantly improves over state-of-the-art approaches on ice hockey, Lacrosse, and CrowdPose datasets, with gains of 4.36%, 2.35%, and 3.8%, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Distribution and Depth-Aware Transformers for 3D Human Mesh Recovery

arXiv

引用

arXiv 2024年

作者： Bright, Jerrin Balaji, Bavesh Prakash, Harish Chen, Yuhao Clausi, David A. Zelek, John Vision and Image Processing Lab University of Waterloo Canada

Precise Human Mesh Recovery (HMR) with in-the-wild data is a formidable challenge and is often hindered by depth ambiguities and reduced precision. Existing works resort to either pose priors or multi-modal data such as multi-view or point cloud information, though their methods often overlook the valuable scene-depth information inherently present in a single image. Moreover, achieving robust HMR for out-of-distribution (OOD) data is exceedingly challenging due to inherent variations in pose, shape and depth. Consequently, understanding the underlying distribution becomes a vital subproblem in modeling human forms. Motivated by the need for unambiguous and robust human modeling, we introduce Distribution and depth-aware human mesh recovery (D2AHMR), an end-to-end transformer architecture meticulously designed to minimize the disparity between distributions and incorporate scene-depth leveraging prior depth information. Our approach demonstrates superior performance in handling OOD data in certain scenarios while consistently achieving competitive results against state-of-the-art HMR methods on controlled datasets. © 2024, CC BY.

关键词： Recovery

来源：评论

学校读者我要写书评

暂无评论

Zero-Shot Monocular Motion Segmentation in the Wild by Combining Deep Learning with Geometric Motion Model Fusion

arXiv

引用

arXiv 2024年

作者： Huang, Yuxiang Chen, Yuhao Zelek, John Vision and Image Processing Lab University of Waterloo WaterlooON Canada

Detecting and segmenting moving objects from a moving monocular camera is challenging in the presence of unknown camera motion, diverse object motions and complex scene structures. Most existing methods rely on a single motion cue to perform motion segmentation, which is usually insufficient when facing different complex environments. While a few recent deep learning based methods are able to combine multiple motion cues to achieve improved accuracy, they depend heavily on vast datasets and extensive annotations, making them less adaptable to new scenarios. To address these limitations, we propose a novel monocular dense segmentation method that achieves state-of-the-art motion segmentation results in a zero-shot manner. The proposed method synergestically combines the strengths of deep learning and geometric model fusion methods by performing geometric model fusion on object proposals. Experiments show that our method achieves competitive results on several motion segmentation datasets and even surpasses some state-of-the-art supervised methods on certain benchmarks, while not being trained on any data. We also present an ablation study to show the effectiveness of combining different geometric models together for motion segmentation, highlighting the value of our geometric model fusion strategy. © 2024, CC BY.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Zero-Shot Monocular Motion Segmentation in the Wild by Combining Deep Learning with Geometric Motion Model Fusion

Zero-Shot Monocular Motion Segmentation in the Wild by Combi...

引用

IEEE Computer Society Conference on Computer vision and Pattern Recognition Workshops (CVPRW)

作者： Yuxiang Huang Yuhao Chen John Zelek Vision and Image Processing Lab University of Waterloo Waterloo Canada

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

关键词： Deep learning Computer vision Motion segmentation Conferences Computational modeling Geometric modeling Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Autocalibration for Creating 2D/3D Displays on Complex Geometric Surfaces

引用

Information Display 2022年第6期38卷 31-37页

作者： Arnold, Katherine Fieguth, Paul Dennison, Andrew Vision and Image Processing Lab University of Waterloo Canada Systems Design Engineering Department University of Waterloo Canada Software Solutions Development Department Christie Digital Systems

Geometric calibration methods tend to rely on precalibrated cameras or real calibration targets. Here we explore the chal-lenge of achieving a sufficiently accurate projector system calibration for complex projection mapping tasks that can rely on neither precalibrated cameras nor calibration targets. Virtual scene models can take the place of a real calibration target for the purpose of providing scene information that is used to refine geometric estimates. Refinement of the display parameters aims to reduce the reprojection error, or the error between the theoretical coordinate (generated from the projection of the scene estimate coordinate by the estimated parameters) and the actual coordinate (obtained from pixel cor-respondences). For Christie installations, the final reprojection error of each pixel should be less than 1 pixel. Mystique was not always so capable. Christie’s research department, Christie labs, has a history of creating solutions for new projection concepts. Part of that strategy has been a long partnership with the University of Waterloo, particularly the vision and image processing (VIP) lab in Systems Design Engineering. Graduate students study computer vision and machine learning—topics related to problems often at the heart of techniques—which can be used to bring new ideas, meth-ods, and solutions to Mystique and, by extension, to Christie’s customers. Years of investment in research and development, including partnership with the VIP lab and others, have enabled Mystique to handle challenges beyond any other projec-tor-alignment solution. ID. © 2022, John Wiley and Sons Inc. All rights reserved.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Multiview Human Action Recognition System Based on OpenPose and KNN Classifier 11th

Multiview Human Action Recognition System Based on OpenPose ...

引用

11th International Conference on Robotics, vision, Signal processing and Power Applications, RoViSP 2021

作者： Malik, Najeeb Ur Rehman Abu Bakar, Syed Abdul Rahman Sheikh, Usman Ullah Computer Vision Video and Image Processing Lab ECE Department Universiti Teknologi Malaysia Johor Malaysia

ISBN: (纸本)9789811681288

Human action recognition is one of the trending research topics in the field of computer vision. Human-computer interaction and video monitoring are broad applications that aid in the understanding of human action in a video. The problem with action recognition algorithms such as 3D CNN, Two-stream network, and CNN-LSTM is that they have highly complex models including a lot of parameters resulting in difficulty while training them. Such models require high configuration machines for real-time human action recognition. Therefore, present research proposes the use of 2D skeleton features along with a KNN classifier based HAR system to overcome the aforementioned problems of complexity and response time. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

How Much You Ate? Food Portion Estimation on Spoons

How Much You Ate? Food Portion Estimation on Spoons

引用

IEEE Computer Society Conference on Computer vision and Pattern Recognition Workshops (CVPRW)

作者： Aaryam Sharma Chris Czarnecki Yuhao Chen Pengcheng Xi Linlin Xu Alexander Wong Vision and Image Processing Lab University of Waterloo National Research Council Canada

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

Monitoring dietary intake is a crucial aspect of promoting healthy living. In recent years, advances in computer vision technology have facilitated dietary intake monitoring through the use of images and depth cameras. However, the current state-of-the-art image-based food portion estimation algorithms assume that users take images of their meals one or two times, which can be inconvenient and fail to capture food items that are not visible from a top-down perspective, such as ingredients submerged in a stew. To address these limitations, we introduce an innovative solution that utilizes stationary user-facing cameras to track food items on utensils, not requiring any change of camera perspective after installation. The shallow depth of utensils provides a more favorable angle for capturing food items, and tracking them on the utensil’s surface offers a significantly more accurate estimation of dietary intake without the need for post-meal image capture. The system is reliable for estimation of nutritional content of liquid-solid heterogeneous mixtures such as soups and stews. Through a series of experiments, we demonstrate the exceptional potential of our method as a non-invasive, user-friendly, and highly accurate dietary intake monitoring tool.

关键词： Computer vision image segmentation Accuracy Pipelines Estimation image capture Cameras

来源：评论

学校读者我要写书评

暂无评论

Cancer-Net BCa-S: Breast Cancer Grade Prediction using Volumetric Deep Radiomic Features from Synthetic Correlated Diffusion Imaging

arXiv

引用

arXiv 2023年

作者： Tai, Chi-En Amy Gunraj, Hayden Wong, Alexander Vision and Image Processing Lab University of Waterloo Canada

The prevalence of breast cancer continues to grow, affecting about 300,000 females in the United States in 2023. However, there are different levels of severity of breast cancer requiring different treatment strategies, and hence, grading breast cancer has become a vital component of breast cancer diagnosis and treatment planning. Specifically, the gold-standard Scarff-Bloom-Richardson (SBR) grade has been shown to consistently indicate a patient's response to chemotherapy. Unfortunately, the current method to determine the SBR grade requires removal of some cancer cells from the patient which can lead to stress and discomfort along with costly expenses. In this paper, we study the efficacy of deep learning for breast cancer grading based on synthetic correlated diffusion (CDIs) imaging, a new magnetic resonance imaging (MRI) modality and found that it achieves better performance on SBR grade prediction compared to those learnt using gold-standard imaging modalities. Hence, we introduce Cancer-Net BCa-S, a volumetric deep radiomics approach for predicting SBR grade based on volumetric CDIs data. Given the promising results, this proposed method to identify the severity of the cancer would allow for better treatment decisions without the need for a biopsy. Cancer-Net BCa-S has been made publicly available as part of a global open-source initiative for advancing machine learning for cancer care. Copyright © 2023, The Authors. All rights reserved.

关键词： Chemotherapy

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：