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

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

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

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

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.

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

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

关键词： Cameras

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 1

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: (数字)9789819720927

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

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

Systematic Architectural Design of Scale Transformed Attention Condenser DNNs via Multi-Scale Class Representational Response Similarity Analysis

Systematic Architectural Design of Scale Transformed Attenti...

引用

2023 IEEE/CVF Conference on Computer vision and Pattern Recognition Workshops, CVPRW 2023

作者： Hryniowski, Andrew Wong, Alexander Vision and Image Processing Research Group University of Waterloo Canada Waterloo Artificial Intelligence Institute WaterlooON Canada DarwinAI Corp. WaterlooON Canada

ISBN: (纸本)9798350302493

Self-attention mechanisms are commonly included in a convolutional neural networks to achieve an improved efficiency performance balance. However, adding self-attention mechanisms adds additional hyperparameters to tune for the application at hand. In this work we propose a novel type of DNN analysis called Multi-Scale Class Representational Response Similarity Analysis (ClassRep-Sim) which can be used to identify specific design interventions that lead to more efficient self-attention convolutional neural network architectures. Using insights grained from ClassRepSim we propose the Spatial Transformed Attention Condenser (STAC) module, a novel attention-condenser based self-attention module. We show that adding STAC modules to ResNet style architectures can result in up to a 1.6% increase in top-1 accuracy compared to vanilla ResNet models and up to a 0.5% increase in top-1 accuracy compared to SENet models on the imageNet64x64 dataset, at the cost of up to 1.7% increase in FLOPs and 2x the number of parameters. In addition, we demonstrate that results from ClassRepSim analysis can be used to select an effective parameterization of the STAC module resulting in competitive performance compared to an extensive parameter search. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Fast GraspNeXt: A Fast Self-Attention Neural Network Architecture for Multi-task Learning in Computer vision Tasks for Robotic Grasping on the Edge

Fast GraspNeXt: A Fast Self-Attention Neural Network Archite...

引用

2023 IEEE/CVF Conference on Computer vision and Pattern Recognition Workshops, CVPRW 2023

作者： Wong, Alexander Wu, Yifan Abbasi, Saad Nair, Saeejith Chen, Yuhao Shafiee, Mohammad Javad Vision and Image Processing Research Group University of Waterloo Canada Waterloo Artificial Intelligence Institute WaterlooON Canada DarwinAI Corp. WaterlooON Canada

ISBN: (纸本)9798350302493

Multi-task learning has shown considerable promise for improving the performance of deep learning-driven vision systems for the purpose of robotic grasping. However, high architectural and computational complexity can result in poor suitability for deployment on embedded devices that are typically leveraged in robotic arms for real-world manufacturing and warehouse environments. As such, the design of highly efficient multi-task deep neural network architectures tailored for computer vision tasks for robotic grasping on the edge is highly desired for widespread adoption in manufacturing environments. Motivated by this, we propose Fast GraspNeXt, a fast self-attention neural network architecture tailored for embedded multi-task learning in computer vision tasks for robotic grasping. To build Fast GraspNeXt, we leverage a generative network architecture search strategy with a set of architectural constraints customized to achieve a strong balance between multitask learning performance and embedded inference efficiency. Experimental results on the MetaGraspNet benchmark dataset show that the Fast GraspNeXt network design achieves the highest performance (average precision (AP), accuracy, and mean squared error (MSE)) across multiple computer vision tasks when compared to other efficient multi-task network architecture designs, while having only 17.8M parameters (about >5× smaller), 259 GFLOPs (as much as >5× lower) and as much as >3.15× faster on a NVIDIA Jetson TX2 embedded processor. © 2023 IEEE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Domain-Guided Masked Autoencoders for Unique Player Identification

arXiv

引用

arXiv 2024年

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

Unique player identification is a fundamental module in vision-driven sports analytics. Identifying players from broadcast videos can aid with various downstream tasks such as player assessment, in-game analysis, and broadcast production. However, automatic detection of jersey numbers using deep features is challenging primarily due to: a) motion blur, b) low resolution video feed, and c) occlusions. With their recent success in various vision tasks, masked autoencoders (MAEs) have emerged as a superior alternative to conventional feature extractors. However, most MAEs simply zero-out image patches either randomly or focus on where to mask rather than how to mask. Motivated by human vision, we devise a novel domain-guided masking policy for MAEs termed dMAE to facilitate robust feature extraction in the presence of motion blur for player identification. We further introduce a new spatio-temporal network leveraging our novel d-MAE for unique player identification. We conduct experiments on three large-scale sports datasets, including a curated baseball dataset, the SoccerNet dataset, and an in-house ice hockey dataset. We preprocess the datasets using an upgraded keyframe identification (KfID) module by focusing on frames containing jersey numbers. Additionally, we propose a keyframe-fusion technique to augment keyframes, preserving spatial and temporal context. Our spatio-temporal network showcases significant improvements, surpassing the current state-of-the-art by 8.58%, 4.29%, and 1.20% in the test set accuracies, respectively. Rigorous ablations highlight the effectiveness of our domain-guided masking approach and the refined KfID module, resulting in performance enhancements of 1.48% and 1.84% respectively, compared to original architectures. © 2024, CC BY.

关键词： image enhancement

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：