检索结果-内蒙古大学图书馆

ROSS: Robust Learning of One-Shot 3D Shape Segmentation

学校读者我要写书评

暂无评论

ROSS: Robust Learning of One-Shot 3D Shape Segmentation

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Shuaihang Yuan Yi Fang NYU Multimedia and Visual Computing Lab USA

ISBN: (数字)9781728165530

ISBN: (纸本)9781728165547

3D shape segmentation is a fundamental computer vision task that partitions the object into labeled semantic parts. Recent approaches to 3D shape segmentation learning heavily rely on high-quality labeled training datasets. This limits their use in applications to handle the large scale unannotated datasets. In this paper, we proposed a novel semi-supervised approach, named Robust Learning of OneShot 3D Shape Segmentation (ROSS), which only requires one single exemplar labeled shape for training. The proposed ROSS can generalize its ability from a one-shot training process to predict the segmentation for previously unseen 3D shape models. The proposed ROSS is composed of three major modules for 3D shape segmentation as follows. The global shape descriptor generator is the first module that utilizes the proposed reference weighted convolution to learn a 3D shape descriptor. The second module is a part-aware shape descriptor constructor that can generate weighted descriptors from a learned 3D shape descriptor according to semantic parts without supervision. The shape morphing with label transferring works as the last module. It morphs the exemplar shape and then transfers labels from the transformed exemplar shape to the target shape. The extensive experimental results on 3D mesh datasets demonstrate the ROSS is robust to noise and incomplete shapes and it can be applied to unannotated datasets. The experiment shows the proposed ROSS can achieve comparable performance with the supervised method.

关键词： Shape Three-dimensional displays Task analysis Convolution Learning systems Robustness Training

Pyramid Learnable Tokens for 3D LiDAR Place Recognition

学校读者我要写书评

暂无评论

Pyramid Learnable Tokens for 3D LiDAR Place Recognition

IEEE International Conference on Robotics and Automation (ICRA)

作者： Congcong Wen Hao Huang Yu-Shen Liu Yi Fang NYUAD Center for Artificial Intelligence and Robotics New York University Abu Dhabi UAE NYU Multimedia and Visual Computing Lab New York University USA New York University Abu Dhabi UAE School of Software Tsinghua University Beijing P. R. China

3D LiDAR place recognition plays a vital role in various robot applications' including robotic navigation, autonomous driving, and simultaneous localization and mapping. However, most previous studies evaluated their models on accumulated 2D scans instead of real-world 3D LiDAR scans with a larger number of points, which limits the application in real scenarios. To address this limitation, we propose a point transformer network with pyramid learnable tokens (PTNet-PLT) to learn global descriptors for an actual scanned 3D LiDAR place recognition. Specifically, we first present a novel shifted cube attention module that consists of a self-attention module for local feature extraction and a cross-attention module for regional feature aggregation. The self-attention module constrains attention computation on a locally partitioned cube and builds connections across cubes based on the shifted cube scheme. In addition, the cross-attention module introduces several learnable tokens to separately aggregate features of points with similar features but spatially distant into an arbitrarily shaped region, which enables the model to capture long-term dependencies of the points. Next, we build a pyramid architecture network to learn multi-scale features and involve a decreasing number of tokens at each layer to aggregate features over a larger region. Finally, we obtain the global descriptor by concatenating learned region tokens of all layers. Experiments on three datasets, including USyd Campus, Oxford Robot-Car, and KITTI, demonstrate the effectiveness and generalization of the proposed model for large-scale 3D LiDAR place recognition.

关键词：

Detect and Approach: Close-Range Navigation Support for People with Blindness and Low Vision

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Hao, Yu Feng, Junchi Rizzo, John-Ross Wang, Yao Fang, Yi Nyu Multimedia and Visual Computing Lab Nyu Tandon School of Engineering New York University United States New York University Abu Dhabi United Arab Emirates Nyu Langone Health United States

People with blindness and low vision (pBLV) experience significant challenges when locating final destinations or targeting specific objects in unfamiliar environments. Furthermore, besides initially locating and orienting oneself to a target object, approaching the final target from one's present position is often frustrating and challenging, especially when one drifts away from the initial planned path to avoid obstacles. In this paper, we develop a novel wearable navigation solution to provide real-time guidance for a user to approach a target object of interest efficiently and effectively in unfamiliar environments. Our system contains two key visual computing functions: initial target object localization in 3D and continuous estimation of the user's trajectory, both based on the 2D video captured by a low-cost monocular camera mounted on in front of the chest of the user. These functions enable the system to suggest an initial navigation path, continuously update the path as the user moves, and offer timely recommendation about the correction of the user's path. Our experiments demonstrate that our system is able to operate with an error of less than 0.5 meter both outdoor and indoor. The system is entirely vision-based and does not need other sensors for navigation, and the computation can be run with the Jetson processor in the wearable system to facilitate real-time navigation assistance. © 2022, CC BY.

关键词： Object detection

Resolving Task Confusion in Dynamic Expansion Architectures for Class Incremental Learning

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Huang, Bingchen Chen, Zhineng Zhou, Peng Chen, Jiayin Wu, Zuxuan Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University China Shanghai Collaborative Innovation Center on Intelligent Visual Computing China University of Maryland College ParkMD United States

The dynamic expansion architecture is becoming popular in class incremental learning, mainly due to its advantages in alleviating catastrophic forgetting. However, task confusion is not well assessed within this framework, e.g., the discrepancy between classes of different tasks is not well learned (i.e., inter-task confusion, ITC), and certain priority is still given to the latest class batch (i.e., old-new confusion, ONC). We empirically validate the side effects of the two types of confusion. Meanwhile, a novel solution called Task Correlated Incremental Learning (TCIL) is proposed to encourage discriminative and fair feature utilization across tasks. TCIL performs a multi-level knowledge distillation to propagate knowledge learned from old tasks to the new one. It establishes information flow paths at both feature and logit levels, enabling the learning to be aware of old classes. Besides, attention mechanism and classifier re-scoring are applied to generate more fair classification scores. We conduct extensive experiments on CIFAR100 and ImageNet100 datasets. The results demonstrate that TCIL consistently achieves state-of-the-art accuracy. It mitigates both ITC and ONC, while showing advantages in battle with catastrophic forgetting even no rehearsal memory is reserved. 1 Copyright © 2022, The Authors. All rights reserved.

关键词： Distillation

Corrigendum to "Can ChatGPT provide appropriate meal plans for NCD patients?" [Nutrition 121 (2024): 112291]

学校读者我要写书评

暂无评论

Nutrition (Burbank, Los Angeles County, Calif.) 2024年 128卷 112532页

作者： Ilias Papastratis Andreas Stergioulas Dimitrios Konstantinidis Petros Daras Kosmas Dimitropoulos The Visual Computing Lab Information Technologies Institute Centre for Research and Technology Hellas Thessaloniki Central Macedonia Greece. The Visual Computing Lab Information Technologies Institute Centre for Research and Technology Hellas Thessaloniki Central Macedonia Greece. Electronic address: dikonsta@iti.gr.

HUMAN SIMULACRA: BENCHMARKING THE PERSONIFICATION OF LARGE LANGUAGE MODELS

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xie, Qiujie Feng, Qiming Zhang, Tianqi Li, Qingqiu Yang, Linyi Zhang, Yuejie Feng, Rui He, Liang Gao, Shang Zhang, Yue School of Computer Science Shanghai Key Lab of Intelligent Information Processing Shanghai Collaborative Innovation Center of Intelligent Visual Computing Fudan University China Tongji University China University College London United Kingdom Huawei Noah’s Ark Lab Canada Shanghai Key Laboratory of Mental Health and Psychological Crisis Intervention China Deakin University Australia Westlake University China Westlake Institute for Advanced Study China

Large Language Models (LLMs) are recognized as systems that closely mimic aspects of human intelligence. This capability has attracted the attention of the social science community, who see the potential in leveraging LLMs to replace human participants in experiments, thereby reducing research costs and complexity. In this paper, we introduce a benchmark for LLMs personification, including a strategy for constructing virtual characters’ life stories from the ground up, a Multi-Agent Cognitive Mechanism capable of simulating human cognitive processes, and a psychology-guided evaluation method to assess human simulations from both self and observational perspectives. Experimental results demonstrate that our constructed simulacra can produce personified responses that align with their target characters. We hope this work will serve as a benchmark in the field of human simulation, paving the way for future research. © 2024, CC BY-NC-SA.

关键词： Digital elevation model

Deep Soft Procrustes for Markerless Volumetric Sensor Alignment

学校读者我要写书评

暂无评论

Deep Soft Procrustes for Markerless Volumetric Sensor Alignm...

IEEE Annual International Symposium Virtual Reality

作者： Vladimiros Sterzentsenko Alexandros Doumanoglou Spyridon Thermos Nikolaos Zioulis Dimitrios Zarpalas Petros Daras Visual Computing Lab Centre for Research and Technology Hellas

ISBN: (数字)9781728156088

ISBN: (纸本)9781728156095

With the advent of consumer grade depth sensors, low-cost volumetric capture systems are easier to deploy. Their wider adoption though depends on their usability and by extension on the practicality of spatially aligning multiple sensors. Most existing alignment approaches employ visual patterns, e.g. checkerboards, or markers and require high user involvement and technical knowledge. More user-friendly and easier-to-use approaches rely on markerless methods that exploit geometric patterns of a physical structure. However, current SoA approaches are bounded by restrictions in the placement and the number of sensors. In this work, we improve markerless data-driven correspondence estimation to achieve more robust and flexible multi-sensor spatial alignment. In particular, we incorporate geometric constraints in an end-to-end manner into a typical segmentation based model and bridge the intermediate dense classification task with the targeted pose estimation one. This is accomplished by a soft, differentiable procrustes analysis that regularizes the segmentation and achieves higher extrinsic calibration performance in expanded sensor placement configurations, while being unrestricted by the number of sensors of the volumetric capture system. Our model is experimentally shown to achieve similar results with marker-based methods and outperform the mark-erless ones, while also being robust to the pose variations of the calibration structure. Code and pretrained models are available at https://***/StructureNet/.

关键词： Cameras Three-dimensional displays Calibration Pose estimation Solid modeling Semantics

InsPLAD: A Dataset and Benchmark for Power Line Asset Inspection in UAV Images

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Vieira e Silva, André Luiz Buarque de Castro Felix, Heitor Simões, Franscisco Paulo Magalhães Teichrieb, Veronica dos Santos, Michel Santiago, Hemir Sgotti, Virginia Neto, Henrique Lott Voxar Labs Centro de Informática Universidade Federal de Pernambuco Recife Brazil In Forma Software Recife Brazil Sistema de Transmissão Nordeste Recife Brazil Visual Computing Lab Departamento de Computação Universidade Federal Rural de Pernambuco Recife Brazil

Power line maintenance and inspection are essential to avoid power supply interruptions, reducing its high social and financial impacts yearly. Automating power line visual inspections remains a relevant open problem for the industry due to the lack of public real-world datasets of power line components and their various defects to foster new research. This paper introduces InsPLAD, a Power Line Asset Inspection Dataset and Benchmark containing 10,607 high-resolution Unmanned Aerial Vehicles colour images. The dataset contains seventeen unique power line assets captured from real-world operating power lines. Additionally, five of those assets present six defects: four of which are corrosion, one is a broken component, and one is a bird's nest presence. All assets were labelled according to their condition, whether normal or the defect name found on an image level. We thoroughly evaluate state-of-the-art and popular methods for three image-level computer vision tasks covered by InsPLAD: object detection, through the AP metric;defect classification, through Balanced Accuracy;and anomaly detection, through the AUROC metric. InsPLAD offers various vision challenges from uncontrolled environments, such as multi-scale objects, multi-size class instances, multiple objects per image, intra-class variation, cluttered background, distinct point-of-views, perspective distortion, occlusion, and varied lighting conditions. To the best of our knowledge, InsPLAD is the first large real-world dataset and benchmark for power line asset inspection with multiple components and defects for various computer vision tasks, with a potential impact to improve state-of-the-art methods in the field. It will be publicly available in its integrity on a repository with a thorough description. It can be found at https://***/andreluizbvs/InsPLAD/or https://***/drive/folders/1psHiRyl7501YolnCcB8k55rTuAUcR9Ak?usp=sharing. © 2023, CC BY-NC-SA.

关键词： Object detection

Virtual-Reality Based Crisis Management Training for Teachers: An Overview of the VRTEACHER Project 23

学校读者我要写书评

暂无评论

Virtual-Reality Based Crisis Management Training for Teacher...

23rd International Symposium on Computers in Education, SIIE 2021

作者： Stavroulia, Kalliopi Evangelia Aedo, Ignacio Diaz, Paloma Lanitis, Andreas Cyprus University of Technology Department of Multimedia and Graphic Arts Limassol Cyprus Universidad Carlos III de Madrid Computer Science Department Madrid Spain Cyprus University of Technology and CYENS Centre of Excellence Visual Media Computing Lab Department of Multimedia and Graphic Arts Limassol Cyprus

ISBN: (纸本)9781665440240

The coronavirus pandemic has created an educational crisis without precedent, posed new challenges, and highlighted the need for digital skills empowerment among teachers along with the use of technology-based approaches to support the delivery of education and ensure the future of learning. As a return to normality is far from over, the implementation of novel training approaches for teacher training is more imperative than ever. In this context, this paper presents the VRTEACHER project that aims to promote the use of digital technologies and innovative and open pedagogies as part of teachers' training methodology. The vision of the project is to empower teacher's skills (such as empathy, perspective-taking, self-efficacy, adaptability, etc.) and readiness related to class management in crisis situations, through Virtual Reality (VR) immersive and experiential training approaches that reflect real-life scenarios and situations. The aim and challenge of the project are not just to adapt the training provided to the digital era and connect it with new technologies but to build a holistic new approach to teacher training through the use of VR. © 2021 IEEE.

关键词： Virtual reality