检索结果-内蒙古大学图书馆

12th International Conference on Learning Representations, ICLR 2024

作者： Mirakhor, Karan Ghosh, Sourav Das, Dipanjan Bhowmick, Brojeshwar Visual Computing and Embodied Intelligence Lab TCS Research Kolkata India

This paper presents a novel modular task planner under partial observability that empowers an embodied agent to use visual input to efficiently plan a sequence of actions for simultaneous object search and rearrangement in an untidy room, to achieve a desired tidy state. The paper introduces (i) a novel Search Network that utilizes commonsense knowledge from large language models to find unseen objects, (ii) a Deep RL network trained with proxy reward, along with (iii) a novel graph-based state representation to produce a scalable and effective planner that interleaves object search and rearrangement to minimize the number of steps taken and overall traversal of the agent, as well as to resolve blocked goal and swap cases, and (iv) a sample-efficient cluster-biased sampling for simultaneous training of the proxy reward network along with the Deep RL network. Furthermore, the paper presents new metrics and a benchmark dataset - RoPOR, to measure the effectiveness of rearrangement planning. Experimental results show that our method significantly outperforms the state-of-the-art rearrangement methodsWeihs et al. (2021);Gadre et al. (2022);Sarch et al. (2022);Ghosh et al. (2022). © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Image Retrieval with Hard Negative Centers and Quadruplet Center Loss in Deep Hashing

Image Retrieval with Hard Negative Centers and Quadruplet Ce...

引用

2024 IEEE International Conference on Future Machine Learning and Data Science, FMLDS 2024

作者： Konstantinou, Nikolaos Semertzidis, Theodoros Dimou, Anastasios Daras, Petros The Visual Computing Lab Centre for Research and Technology Hellas Thessaloniki Greece

ISBN: (纸本)9798350391213

In this work, we enhance image retrieval performance by building upon the Central Similarity Quantization method in deep learning, which uses 'hash centers' - points in a K-dimensional Hamming space fulfilling certain distance criteria. Our approach is inspired by the concept of selecting hard negatives in deep learning, aiming to boost model performance. We introduce an alternative strategy for quadruplet loss training that employs corresponding positive/negative hash centers instead of positive/negative samples. For each sample, we compute the Hamming distances between its hash code and all hash centers and select the two closest centers as negative centers. The positive center is its random assigned center and is used to guide the sample towards convergence. We then define a quadruplet loss function that encourages the learned hash codes to be both discriminative and compact, minimizing the distances between the sample and its positive center while maximizing the distances between the sample and the negative centers. Our method is evaluated using mAP and Recall@K metrics on the Hotels50k, Stanford Dogs, and CUB200 datasets, demonstrating promising results in image retrieval tasks by effectively utilizing hard negative centers and quadruplet center loss. © 2024 IEEE.

关键词： Hamming distance

来源：评论

学校读者我要写书评

暂无评论

An integrated framework for developing and evaluating a lecture style assessment methodology

引用

Multimedia Tools and Applications 2024年 1-28页

作者： Dimitriadou, Eleni Lanitis, Andreas Visual Media Computing Lab Department of Multimedia and Graphic Arts Cyprus University of Technology Limassol Cyprus CYENS Centre of Excellence Nicosia Cyprus

The aim of the work presented in this paper is to develop and evaluate an integrated lecture style evaluation methodology that provides, teachers instant feedback related to the quality of their lecturing style. The proposed method aims to promote improvement of lecture quality, that could upgrade the overall student learning experience. The proposed methodology utilizes specific measurable visual, and audio biometric characteristics extracted from a video showing the lecturer from the audience’s point of view. Measurable biometric features extracted during a lecture are combined to provide teachers with a score reflecting lecture style quality both at frame rate and by providing lecture quality metrics for the whole lecture. The results of a comprehensive quantitative evaluation indicate that the proposed methodology can be used for obtaining metrics that reflect lecture style quality. Furthermore, the performance evaluation of the proposed methodology was compared with the performance of humans in the task of lecture style evaluation. Results indicate that the proposed method not only achieves similar performance to human observers, but in some cases, it outperforms them. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

Advancing Handwritten Text Detection by Synthetic Text 27th

Advancing Handwritten Text Detection by Synthetic Text

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Muth, Markus Peer, Marco Kleber, Florian Sablatnig, Robert Computer Vision Lab Institute of Visual Computing and Human-Centered Technology TU Wien Wien1040 Austria

ISBN: (纸本)9783031784941

In this paper, the usability of synthetic handwritten text to improve machine learning models is examined for the domain of handwritten text detection. We generate synthetic handwritten text by using an existing model based on a style conditioned GAN, and add those texts to scanned documents to mimic handwritten annotations. Object detection models (YOLOv5 and YOLOv8) are trained using synthetic data as a baseline to distinguish handwritten text from remaining content. We study different granularity labels (word-, line- and paragraph-level) and model sizes in our evaluation and show that applying those models to real data results in a mAP@50 of 0.88 and a pixel-level F1@50 of 0.96 for the CVL dataset, and a mAP@50 of 0.72 and F1@50 of 0.89 for SCAN, a custom dataset, created by adding real handwritten annotations to a scientific paper. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

The Digital Ocean lab (DOL): Centralising Ocean Research in the Baltic Sea

The Digital Ocean Lab (DOL): Centralising Ocean Research in ...

引用

OCEANS 2024 - Halifax, OCEANS 2024

作者： Umlauft, Alexandru Schmidt, Felix Lünsdorf, Gerrit Globisch, Torben Daske, Nele Suhrbier, Patrick Bauer, Kristine Krohmann, Sascha Von Lukas, Uwe Freiherr Maritime Graphics University of Rostock Rostock Germany Visual Computing Fraunhofer Igd Rostock Germany Maritime Graphics Fraunhofer Igd Rostock Germany Digital Ocean Lab Fraunhofer Igd Rostock Germany

ISBN: (纸本)9798331540081

Concentrating several underwater research applications into one research station directly on the sea can prove to be a cost-saving method and foster more research on maritime domains. We aim to develop a maritime research test bed in the Baltic Sea and create digital twins of the environment. These digital twins can greatly help to better understand the oceans and react to the challenges of climate change. Here we describe our technical setup and experience with maintaining this maritime research field ('DOL') and the issues we encountered. © 2024 IEEE.

关键词： digital twin ocean observation sensors underwater

来源：评论

学校读者我要写书评

暂无评论

Federated Learning Aggregation based on Weight Distribution Analysis

Federated Learning Aggregation based on Weight Distribution ...

引用

2023 IEEE International Conference on Imaging Systems and Techniques, IST 2023

作者： Chatzikonstantinou, Christos Konstantinidis, Dimitrios Dimitropoulos, Kosmas Daras, Petros Centre for Research and Technology Hellas Visual Computing Lab Information Technologies Institute Greece

ISBN: (纸本)9798350330830

Federated learning has recently been proposed as a solution to the problem of using private or sensitive data for training a central deep model, without exchanging the local data. In federated learning, local models are trained on the client side using the available data, while a server is responsible for aggregating the weights of these models into a global model. However, the traditional weight averaging approach does not take into consideration the importance of the different weights for the performance of a model. To this end, this work proposes a novel federated learning weight aggregation method that estimates the statistical distance of each client's parameters from the Gaussianity, and weighs the contribution of each client to the global model accordingly so that the most significant information is retained and enhanced. To create an accurate global model, a complex weighted averaging of the parameters of clients' models at the layer level is performed, considering as low quality the parameters following the Gaussian distribution. The proposed method can be employed to both convolutional and linear layers and it is based on the notion that parameters following a Gaussian distribution do not significantly affect the output of a model. Experiments with different network architectures and a comparison with a plethora of state-of-the-art approaches on three well-known image classification datasets demonstrate the superiority of the proposed method for federated learning weight aggregation. © 2023 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

3D Pose Estimation Using a Global and Local Cross-Attention Mechanism

3D Pose Estimation Using a Global and Local Cross-Attention ...

引用

2023 IEEE International Conference on Imaging Systems and Techniques, IST 2023

作者： Chatzis, Theocharis Konstantinidis, Dimitrios Dimitropoulos, Kosmas Daras, Petros Centre for Research and Technology Hellas Visual Computing Lab Information Technologies Institute Greece

ISBN: (纸本)9798350330830

The task of 3D human pose and shape estimation involves the accurate prediction of 3D joint coordinates using a single image or a video sequence and it is crucial in several computer vision fields, such as sign language recognition, human-computer interaction and autonomous vehicles. Existing methodologies typically rely on modeling global and local temporal relationships among image frames without paying much attention to the interaction between these relationships and the modeling of the input space in other manifolds that possess important statistical and geometrical properties. This work proposes a novel multi-stage 3D pose estimation method that seamlessly combines global and local temporal modeling through self-Attention mechanisms operating on multiple manifolds, thus leveraging the ability of different manifolds to model complementary features of the input space. Through the extraction of global and local attention maps and the fusion of these maps using a novel cross-Attention mechanism, the proposed method aims to enhance the contextual understanding and improve the capacity of the model to capture the intricate human motion dynamics present in a video sequence. The effectiveness of the proposed method in achieving precise 3D pose and shape across successive frames is confirmed by the experimental results on two challenging datasets, namely 3DPW and MPI-INF-3DHP. © 2023 IEEE.

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

2D-Pose Based Human Body Segmentation for Weakly-Supervised Concealed Object Detection in Backscatter Millimeter-Wave Images 26th

2D-Pose Based Human Body Segmentation for Weakly-Supervised...

引用

26th International Conference on Pattern Recognition, ICPR 2022

作者： Amadi, Lawrence Agam, Gady Visual Computing Lab Illinois Institute of Technology ChicagoIL60616 United States

ISBN: (纸本)9783031376597

The detection and localization of anomalies in backscatter images of a person is a standard procedure in airport security screening. Detecting a concealed item on a person and localizing the item to a specific body part requires the ability to recognize and segment distinct body parts. This can be challenging for backscatter images compared with RGB images due to lacking chromaticity cues and the limited availability of annotated backscatter images. To address this problem, we propose a weakly-supervised method for anomaly detection on human body parts which is based on an unsupervised body segmentation procedure that uses keypoints from a pretrained pose estimator to segment backscatter images without significant performance degradation. The paper presents a method for adapting a pretrained RGB pose estimator to segment human body parts in millimeter-wave images. We then train a body part-aware anomaly detection classifier to detect foreign objects on the body part. Our work is applied to TSA’s passenger screening dataset containing backscatter millimeter-wave scan images of airport travelers with binary labels that indicate whether a concealed item is attached to a body part. Our proposed approach significantly improves detection accuracy on 2D images from the baseline approach with a state-of-the-art performance of 97% F1-score and 0.0559 log-loss on TSA-PSD test set. © 2023, Springer Nature Switzerland AG.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Hardware/Software Solutions For an Efficient Thermal Scanning Mobile Robot 40

Hardware/Software Solutions For an Efficient Thermal Scannin...

引用

40th International Symposium on Automation and Robotics in Construction, ISARC 2023

作者： López-Rey, A. Ramón, A. Adán, A. 3D Visual Computing & Robotics Lab University of Castilla-La Mancha Spain

ISBN: (纸本)9780645832204

The use of robotic platforms greatly facilitates the reconstructions of 3D models of buildings and automates tasks that would be tiring and inaccurate when carried out manually. In the specific area of thermal monitoring of buildings, robots can also develop an important role providing dense temperature information of envelopes and structural elements. However, the current robot-based systems that extract thermal models can work under serious restrictions that concern, among others, the complexity of the scene, autonomy, navigation, and computation. This article discusses the limitations and restrictions of the current mobile scanning robots for thermal mapping inside buildings and proposes a thermal scanning robot that solves some of these issues. © ISARC 2023. All rights reserved.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

Detecting Human Distraction from Gaze: An Augmented Reality Approach in the Robotic Environment 12th

Detecting Human Distraction from Gaze: An Augmented Reality ...

引用

Proceedings of the 12th International Conference on Biomimetic and Biohybrid Systems, Living Machines 2023

作者： Zaparas, Panagiotis Katranitsiotis, Panagiotis Stavridis, Konstantinos Daras, Petros The Visual Computing Lab - Centre for Research and Technology Hellas/Information Technologies Institute Thessaloniki Greece

ISBN: (纸本)9783031388569

The investigation of human signals has been a topic of research since the advent of technology enabled their acquisition. Signals like gaze can reveal part of the human brain mechanisms. To facilitate the research of the analysis of these signals, researchers are developing and publishing datasets. This paper introduces the Augmented Reality DISTraction dataset (ARDIST), a novel dataset for processing human gaze. The primary objective of this dataset is to provide the scientific community with a resource that researchers can use to assess the distraction/attention levels of individuals performing specific tasks in the Robotic environment. The experiment was designed based on the latest findings in the field of neuroscience to include a diverse range of variables that affect human attention levels. Furthermore, the dataset can be utilized to model the human gaze signal under the influence of significant factors. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Augmented reality

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：