检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Jang, Hojun Kim, Young Min Dept. of Electrical and Computer Engineering Seoul National University Korea Republic of Interdisciplinary Program in Artificial Intelligence and INMC Seoul National University Korea Republic of

We present Reusable Motion prior (ReMP), an effective motion prior that can accurately track the temporal evolution of motion in various downstream tasks. Inspired by the success of foundation models, we argue that a robust spatio-temporal motion prior can encapsulate underlying 3D dynamics applicable to various sensor modalities. We learn the rich motion prior from a sequence of complete parametric models of posed human body shape. Our prior can easily estimate poses in missing frames or noisy measurements despite significant occlusion by employing a temporal attention mechanism. More interestingly, our prior can guide the system with incomplete and challenging input measurements to quickly extract critical information to estimate the sequence of poses, significantly improving the training efficiency for mesh sequence recovery. ReMP consistently outperforms the baseline method on diverse and practical 3D motion data, including depth point clouds, LiDAR scans, and IMU sensor data. Project page is available in https://***/ReMP. Copyright © 2024, The Authors. All rights reserved.

关键词： Reusability

来源：评论

学校读者我要写书评

暂无评论

Dynamic Mesh Recovery from Partial Point Cloud Sequence

Dynamic Mesh Recovery from Partial Point Cloud Sequence

引用

International Conference on computer Vision (ICCV)

作者： Hojun Jang Minkwan Kim Jinseok Bae Young Min Kim Dept. of Electrical and Computer Engineering Seoul National University Interdisciplinary Program in Artificial Intelligence and INMC Seoul National University

The exact 3D dynamics of the human body provides crucial evidence to analyze the consequences of the physical interaction between the body and the environment, which can eventually assist everyday activities in a wide range of applications. However, optimizing for 3D configurations from image observation requires a significant amount of computation, whereas real-world 3D measurements often suffer from noisy observation or complex occlusion. We resolve the challenge by learning a latent distribution representing strong temporal priors. We use a conditional variational autoencoder (CVAE) architecture with a transformer to train the motion priors with a large-scale motion dataset. Then our feature follower effectively aligns the feature spaces of noisy, partial observation with the necessary input for pre-trained motion priors, and quickly recovers a complete mesh sequence of motion. We demonstrate that the transformer-based autoencoder can collect necessary spatio-temporal correlations robust to various adversaries, such as missing temporal frames, or noisy observation under severe occlusion. Our framework is general and can be applied to recover the full 3D dynamics of other subjects with parametric representations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

P-flow: a fast and data-efficient zero-shot TTS through speech prompting 23

P-flow: a fast and data-efficient zero-shot TTS through spee...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Sungwon Kim Kevin J Shih Rohan Badlani João Felipe Santos Evelina Bhakturina Mikyas Desta Rafael Valle Sungroh Yoon Bryan Catanzaro NVIDIA and Department of Electrical and Computer Engineering Seoul National University NVIDIA Department of Electrical and Computer Engineering Seoul National University and Interdisciplinary Program in Artificial Intelligence Seoul National University

While recent large-scale neural codec language models have shown significant improvement in zero-shot TTS by training on thousands of hours of data, they suffer from drawbacks such as a lack of robustness, slow sampling speed similar to previous autoregressive TTS methods, and reliance on pre-trained neural codec representations. Our work proposes P-Flow, a fast and data-efficient zero-shot TTS model that uses speech prompts for speaker adaptation. P-Flow comprises a speech-prompted text encoder for speaker adaptation and a flow matching generative decoder for high-quality and fast speech synthesis. Our speech-prompted text encoder uses speech prompts and text input to generate speaker-conditional text representation. The flow matching generative decoder uses the speaker-conditional output to synthesize high-quality personalized speech significantly faster than in real-time. Unlike the neural codec language models, we specifically train P-Flow on LibriTTS dataset using a continuous mel-representation. Through our training method using continuous speech prompts, P-Flow matches the speaker similarity performance of the large-scale zero-shot TTS models with two orders of magnitude less training data and has more than 20× faster sampling speed. Our results show that P-Flow has better pronunciation and is preferred in human likeness and speaker similarity to its recent state-of-the-art counterparts, thus defining P-Flow as an attractive and desirable alternative. We provide audio samples on our demo page https://***/labs/adlr/projects/pflow.

关键词：

来源：评论

学校读者我要写书评

暂无评论

NEW INSIGHTS FOR THE STABILITY-PLASTICITY DILEMMA IN ONLINE CONTINUAL LEARNING 11

NEW INSIGHTS FOR THE STABILITY-PLASTICITY DILEMMA IN ONLINE ...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Jung, Dahuin Lee, Dongjin Hong, Sunwon Jang, Hyemi Bae, Ho Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Korea Republic of DeepBrain AI Inc. Korea Republic of Department of Cyber Security Ewha Womans University Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul08826 Korea Republic of

The aim of continual learning is to learn new tasks continuously (i.e., plasticity) without forgetting previously learned knowledge from old tasks (i.e., stability). In the scenario of online continual learning, wherein data comes strictly in a streaming manner, the plasticity of online continual learning is more vulnerable than offline continual learning because the training signal that can be obtained from a single data point is limited. To overcome the stability-plasticity dilemma in online continual learning, we propose an online continual learning framework named multi-scale feature adaptation network (MuFAN) that utilizes a richer context encoding extracted from different levels of a pre-trained network. Additionally, we introduce a novel structure-wise distillation loss and replace the commonly used batch normalization layer with a newly proposed stability-plasticity normalization module to train MuFAN that simultaneously maintains high plasticity and stability. MuFAN outperforms other state-of-the-art continual learning methods on the SVHN, CIFAR100, miniImageNet, and CORe50 datasets. Extensive experiments and ablation studies validate the significance and scalability of each proposed component: 1) multi-scale feature maps from a pre-trained encoder, 2) the structure-wise distillation loss, and 3) the stability-plasticity normalization module in MuFAN. Code is publicly available at https://***/whitesnowdrop/MuFAN. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Stability

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Real-Time Multi-Person Pose Detection in Electrical Industrial Safety Scenarios Using YOLOv8-Pose and OpenPose 4

Comparative Analysis of Real-Time Multi-Person Pose Detectio...

引用

4th IEEE International Conference on Electronic Communications, Internet of Things and Big Data, ICEIB 2024

作者： Tsai, Shang-Te Wu, Zong-Rong Lin, Pin-Hsuan Chen, Chin-Hsiung Chien, Wei Chang, Yu-Cheng School of Art and Design Sanming University Fujian365004 China National Yunlin University of Science and Technology Department of Technical and Vocational Program in Artificial Intelligence Yunlin Taiwan National Central University Department of Business Administration Taoyuan Taiwan Commercial Industrial Vocational Senior High School Department of Electrical Engineering New Taipei Municipal Tamsui New Taipei Taiwan Lunghwa University of Science and Technology Department of Computer Information and Network Engineering Taoyuan Taiwan National Taipei University of Technology Department of Computer Science and Information Engineering Taipei Taiwan

ISBN: (纸本)9798350360721

We reviewed the application of modern technology for rapid and accurate multi-person real-time pose detection in the hazardous field of electrical engineering. We focused on two leading pose detection technologies: YOLOv8 and OpenPose. To optimize performance, we integrated these two techniques into the LSTM model for training and investigated frame rates and accuracy. © 2024 IEEE.

关键词： Accident prevention

来源：评论

学校读者我要写书评

暂无评论

AI-Powered Precision: Revolutionizing Skin Cancer Detection with Advanced Machine Learning

AI-Powered Precision: Revolutionizing Skin Cancer Detection ...

引用

Novel Intelligent and Leading Emerging Sciences Conference (NILES)

作者： Mariam M. Abd-elaziz Basma M. Elshafie Hagar Abdullah Karen Y. Gerges Ingy A. Ghanem Khaled M. Fouad Amir El-Ghamry Ibrahim F. Moawad Sara El-Metwally Faculty of computer science and engineering New Mansoura university Dakahlia Egypt Faculty of Engineering Computer and Communication program Faculty of Computer Science and Engineering Mansoura University New Mansoura University Information Systems Faculty of Computers and Artificial Intelligence Benha University Egypt Faculty of Computer and Information Sciences Faculty of Computer Science and Engineering Mansoura University New Mansoura University Egypt School of Engineering and Computer Science University of Hertfordshire GAF Egypt Faculty of Computer and Information Sciences Ain Shams University Cairo Egypt Department of Artificial Intelligence College of Computer Science and Engineering Taibah University Medina Saudi Arabia

ISBN: (数字)9798350378511

ISBN: (纸本)9798350378528

Skin cancer's increasing incidence rates necessitate advanced diagnostic tools. This research uses MobileNet architecture to develop an enhanced system for skin cancer detection. MobileNet's efficient CNN architecture, combined with Keras for model lifecycle management and TensorFlow for real-time inference, forms the foundation of this study. Using 10,015 dermatoscopic pictures from seven different classifications of skin cancer in the HAM10000 dataset, the methodology includes several key stages: image preprocessing to correct illumination and adjust resolution, data augmentation to balance the dataset, and model training using Transfer Learning. The MobileNet model was trained over 50 epochs with a comprehensive architecture incorporating multiple specialized layers. By combining large-scale data analysis and adaptive learning, this methodology demonstrates The revolutionary possibilities of AI and ML in improving skin cancer diagnostics and public health outcomes. Keywords Skin Cancer Detection, Dermatoscopic Images, Machine Learning, Deep Learning

关键词： Training Deep learning Adaptation models Image resolution Transfer learning Lighting Real-time systems Image preprocessing Public healthcare Skin cancer

来源：评论

学校读者我要写书评

暂无评论

Zero-Shot Vision-and-Language Navigation with Collision Mitigation in Continuous Environment

arXiv

引用

arXiv 2024年

作者： Jeong, Seongjun Kang, Gi-Cheon Kim, Joochan Zhang, Byoung-Tak Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of Dept. of Computer Science and Engineering Seoul National University Korea Republic of Korea Republic of

We propose the zero-shot Vision-and-Language Navigation with Collision Mitigation (VLN-CM), which takes these considerations. VLN-CM is composed of four modules and predicts the direction and distance of the next movement at each step. We utilize large foundation models for each modules. To select the direction, we use the Attention Spot Predictor (ASP), View Selector (VS), and Progress Monitor (PM). The ASP employs a Large Language Model (e.g. ChatGPT) to split navigation instructions into attention spots, which are objects or scenes at the location to move to (e.g. a yellow door). The VS selects from panorama images provided at 30-degree intervals the one that includes the attention spot, using CLIP similarity. We then choose the angle of the selected image as the direction to move in. The PM uses a rule-based approach to decide which attention spot to focus on next, among multiple spots derived from the instructions. If the similarity between the current attention spot and the visual observations decreases consecutively at each step, the PM determines that the agent has passed the current spot and moves on to the next one. For selecting the distance to move, we employed the Open Map Predictor (OMP). The OMP uses panorama depth information to predict an occupancy mask. We then selected a collision-free distance in the predicted direction based on the occupancy mask. We evaluated our method using the validation data of VLN-CE. Our approach showed better performance than several baseline methods, and the OPM was effective in mitigating collisions for the agent. © 2024, CC BY-NC-ND.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Sample-efficient Adversarial Imitation Learning

arXiv

引用

arXiv 2023年

作者： Jung, Dahuin Lee, Hyungyu Yoon, Sungroh Electrical and Computer Engineering Seoul National University Seoul08826 Korea Republic of Electrical and Computer Engineering Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul08826 Korea Republic of

Imitation learning, in which learning is performed by demonstration, has been studied and advanced for sequential decision-making tasks in which a reward function is not predefined. However, imitation learning methods still require numerous expert demonstration samples to successfully imitate an expert’s behavior. To improve sample efficiency, we utilize self-supervised representation learning, which can generate vast training signals from the given data. In this study, we propose a self-supervised representation-based adversarial imitation learning method to learn state and action representations that are robust to diverse distortions and temporally predictive, on non-image control tasks. In particular, in comparison with existing self-supervised learning methods for tabular data, we propose a different corruption method for state and action representations that is robust to diverse distortions. We theoretically and empirically observe that making an informative feature manifold with less sample complexity significantly improves the performance of imitation learning. The proposed method shows a 39% relative improvement over existing adversarial imitation learning methods on MuJoCo in a setting limited to 100 expert state-action pairs. Moreover, we conduct comprehensive ablations and additional experiments using demonstrations with varying optimality to provide insights into a range of factors. Copyright © 2023, The Authors. All rights reserved.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Investigating the Relation between Code Comments and Issue Resolution Time in Java Repositories

Investigating the Relation between Code Comments and Issue R...

引用

IEEE International Conference on Intelligent Computing and Information Systems (ICICIS)

作者： Ahmed Ashraf Hamza Mohammad El-Ramly Manar ElKady M.Sc. in Software Engineering Program Faculty of Computers and Artificial Intelligence Cairo University Cairo Egypt Department of Computer Sciences Faculty of Computers and Artificial Intelligence Cairo University Cairo Egypt

Source code comments play a critical role in software development by facilitating issue resolution and reducing maintenance time and cost. However, the impact of code comments, particularly those aiding program comprehension, on expediting issue resolution remains insufficiently explored. This study investigates the impact of code comments on issue resolution time for issues related to pulling requests involving code maintenance. To this end, ten of the most popular Java repositories on GitHub were selected, and closed pull request-related issues were identified using a specific criterion. Comments were then extracted from classes modified by the pull requests, and a trained BERT model was utilized to classify them according to their usefulness. The percentage of comments relative to code size, the percentage of useful comments relative to all comments, and the average issue resolution time were computed and examined for correlations. The results indicate a negative correlation (-0.68) between the percentage of code comments in modified classes and the average issue resolution time. A stronger negative correlation (-0.73) was found between the percentage of useful code comments to all comments in modified classes and the average issue resolution time per class. These findings demonstrate that code with more comments, particularly useful ones, leads to faster issue resolution. This serves as a basis for further research into the impact of various fine-grained comment types on issue resolution time in different programming languages. Also, it can assist developers in writing more effective comments that accelerate bug-fixing and reduce software maintenance efforts.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Balanced Spherical Grid for Egocentric View Synthesis

Balanced Spherical Grid for Egocentric View Synthesis

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Changwoon Choi Sang Min Kim Young Min Kim Dept. of Electrical and Computer Engineering Seoul National University Korea Interdisciplinary Program in Artificial Intelligence and INMC Seoul National University

We present EgoNeRF, a practical solution to reconstruct large-scale real-world environments for VR assets. Given a few seconds of casually captured 360 video, EgoNeRF can efficiently build neural radiance fields. Motivated by the recent acceleration of NeRF using feature grids, we adopt spherical coordinate instead of conventional Cartesian coordinate. Cartesian feature grid is inefficient to represent large-scale unbounded scenes because it has a spatially uniform resolution, regardless of distance from viewers. The spherical parameterization better aligns with the rays of egocentric images, and yet enables factorization for performance enhancement. However, the naive spherical grid suffers from singularities at two poles, and also cannot represent unbounded scenes. To avoid singularities near poles, we combine two balanced grids, which results in a quasi-uniform angular grid. We also partition the radial grid exponentially and place an environment map at infinity to represent unbounded scenes. Furthermore, with our resampling technique for grid-based methods, we can increase the number of valid samples to train NeRF volume. We extensively evaluate our method in our newly introduced synthetic and real-world egocentric 360 video datasets, and it consistently achieves state-of-the-art performance.

关键词：

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：