检索结果-内蒙古大学图书馆

ieee computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： Aayush Dhakal Adeel Ahmad Subash Khanal Srikumar Sastry Hannah Kerner Nathan Jacobs Washington University in St. Louis Taylor Geospatial Institute Arizona State University

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

We propose a weakly supervised approach for creating maps using free-form textual descriptions. We refer to this work of creating textual maps as zero-shot mapping. Prior works have approached mapping tasks by developing models that predict a fixed set of attributes using overhead imagery. However, these models are very restrictive as they can only solve highly specific tasks for which they were trained. Mapping text, on the other hand, allows us to solve a large variety of mapping problems with minimal restrictions. To achieve this, we train a contrastive learning framework called Sat2Cap on a new large-scale dataset with 6.1M pairs of overhead and ground-level images. For a given location and overhead image, our model predicts the expected CLIP embeddings of the ground-level scenery. The predicted CLIP embeddings are then used to learn about the textual space associated with that location. Sat2Cap is also conditioned on date-time information, allowing it to model temporally varying concepts over a location. Our experimental results demonstrate that our models successfully capture ground-level concepts and allow large-scale mapping of fine-grained textual queries. Our approach does not require any text-labeled data, making the training easily scalable. The code, dataset, and models will be made publicly available.

关键词： Training computer vision Codes Geology conferences Contrastive learning Predictive models

来源：评论

学校读者我要写书评

暂无评论

Dedicated Inference Engine and Binary-Weight Neural Networks for Lightweight Instance Segmentation

Dedicated Inference Engine and Binary-Weight Neural Networks...

引用

ieee computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： Tse-Wei Chen Wei Tao Dongyue Zhao Kazuhiro Mima Tadayuki Ito Kinya Osa Masami Kato Device Technology Development Headquarters Canon Inc. Tokyo Japan Canon Innovative Solution (Beijing) Co. Ltd. Beijing China

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

Binary-weight Neural Networks (BNNs), in which weights are binarized and activations are quantized, are employed to reduce computational costs of various kinds of applications. In this paper, a design methodology of hardware architecture for inference engines is proposed to handle modern BNNs with two operation modes. Multiply-Accumulate (MAC) operations can be simplified by replacing multiply operations with bitwise operations. The proposed method can effectively reduce the gate count of inference engines by removing a part of computational costs from the hardware system. The architecture of MAC operations can calculate the inference results of BNNs efficiently with only 52% of hardware costs compared with the related works. To show that the inference engine can handle practical applications, two lightweight networks which combine the backbones of SegNeXt and the decoder of SparseInst for instance segmentation are also proposed. The output results of the lightweight networks are computed using only bitwise operations and add operations. The proposed inference engine has lower hardware costs than related works. The experimental results show that the proposed inference engine can handle the proposed instance-segmentation networks and achieves higher accuracy than YOLACT on the "Person" category although the model size is 77.7× smaller compared with YOLACT.

关键词： Instance segmentation Costs Accuracy Design methodology Neural networks computer architecture Logic gates

来源：评论

学校读者我要写书评

暂无评论

Cross-Temporal Spectrogram Autoencoder (CTSAE): Unsupervised Dimensionality Reduction for Clustering Gravitational Wave Glitches

Cross-Temporal Spectrogram Autoencoder (CTSAE): Unsupervised...

引用

ieee computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： Yi Li Yunan Wu Aggelos K. Katsaggelos The Department of Computer Science Northwestern University Evanston IL The Department of Electrical Computer Engineering Northwestern University Evanston IL

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

The advancement of The Laser Interferometer Gravitational-Wave Observatory (LIGO) has significantly enhanced the feasibility and reliability of gravitational wave detection. However, LIGO’s high sensitivity makes it susceptible to transient noises known as glitches, which necessitate effective differentiation from real gravitational wave signals. Traditional approaches predominantly employ fully supervised or semi-supervised algorithms for the task of glitch classification and clustering. In the future task of identifying and classifying glitches across main and auxiliary channels, it is impractical to build a dataset with manually labeled ground-truth. In addition, the patterns of glitches can vary with time, generating new glitches without manual labels. In response to this challenge, we introduce the Cross-Temporal Spectrogram Autoencoder (CTSAE), a pioneering unsupervised method for the dimensionality reduction and clustering of gravitational wave glitches. CTSAE integrates a novel four-branch autoencoder with a hybrid of Convolutional Neural Networks (CNN) and vision Transformers (ViT). To further extract features across multi-branches, we introduce a novel multi-branch fusion method using the CLS (Class) token. Our model, trained and evaluated on the GravitySpy O3 dataset on the main channel, demonstrates superior performance in clustering tasks when compared to state-of-the-art semi-supervised learning methods. To the best of our knowledge, CTSAE represents the first unsupervised approach tailored specifically for clustering LIGO data, marking a significant step forward in the field of gravitational wave research. The code of this paper is available at https://***/Zod-L/CTSAE

关键词： Dimensionality reduction computer vision Sensitivity Gravitational waves Sensor phenomena and characterization Feature extraction Transformers

来源：评论

学校读者我要写书评

暂无评论

NTIRE 2021 Learning the Super-Resolution Space Challenge

NTIRE 2021 Learning the Super-Resolution Space Challenge

引用

ieee/cvf conference on computer vision and pattern recognition (CVPR)

作者： Lugmayr, Andreas Danelljan, Martin Timofte, Radu Busch, Christoph Chen, Yang Cheng, Jian Chudasama, Vishal Gang, Ruipeng Gao, Shangqi Gao, Kun Gong, Laiyun Han, Qingrui Huang, Chao Jin, Zhi Jo, Younghyun Kim, Seon Joo Kim, Younggeun Lee, Seungjun Lei, Yuchen Li, Chu-Tak Li, Chenghua Li, Ke Liu, Zhi-Song Liu, Youming Nan, Nan Park, Seung-Ho Patel, Heena Peng, Shichong Prajapati, Kalpesh Qi, Haoran Raja, Kiran Ramachandra, Raghavendra Siu, Wan-Chi Son, Donghee Song, Ruixia Upla, Kishor Wang, Li-Wen Wang, Yatian Wang, Junwei Wu, Qianyu Xu, Xinhua Yang, Sejong Yuan, Zhen Zhang, Liting Zhang, Huanrong Zhang, Junkai Zhang, Yifan Zhang, Zhenzhou Zhou, Hangqi Zhu, Aichun Zhuang, Xiahai Zou, Jiaxin Swiss Fed Inst Technol Zurich Switzerland Swiss Fed Inst Technol Comp Vis Lab Zurich Switzerland Zhejiang Univ Hangzhou Peoples R China NetEaseYunXin Beijing Peoples R China Yonsei Univ Seoul South Korea Seoul Natl Univ Seoul South Korea Univ Ulsan Coll Med Asan Med Ctr Ulsan South Korea Lomin Inc Portland OR USA Fudan Univ Shanghai Peoples R China Simon Fraser Univ Burnaby BC Canada Caritas Inst Higher Educ Hong Kong Peoples R China Hong Kong Polytech Univ Hong Kong Peoples R China Sun Yat Sen Univ Guangzhou Peoples R China North China Univ Technol Beijing Peoples R China Univ Elect Sci & Technol China Chengdu Peoples R China CASIA Beijing Peoples R China NRTA Beijing Peoples R China NCUT Beijing Peoples R China Nanjing Tech Univ Sch Comp Sci & Technol Nanjing Peoples R China Southeast Univ Lab Image Sci & Technol Nanjing Peoples R China SVNIT Surat Gujarat India NTNU Trondheim Norway

ISBN: (纸本)9781665448994

This paper reviews the NTIRE 2021 challenge on learning the super-Resolution space. It focuses on the participating methods and final results. The challenge addresses the problem of learning a model capable of predicting the space of plausible super-resolution (SR) images, from a single low-resolution image. The model must thus be capable of sampling diverse outputs, rather than just generating a single SR image. The goal of the challenge is to spur research into developing learning formulations and models better suited for the highly ill-posed SR problem. And thereby advance the state-of-the-art in the broader SR field. In order to evaluate the quality of the predicted SR space, we propose a new evaluation metric and perform a comprehensive analysis of the participating methods. The challenge contains two tracks: 4x and 8 x scale factor. In total, 11 teams competed in the final testing phase.

关键词： Measurement computer vision conferences Superresolution Predictive models pattern recognition

来源：评论

学校读者我要写书评

暂无评论

DMR: Disentangling Marginal Representations for Out-of-Distribution Detection

DMR: Disentangling Marginal Representations for Out-of-Distr...

引用

ieee computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： Dasol Choi Dongbin Na MODULABS Yonsei University Pohang University of Science and Technology

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

Out-of-Distribution (OOD) detection is crucial for the reliable deployment of deep-learning applications. When a given input image does not belong to any categories of the deployed classification model, the classification model is expected to alert the user that the predicted outputs might be unreliable. Recent studies have shown that utilizing a large amount of explicit OOD training data is helpful for improving OOD detection performance. However, collecting explicit real-world OOD data is burdensome, and pre-defining all out-of-distribution labels is fundamentally difficult. In this work, we present a novel method, Disentangling Marginal Representations (DMR), that generates artificial OOD training data by extracting marginal features from images of an In-Distribution (ID) training dataset and manipulating these extracted marginal representations. DMR is intuitive and can be used as a realistic solution that does not require any extra real-world OOD data. Moreover, our method can be simply applied to pre-trained classifier networks without affecting the original classification performance. We demonstrate that a shallow rejection network that is trained on the small subset of synthesized OOD training data generated from our method and attachable to the classifier network achieves superior OOD detection performance. With extensive experiments, we show that our proposed method significantly outperforms the state-of-the-art OOD detection methods on the broadly used CIFAR-10 and CIFAR-100 detection benchmark datasets. We also demonstrate that our proposed method can be further improved when combined with existing methods. The source codes are publicly available at https://***/ndb796/DMR.

关键词： Training computer vision Source coding conferences Training data Predictive models Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Speech2UnifiedExpressions: Synchronous Synthesis of Co-Speech Affective Face and Body Expressions from Affordable Inputs

Speech2UnifiedExpressions: Synchronous Synthesis of Co-Speec...

引用

ieee computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： Uttaran Bhattacharya Aniket Bera Dinesh Manocha Adobe Inc. San Jose CA USA Purdue University West Lafayette IN USA University of Maryland College Park MD USA

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

We present a multimodal learning-based method to simultaneously synthesize co-speech facial expressions and upper-body gestures for digital characters using RGB video data captured using commodity cameras. Our approach learns from sparse face landmarks and upper-body joints, estimated directly from video data, to generate plausible emotive character motions. Given a speech audio waveform and a token sequence of the speaker’s face landmark motion and body-joint motion computed from a video, our method synthesizes the motion sequences for the speaker’s face landmarks and body joints to match the content and the affect of the speech. We design a generator consisting of a set of encoders to transform all the inputs into a multimodal embedding space capturing their correlations, followed by a pair of decoders to synthesize the desired face and pose motions. To enhance the plausibility of synthesis, we use an adversarial discriminator that learns to differentiate between the face and pose motions computed from the original videos and our synthesized motions based on their affective expressions. To evaluate our approach, we extend the TED Gesture Dataset to include view-normalized, co-speech face landmarks in addition to body gestures. We demonstrate the performance of our method through thorough quantitative and qualitative experiments on multiple evaluation metrics and via a user study. We observe that our method results in low reconstruction error and produces synthesized samples with diverse facial expressions and body gestures for digital characters. The relevant source code and dataset are available at https://***/UttaranB127/speech2unified_expressions.

关键词： Measurement Learning systems computer vision Correlation Face recognition Source coding conferences

来源：评论

学校读者我要写书评

暂无评论

Correction to: Automated facial expression recognition using exemplar hybrid deep feature generation technique (Soft Computing, (2023), 27, 13, (8721-8737), 10.1007/s00500-023-08230-9)

引用

Soft Computing 2024年 1-2页

作者： Baygin, Mehmet Tuncer, Ilknur Dogan, Sengul Barua, Prabal Datta Tuncer, Turker Cheong, Kang Hao Acharya, U. Rajendra Department of Computer Engineering Faculty of Engineering Ardahan University Ardahan Turkey Interior Ministry Elazig Turkey Department of Digital Forensics Engineering Technology Faculty Firat University Elazig Turkey University of Southern Queensland ToowoombaQLD4350 Australia Faculty of Engineering and Information Technology University of Technology Sydney SydneyNSW2007 Australia Science Mathematics and Technology Cluster Singapore University of Technology and Design Singapore487372 Singapore School of Mathematics Physics and Computing University of Southern Queensland Springfield Australia

The author found that the below references were not included in the published article. Kanade T, Cohn JF, Tian Y (2000) Comprehensive database for facial expression analysis. In: Proc-4th ieee int conf autom face gesture recognition, FG 2000, pp 46–53. Lucey P, Cohn JF, Kanade T et al (2010) The extended Cohn–Kanade dataset (CK+): a complete dataset for action unit and emotion-specified expression. In: 2010 ieee comput soc conf comput vis pattern recognit-work cvprw 2010, pp 94–101. Pantic M, Valstar M, Rademaker R, Maat L (2005) Web-based database for facial expression analysis. In: ieee int conf multimed expo, ICME 2005, pp 317–321. Li S, Deng W, Du J (2017) Reliable crowdsourcing and deep locality-preserving learning for expression recognition in the wild. In: Proceedings of the ieee conference on computer vision and pattern recognition, pp 2852–2861 Yin L, Wei X, Sun Y et al (2006) A 3D facial expression database for facial behavior research. In: FGR 2006 proc 7th int conf autom face gesture recognit 2006, pp 211–216. Goodfellow IJ, Erhan D, Luc Carrier P et al (2015) Challenges in representation learning: a report on three machine learning contests. Neural Netw 64:59–63. Zhang Z, Luo P, Loy CC, Tang X (2018) From facial expression recognition to interpersonal relation prediction. Int J Comput Vis 126:550–569. Chen L-F, Yen Y-S (2007) Taiwanese facial expression image database. Brain Mapp Lab Inst Brain Sci Natl Yang-Ming Univ Taipei, Taiwan Lyons MJ, Kamachi M, Gyoba J (2020) Coding facial expressions with Gabor wavelets (IVC special issue). Lyons MJ (2021) "Excavating AI" re-excavated: debunking a fallacious account of the JAFFE Dataset. Lundqvist D, Flykt A, Ohman A (1998) The Karolinska directed emotional faces (KDEF). CD ROM from Dep Clin Neurosci Psychol Sect Karolinska Institutet 2–2 Zhao G, Huang X, Taini M et al (2011) Facial expression recognition from near-infrared videos. Image Vis Comput 29:607–619. Goldberger J, Hinton GE, Roweis S, Salakhutdinov R

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards Efficient Machine Unlearning with Data Augmentation: Guided Loss-Increasing (GLI) to Prevent the Catastrophic Model Utility Drop

Towards Efficient Machine Unlearning with Data Augmentation:...

引用

ieee computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： Dasol Choi Soora Choi Eunsun Lee Jinwoo Seo Dongbin Na Yonsei University MODULABS Chung Ang University Kyung Hee University Millennialsworks Inc. POSTECH

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

Machine unlearning algorithms aim to make a model forget specific data that might be used in the training phase. To solve this problem, various studies have adopted loss-increasing methods. For example, some unlearning methods have presented data augmentation methods to generate synthesized images that maximize loss values for images to be forgotten. In contrast, some unlearning methods directly update the model in the direction of increasing loss for the images to be forgotten. In this paper, we first revisit these loss-increasing methods and analyze their limitations. We have found that these simple loss-increasing strategies can be effective in the aspect of the forgetting score, however, can hurt the original model utility unexpectedly, we call this phenomenon catastrophic model utility drop. We propose a novel data augmentation method, Guided Loss-Increasing (GLI), that restricts the direction of the data update to resolve the utility drop issue. This is achieved by aligning updates with the model’s existing knowledge, thereby ensuring that the unlearning process does not adversely affect the model’s original performance. Our extensive experiments demonstrate our method shows superior (1) model utility and (2) forgetting performance compared to the previous state-of-the-art (SOTA) methods. Furthermore, we demonstrate Jensen–Shannon divergence can be utilized to robustly evaluate the forgetting score. The source codes are publicly available at https://***/Dasol-Choi/Guided_Loss_Increasing.

关键词： Measurement Training computer vision Source coding conferences Computational modeling Data augmentation

来源：评论

学校读者我要写书评

暂无评论

Video Anomaly Detection via Spatio-Temporal Pseudo-Anomaly Generation : A Unified Approach

Video Anomaly Detection via Spatio-Temporal Pseudo-Anomaly G...

引用

ieee computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： Ayush K. Rai Tarun Krishna Feiyan Hu Alexandru Drimbarean Kevin McGuinness Alan F. Smeaton Noel E. O’Connor Insight SFI Centre for Data Analytics Dublin City University Tobii Corporation Galway

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

Video Anomaly Detection (VAD) is an open-set recognition task, which is usually formulated as a one-class classification (OCC) problem, where training data is comprised of videos with normal instances while test data contains both normal and anomalous instances. Recent works have investigated the creation of pseudo-anomalies (PAs) using only the normal data and making strong assumptions about real-world anomalies with regards to abnormality of objects and speed of motion to inject prior information about anomalies in an autoencoder (AE) based reconstruction model during training. This work proposes a novel method for generating generic spatio-temporal PAs by inpainting a masked out region of an image using a pre-trained Latent Diffusion Model and further perturbing the optical flow using mixup to emulate spatio-temporal distortions in the data. In addition, we present a simple unified framework to detect real-world anomalies under the OCC setting by learning three types of anomaly indicators, namely reconstruction quality, temporal irregularity and semantic inconsistency. Extensive experiments on four VAD benchmark datasets namely Ped2, Avenue, ShanghaiTech and UBnormal demonstrate the effectiveness of our work against other existing state-of-the-art PAs generation and reconstruction based methods under the OCC setting. Our analysis also examines the transferability and generalisation of PAs across these datasets, offering valuable insights by identifying real-world anomalies through PAs. Our results can be reproduced on github.

关键词： Training Semantics Training data Optical distortion Distortion pattern recognition Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Analyzing Participants’ Engagement during Online Meetings Using Unsupervised Remote Photoplethysmography with Behavioral Features

Analyzing Participants’ Engagement during Online Meetings U...

引用

ieee computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： Alexander Vedernikov Zhaodong Sun Virpi-Liisa Kykyri Mikko Pohjola Miriam Nokia Xiaobai Li Center for Machine Vision and Signal Analysis University of Oulu Finland Department of Psychology University of Jyväskylä Finland State Key Laboratory of Blockchain and Data Security Zhejiang University China

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

Engagement measurement finds application in healthcare, education, services. The use of physiological and behavioral features is viable, but the impracticality of traditional physiological measurement arises due to the need for contact sensors. We demonstrate the feasibility of unsupervised remote photoplethysmography (rPPG) as an alternative for contact sensors in deriving heart rate variability (HRV) features, then fusing these with behavioral features to measure engagement in online group meetings. Firstly, a unique Engagement Dataset of online interactions among social workers is collected with granular engagement labels, offering insight into virtual meeting dynamics. Secondly, a pre-trained rPPG model is customized to reconstruct rPPG signals from video meetings in an unsupervised manner, enabling the calculation of HRV features. Thirdly, the feasibility of estimating engagement from HRV features using short observation windows, with a notable enhancement when using longer observation windows of two to four minutes, is demonstrated. Fourthly, the effectiveness of behavioral cues is evaluated when fused with physiological data, which further enhances engagement estimation performance. An accuracy of 94% is achieved when only HRV features are used, eliminating the need for contact sensors or ground truth signals; use of behavioral cues raises the accuracy to 96%. Facial analysis offers precise engagement measurement, beneficial for future applications.

关键词： Accuracy Atmospheric measurements Estimation Web conferencing Sensor phenomena and characterization Photoplethysmography Particle measurements

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：