检索结果-内蒙古大学图书馆

DASOD: Detail-aware salient object detection

IMAGE AND VISION COMPUTING 2024年 148卷

作者： Asheghi, Bahareh Salehpour, Pedram Khiavi, Abdolhamid Moallemi Hashemzadeh, Mahdi Monajemi, Amirhassan Univ Tabriz Fac Elect & Comp Engn Dept Comp Engn Tabriz Iran Azarbaijan Shahid Madani Univ Fac Informat Technol & Comp Engn Tabriz Iran Azarbaijan Shahid Madani Univ Artificial Intelligence & Machine Learning Res Lab Tabriz Iran Natl Univ Singapore Sch Comp Dept Comp Sci Singapore Singapore

Salient object detection (SOD) is a challenging task in computer vision. Current SOD approaches have made significant progress, but they fail in challenging scenarios. This paper categorizes the existing challenges in SOD into four groups: images with complex backgrounds, low contrast, transparent objects, and occluded objects. Then, the Detail-Aware Salient Object Detection (DASOD) method is proposed to address these challenging scenarios. To the best of our knowledge, DASOD is the first method that considers mentioned challenging situations together and detects salient objects in images through camouflaged object detection (COD). DASOD has two main stages: 1) pseudo-mask generation and 2) refinement. It first generates a pseudo-mask using the body label and super-resolution technique, then refines the pseudo-mask with the detail map produced by the pseudoedge generator to detect salient objects with clear boundaries in the pseudo-mask refinement module. This module quantifies uncertainty using the conditional normalizing flows (cFlow) based conditional variational auto-encoder (cVAE) to generate reliable results. Extensive experiments are conducted on six datasets, and the performance of DASOD is compared with 18 state-of-the-art methods. The results demonstrate that DASOD outperforms its competitors and can accurately detect the salient objects when the image background is cluttered and the contrast between foreground and background is low. Also, it effectively detects the transparent and occluded objects in images. It achieves MAE rates of 0.052, 0.033, 0.027, 0.024, 0.059, and 0.088 on DUTOMRON, DUTS-TE, ECSSD, HKU-IS, PASCAL-S, and SCAS datasets, respectively. All the implementation source codes and results are available at: https://***/BaharehAsheghi/DASOD.

关键词： conditional variational auto-encoder Uncertainty quantification Refinement network Saliency detection Salient object detection SOD

来源：评论

学校读者我要写书评

暂无评论

EDITnet: A Lightweight Network for Unsupervised Domain Adaptation in Speaker Verification 23

EDITnet: A Lightweight Network for Unsupervised Domain Adapt...

引用

Interspeech Conference

作者： Li, Jingyu Liu, Wei Lee, Tan Chinese Univ Hong Kong Dept Elect Engn Hong Kong Peoples R China

Performance degradation caused by language mismatch is a common problem when applying a speaker verification system on speech data in different languages. This paper proposes a domain transfer network, named EDITnet, to alleviate the language-mismatch problem on speaker embeddings without requiring speaker labels. The network leverages a conditional variational auto-encoder to transfer embeddings from the target domain into the source domain. A self-supervised learning strategy is imposed on the transferred embeddings so as to increase the cosine distance between embeddings from different speakers. In the training process of the EDITnet, the embedding extraction model is fixed without fine-tuning, which renders the training efficient and low-cost. Experiments on Voxceleb and CN-Celeb show that the embeddings transferred by EDITnet outperform the un-transferred ones by around 30% with the ECAPA-TDNN512. Performance improvement can also be achieved with other embedding extraction models, e.g., TDNN, SE-ResNet34.

关键词： speaker verification domain adaptation conditional variational auto-encoder self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

variational DEPTH ESTIMATION ON HYPERSPHERE FOR PANORAMA 29

VARIATIONAL DEPTH ESTIMATION ON HYPERSPHERE FOR PANORAMA

引用

IEEE International Conference on Image Processing (ICIP)

作者： Miao, Jingbo Liu, Yanwei Wang, Kan Liu, Jinxia Xu, Zhen Chinese Acad Sci Inst Informat Engn Beijing Peoples R China Univ Chinese Acad Sci Sch Cyber Secur Beijing Peoples R China Zhejiang Wanli Univ Ningbo Peoples R China

ISBN: (数字)9781665496209

ISBN: (纸本)9781665496209

Depth estimation for panorama is a key part of 3D scene understanding, and adopting discriminative models is the most common solution. However, due to the rectangular convolution kernel, these existing learning methods cannot efficiently extract the distorted features in panoramas. To this end, we propose OmniVAE, a generative model based on conditional variational auto-encoder (CVAE) and von Mises-Fisher (vMF) distribution, to strengthen the exclusive generative ability for spherical signals by mapping panoramas to hypersphere space. Further, to alleviate the side effects of manifold-mismatching caused by non-planar distribution, we put forward the Atypical Receptive Field (ARF) module to slightly shift the receptive field of the network and even take the distribution difference into account in the reconstruction loss. The quantitative and qualitative evaluations are performed on real-world and synthetic datasets, and the results show that OmniVAE outperforms the state-of-the-art methods.

关键词： Panorama depth estimation hypersphere space conditional variational auto-encoder

来源：评论

学校读者我要写书评

暂无评论

Learning emotions latent representation with CVAE for text-driven expressive audiovisual speech synthesis

引用

NEURAL NETWORKS 2021年 141卷 315-329页

作者： Dahmani, Sara Colotte, Vincent Girard, Valerian Ouni, Slim Univ Lorraine CNRS INRIA LORIA F-54000 Nancy France

Great improvement has been made in the field of expressive audiovisual Text-to-Speech synthesis (EAVTTS) thanks to deep learning techniques. However, generating realistic speech is still an open issue and researchers in this area have been focusing lately on controlling the speech variability. In this paper, we use different neural architectures to synthesize emotional speech. We study the application of unsupervised learning techniques for emotional speech modeling as well as methods for restructuring emotions representation to make it continuous and more flexible. This manipulation of the emotional representation should allow us to generate new styles of speech by mixing emotions. We first present our expressive audiovisual corpus. We validate the emotional content of this corpus with three perceptual experiments using acoustic only, visual only and audiovisual stimuli. After that, we analyze the performance of a fully connected neural network in learning characteristics specific to different emotions for the phone duration aspect and the acoustic and visual modalities. We also study the contribution of a joint and separate training of the acoustic and visual modalities in the quality of the generated synthetic speech. In the second part of this paper, we use a conditional variational auto-encoder (CVAE) architecture to learn a latent representation of emotions. We applied this method in an unsupervised manner to generate features of expressive speech. We used a probabilistic metric to compute the overlapping degree between emotions latent clusters to choose the best parameters for the CVAE. By manipulating the latent vectors, we were able to generate nuances of a given emotion and to generate new emotions that do not exist in our database. For these new emotions, we obtain a coherent articulation. We conducted four perceptual experiments to evaluate our findings. (C) 2021 Elsevier Ltd. All rights reserved.

关键词： Expressive audiovisual speech synthesis conditional variational auto-encoder Expressive talking avatar Deep learning Bidirectional long short-term memory (BLSTM)

来源：评论

学校读者我要写书评

暂无评论

PAV-SOD: A New Task towards Panoramic Audiovisual Saliency Detection

引用

ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS 2023年第3期19卷 101-101页

作者： Zhang, Yi Chao, Fang-Yi Hamidouche, Wassim Deforges, Olivier Univ Rennes CNRS INSA Rennes IETRUMR 6164 F-6164 Rennes France Trin Coll Dublin Dublin Ireland

Object-level audiovisual saliency detection in 360 degrees panoramic real-life dynamic scenes is important for exploring and modeling human perception in immersive environments, also for aiding the development of virtual, augmented, and mixed reality applications in fields such as education, social network, entertainment, and training. To this end, we propose a new task, panoramic audiovisual salient object detection, (PAV-SOD1), which aims to segment the objects grasping most of the human attention in 360 degrees panoramic videos reflecting real-life daily scenes. To support the task, we collect PAVS10K, the first panoramic video dataset for audiovisual salient object detection, which consists of 67 4K-resolution equirectangular videos with per-video labels including hierarchical scene categories and associated attributes depicting specific challenges for conducting PAV-SOD, and 10,465 uniformly sampled video frames with manually annotated object-level and instance-level pixel-wise masks. The coarse-to-fine annotations enable multi-perspective analysis regarding PAV-SOD modeling. We further systematically benchmark 13 state-of-the-art salient object detection (SOD)/video object segmentation (VOS) methods based on our PAVS10K. Besides, we propose a new baseline network, which takes advantage of both visual and audio cues of 360 degrees video frames by using a new conditional variational auto-encoder (CVAE). Our CVAE-based audiovisual network, namely, CAV-Net, consists of a spatial-temporal visual segmentation network, a convolutional audio-encoding network, and audiovisual distribution estimation modules. As a result, our CAV-Net outperforms all competing models and is able to estimate the aleatoric uncertainties within PAVS10K. With extensive experimental results, we gain several findings about PAV-SOD challenges and insights towards PAV-SOD model interpretability. We hope that our work could serve as a starting point for advancing SOD towards immersive media.

关键词： Audiovisual saliency 360 degrees panorama segmentation conditional variational auto-encoder

来源：评论

学校读者我要写书评

暂无评论

Variation Control and Evaluation for Generative Slate Recommendations 21

Variation Control and Evaluation for Generative Slate Recomm...

引用

30th World Wide Web Conference (WWW)

作者： Liu, Shuchang Sun, Fei Ge, Yingqiang Pei, Changhua Zhang, Yongfeng Rutgers State Univ New Brunswick NJ 08854 USA Alibaba Grp Beijing Peoples R China

ISBN: (纸本)9781450383127

Slate recommendation generates a list of items as a whole instead of ranking each item individually, so as to better model the intra-list positional biases and item relations. In order to deal with the enormous combinatorial space of slates, recent work considers a generative solution so that a slate distribution can be directly modeled. However, we observe that such approaches-despite their proved effectiveness in computer vision-suffer from a trade-off dilemma in recommender systems: when focusing on reconstruction, they easily over-fit the data and hardly generate satisfactory recommendations;on the other hand, when focusing on satisfying the user interests, they get trapped in a few items and fail to cover the item variation in slates. In this paper, we propose to enhance the accuracy-based evaluation with slate variation metrics to estimate the stochastic behavior of generative models. We illustrate that instead of reaching to one of the two undesirable extreme cases in the dilemma, a valid generative solution resides in a narrow "elbow" region in between. And we show that item perturbation can enforce slate variation and mitigate the over-concentration of generated slates, which expand the "elbow" performance to an easy-to-find region. We further propose to separate a pivot selection phase from the generation process so that the model can apply perturbation before generation. Empirical results show that this simple modification can provide even better variance with the same level of accuracy compared to post-generation perturbation methods.

关键词： Generative Recommendation Slate Recommendation conditional variational auto-encoder

来源：评论

学校读者我要写书评

暂无评论

An online real-time estimation tool of leakage parameters for hazardous liquid pipelines

引用

INTERNATIONAL JOURNAL OF CRITICAL INFRASTRUCTURE PROTECTION 2020年 31卷 100389-100389页

作者： Zheng, Jianqin Dai, Yuanhao Liang, Yongtu Liao, Qi Zhang, Haoran China Univ Petr Natl Engn Lab Pipeline Safety MOE Key Lab Petr Engn Beijing Key Lab Urban Oil & Gas Distribut Technol Fuxue Rd 18 Beijing 102249 Peoples R China Univ Tokyo Ctr Spatial Informat Sci 5-1-5 Kashiwanoha Kashiwa Chiba 2778568 Japan

Hazardous liquid pipeline (HLP) leaks not only result in energy waste and environmental pollution, but also pose a threat to people's lives and property. The estimation of leakage parameters is an essential part of risk assessment and environment pollution assessment. However, current common leak detection methods are mainly based on physical models with assumptions and are susceptible to noise. Limited historical leakage data render it impossible to develop a leak model in advance. To address this problem, this study establishes a pipeline digital twin model that simulates a pipeline leak to generate leakage data. A conditional variational auto-encoder (CVAE) framework is proposed to estimate the leakage parameters based on data detected by upstream and downstream meters once the HLP leak occurs. CVAE can treat the high-dimensional detected data as labels to overcome the dimensionality problem. Based on the CVAE framework, an online real-time leakage parameter estimation tool for HLP is formed. To qualify the performance of the approach, a sensitivity analysis for the structure of the CVAE framework is evaluated. Finally, four examples demonstrate the effectiveness, stability, and applicability of the proposed method. (C) 2020 Elsevier B.V. All rights reserved.

关键词： Digital twin Hazardous liquid pipelines Leakage parameters conditional variational auto-encoder Sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

Stochastic bandit algorithms for demand side management

Stochastic bandit algorithms for demand side management

引用

作者： Brégère, Margaux Université Paris-Saclay

学位级别：博士

L'électricité se stockant difficilement à grande échelle, l'équilibre entre la production et la consommation doit être rigoureusement maintenu. Une gestion par anticipation de la demande se complexifie avec l'intégration au mix de production des énergies renouvelables intermittentes. Parallèlement, le déploiement des compteurs communicants permet d'envisager un pilotage dynamique de la consommation électrique. Plus concrètement, l'envoi de signaux - tels que des changements du prix de l'électricité – permettrait d'inciter les usagers à moduler leur consommation afin qu'elle s'ajuste au mieux à la production d'électricité. Les algorithmes choisissant ces signaux devront apprendre la réaction des consommateurs face aux envois tout en les optimisant (compromis exploration-exploitation). Notre approche, fondée sur la théorie des bandits, a permis de formaliser ce problème d'apprentissage séquentiel et de proposer un premier algorithme pour piloter la demande électrique d'une population homogène de consommateurs. Une borne supérieure d'ordre T⅔ a été obtenue sur le regret de cet algorithme. Des expériences réalisées sur des données de consommation de foyers soumis à des changements dynamiques du prix de l'électricité illustrent ce résultat théorique. Un jeu de données en « information complète » étant nécessaire pour tester un algorithme de bandits, un simulateur de données de consommation fondé sur les auto-encodeurs variationnels a ensuite été construit. Afin de s'affranchir de l'hypothèse d'homogénéité de la population, une approche pour segmenter les foyers en fonction de leurs habitudes de consommation est aussi proposée. Ces différents travaux sont finalement combinés pour proposer et tester des algorithmes de bandits pour un pilotage personnalisé de la consommation électrique. As electricity is hard to store, the balance between production and consumption must be strictly maintained. With the integration of intermittent renewable energies into the production mix,

关键词： Bandits stochastiques Apprentissage séquentiel Gestion de flexibilités électriques Prévision de la demande électrique auto-Encodeur variationnel conditionnel Segmentation Stochastic bandit Online learning Demand response Load forecasting conditional variational auto-encoder Clustering

来源：评论

学校读者我要写书评

暂无评论

A Novel and Efficient CVAE-GAN-Based Approach With Informative Manifold for Semi-Supervised Anomaly Detection

引用

IEEE ACCESS 2019年 7卷 88903-88916页

作者： Bian, Jiang Hui, Xiaolong Sun, Shiying Zhao, Xiaoguang Tan, Min Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Univ Chinese Acad Sci Beijing 100190 Peoples R China

Semi-supervised anomaly detection identifies abnormal (testing) observations which are different from normal (training) observations. In many practical situations, anomalies are poorly insufficient and not well defined, while the normal data are easily sampled, have a wide variety, and may not be classified. For this paradigm, we propose a novel end-to-end deep network as an anomaly detector only trained on normal samples. Our architecture consists of a conditional variational auto-encoder (CVAE), a feature discriminator (FD), and an adversarially trained WGAN-GP discriminator. The CVAE is designed as a generator to reconstruct images. It leverages underlying category information and multivariate Gaussian distributions to regularize the latent space, enabling a smooth and informative manifold. For anomalies which have a certain similarity to normal data, we perform active negative training by generating potential outliers from the latent space to limit network generative capability. In order to capture data characteristics, we maximize the mutual information between the inputs and the latent codes by the FD. It enhances the relationship between the high-dimensional image space and corresponding encoded vectors. To promote reconstruction, a structural similarity loss is applied to robustly recover local texture details and the WGAN-GP discriminator is employed to aid in generating photo-realistic images. We distinguish anomalies by computing a reconstruction-based anomaly score. Different from recent encoder-decoder or GAN-based architectures, our approach considers input categories, constructs, and exploits a useful manifold in an unsupervised manner and has a stronger reconstruction capability. The experimental results demonstrate that the proposed approach outperforms state-of-the-art methods over several benchmark datasets.

关键词： Semi-supervised anomaly detection conditional variational auto-encoder generative adversarial networks informative manifold structural similarity loss

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：