检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Niu, Li Tan, Linfeng Tao, Xinhao Cao, Junyan Guo, Fengjun Long, Teng Zhang, Liqing Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University China INTSIG

Given a composite image, image harmonization aims to adjust the foreground illumination to be consistent with background. Previous methods have explored transforming foreground features to achieve competitive performance. In this work, we show that using global information to guide foreground feature transformation could achieve significant improvement. Besides, we propose to transfer the foreground-background relation from real images to composite images, which can provide intermediate supervision for the transformed encoder features. Additionally, considering the drawbacks of existing harmonization datasets, we also contribute a ccHarmony dataset which simulates the natural illumination variation. Extensive experiments on iHarmony4 and our contributed dataset demonstrate the superiority of our method. Our ccHarmony dataset is released at https://***/bcmi/Image-Harmonization-Dataset-ccHarmony. Copyright © 2023, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Exploiting Persistent CPU Cache for Scalable Persistent Hash Index

Exploiting Persistent CPU Cache for Scalable Persistent Hash...

引用

International Conference on Data engineering

作者： Bowen Zhang Shengan Zheng Liangxu Nie Zhenlin Qi Linpeng Huang Hong Mei Department of Computer Science and Engineering Shanghai Jiao Tong University MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

Byte-addressable persistent memory (PM) has been widely studied in the past few years. Recently, the emerging eADR technology further incorporates CPU cache into the persistence domain. The persistent CPU cache is promising to optimize the write performance of PM-based storage systems and facilitate the design of concurrent crash-consistent data structures. In this paper, we propose Spash, a highly scalable persistent hash index for PM systems with persistent CPU cache. Spash fully exploits the benefits of persistent CPU cache to implement a durable linearizable index with low PM access overhead and high concurrency. Spash employs a fine-grained extendible hash architecture and a metadata-free segment design to minimize the number of PM accesses. Moreover, Spash adopts adaptive in-place updates and compacted-flush insertions, which dramatically conserve scarce PM write bandwidth by absorbing a large amount of PM write in the persistent CPU cache. Furthermore, Spash proposes a two-phase concurrency protocol and a collaborative staged doubling mechanism, which leverage the persistent CPU cache and hardware transactional memory to achieve lock-free concurrency and durable linearizability. Spash outperforms the other state-of-the-art persistent hash indexes in YCSB workloads by up to 19.6×.

关键词： Concurrent computing Protocols Collaboration Bandwidth Data structures Data engineering Hardware

来源：评论

学校读者我要写书评

暂无评论

DBAugur: An Adversarial-based Trend Forecasting System for Diversified Workloads

DBAugur: An Adversarial-based Trend Forecasting System for D...

引用

International Conference on Data engineering

作者： Yuanning Gao Xiuqi Huang Xuanhe Zhou Xiaofeng Gao Guoliang Li Guihai Chen Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University Shanghai China

Trend forecasting is vital to optimize the workload performance. It becomes even more urgent with an increasing number of applications and database configurations. However, DBAs mainly target at historical workloads and may give suboptimal configuration advice when the workload trends have changed. Although there are some studies on trend forecasting, they have several limitations. First, they mainly predict the changes of query numbers, which do not combine other critical factors (e.g., disk utilization) and cannot fully reflect the future workload trends. Besides, there are numerous queries in the workloads and exact clustering algorithms like K-means cannot effectively merge similar queries which contain noises like time shifts. Second, basic machine learning models like RNN may have relatively low prediction accuracy on complex workloads (e.g., no cycles but random bursts). Third, real-world workloads may have diverse patterns, while previous models cannot efficiently and reliably predict for all the different workload *** address these challenges, we propose a trend forecasting system (DBAugur) that utilizes adversarial neural networks to predict the trends of different workloads. First, DBAugur collects the important features (e.g., queries, resource metrics) to characterize workloads, and reduces the number of involved queries by separately merging similar queries based on the SQL semantics and trend patterns. Second, DBAugur utilizes Generative Adversarial Networks (GANs) to capture the latent patterns, correlations between different metrics, and occasional bursts within the complicated and time-varying workloads. Moreover, we further propose a time-sensitive ensemble algorithm that takes advantage of various machine learning models (e.g., generative models, convolutional models, feed-forward models) to accommodate the various workload patterns. The experimental results show that DBAugur outperformed state-of-the-art methods on various real-world wor

关键词：

来源：评论

学校读者我要写书评

暂无评论

Advancing Non-intrusive Suppression on Enhancement Distortion for Noise Robust ASR

Advancing Non-intrusive Suppression on Enhancement Distortio...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Wei Wang Siyi Zhao Yanmin Qian AI Institute Department of Computer Science and Engineering Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Recent advancements in speech enhancement (SE) techniques have greatly improved speech clarity and intelligibility in challenging acoustic environments. However, integrating SE into automatic speech recognition (ASR) systems often results in performance degradation due to artifacts introduced during the enhancement process. While various methods have enhanced recognition accuracy in SE-ASR systems, they often require fine-tuning or re-training of SE or ASR models, which is impractical in many real-world applications. In this paper, we propose a lightweight distortion suppression (DS) network that addresses these artifacts without modifying the SE or ASR models, treating them as fixed black boxes. The DS module operates on the time-frequency (T-F) bands of the original and enhanced complex spectrograms, efficiently compensating for SE distortions using the original T-F information. We validate our approach through experiments on both Mandarin and English ASR tasks using monaural and multi-channel SE frontends, across various ASR backends. Results show that the DS module significantly improves the performance of SE-ASR systems, even when used with robust commercial ASR backends.

关键词： Degradation Time-frequency analysis Acoustic distortion Closed box Speech enhancement Acoustics Noise robustness Noise measurement Spectrogram Automatic speech recognition

来源：评论

学校读者我要写书评

暂无评论

Advanced Zero-Shot Text-to-Speech for Background Removal and Preservation with Controllable Masked Speech Prediction

Advanced Zero-Shot Text-to-Speech for Background Removal and...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Leying Zhang Wangyou Zhang Zhengyang Chen Yanmin Qian AI Institute Department of Computer Science and Engineering Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

The acoustic background plays a crucial role in natural conversation. It provides context and helps listeners understand the environment, but a strong background makes it difficult for listeners to understand spoken words. The appropriate handling of these backgrounds is situation-dependent: Although it may be necessary to remove background to ensure speech clarity, preserving the background is sometimes crucial to maintaining the contextual integrity of the speech. Despite recent advancements in zero-shot Text-to-Speech technologies, current systems often struggle with speech prompts containing backgrounds. To address these challenges, we propose a Controllable Masked Speech Prediction strategy coupled with a dual-speaker encoder, utilizing a task-related control signal to guide the prediction of dual background removal and preservation targets. Experimental results demonstrate that our approach enables precise control over the removal or preservation of background across various acoustic conditions and exhibits strong generalization capabilities in unseen scenarios.

关键词： Oral communication Predictive models Signal processing Acoustics Text to speech Speech processing

来源：评论

学校读者我要写书评

暂无评论

SparseFormer: Detecting Objects in HRW Shots via Sparse Vision Transformer 24

SparseFormer: Detecting Objects in HRW Shots via Sparse Visi...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Li, Wenxi Guo, Yuchen Zheng, Jilai Lin, Haozhe Ma, Chao Fang, Lu Yang, Xiaokang MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai China Beijing National Research Center for Information Science and Technology Tsinghua University Beijing China Department of Electronic Engineering BNRist Tsinghua University Beijing China

ISBN: (纸本)9798400706868

Recent years have seen an increase in the use of gigapixel-level image and video capture systems and benchmarks with high-resolution wide (HRW) shots. However, unlike close-up shots in the MS COCO dataset, the higher resolution and wider field of view raise unique challenges, such as extreme sparsity and huge scale changes, causing existing close-up detectors inaccuracy and inefficiency. In this paper, we present a novel model-agnostic sparse vision transformer, dubbed SparseFormer, to bridge the gap of object detection between close-up and HRW shots. The proposed SparseFormer selectively uses attentive tokens to scrutinize the sparsely distributed windows that may contain objects. In this way, it can jointly explore global and local attention by fusing coarse- and fine-grained features to handle huge scale changes. SparseFormer also benefits from a novel Cross-slice non-maximum suppression (C-NMS) algorithm to precisely localize objects from noisy windows and a simple yet effective multi-scale strategy to improve accuracy. Extensive experiments on two HRW benchmarks, PANDA and DOTA-v1.0, demonstrate that the proposed SparseFormer significantly improves detection accuracy (up to 5.8%) and speed (up to 3x) over the state-of-the-art approaches. © 2024 ACM.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

STATIC IMAGE ACTION RECOGNITION WITH HALLUCINATED FINE-GRAINED MOTION INFORMATION

STATIC IMAGE ACTION RECOGNITION WITH HALLUCINATED FINE-GRAIN...

引用

2021 IEEE International Conference on Multimedia and Expo, ICME 2021

作者： Huang, Shengyuan Zhao, Xing Niu, Li Zhang, Liqing MoE Key Lab of Artificial Intelligence Department of Computer Science and Engineering Shanghai Jiaotong University Shanghai China

ISBN: (纸本)9781665438643

Static image action recognition is a challenging task due to the lack of motion information in a static image. Some previous works have attempted to hallucinate the motion information in a static image using a generator learnt from freely available unlabeled videos. However, their hallucinated motion information is either low-level or coarse-grained, which may contain lots of noise or lose motion details. In contrast, we propose to hallucinate fine-grained high-level motion information, which is more robust and detail-preserving. Specifically, we hallucinate motion feature map which encodes the motion details of human body parts. We also hallucinate motion attention map to focus on motion-related regions. Our hallucinated motion information can greatly facilitate static image action recognition, which is confirmed by the experiments on two static action image datasets and two video datasets. © 2021 IEEE

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Knowledge Distillation from Discriminative Model to Generative Model with Parallel Architecture for Speech Enhancement

Knowledge Distillation from Discriminative Model to Generati...

引用

International Symposium on Chinese Spoken Language Processing

作者： Tingxiao Zhou Leying Zhang Yanmin Qian Department of Computer Science and Engineering Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence Al Institute Shanghai Jiao Tong University Shanghai

ISBN: (数字)9798331516826

ISBN: (纸本)9798331516833

Generative speech enhancement methods, especially diffusion methods, have recently gained attention. However, current generative methods face several unresolved issues, such as lagging performance compared to discriminative methods on conventional enhancement metrics and slower inference speeds. In order to address these challenges, we propose a knowledge distillation approach from discriminative to generative models, and we design a parallel architecture with a latent vector fusion module to leverage their respective strengths. We conduct experiments and ablation studies on the LibriMix dataset to validate its effectiveness. The results demonstrate that our approach substantially improves performance over baseline systems in terms of speech quality and inference speed.

关键词： Measurement Speech enhancement Vectors Parallel architectures Faces

来源：评论

学校读者我要写书评

暂无评论

Insights from Hyperparameter Scaling of Online Speech Separation

Insights from Hyperparameter Scaling of Online Speech Separa...

引用

International Symposium on Chinese Spoken Language Processing

作者： Xin Zhou Wangyou Zhang Chenda Li Yanmin Qian Department of Computer Science and Engineering Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai

ISBN: (数字)9798331516826

ISBN: (纸本)9798331516833

With the rapid development of deep learning, a large number of models with excellent performance for speech separation tasks have emerged in the literature. Despite their impressive performance, these models usually cannot be used for online speech separation tasks due to high computational and memory costs. In recent years, some approaches tailored for online speech separation have been developed to achieve state-of-the-art performance while keeping the model lightweight. However, it is often unclear how these models can scale with their architecture-specific hyperparameters as they are under-explored in the literature. To fill this gap, this paper investigates the effect of hyper-parameter scaling on the model performance, number of parameters, and computational cost based on two representative online speech separation models, BSRNN and SkiM. Experimental results on the Libri2Mix dataset reveal the relationship between model performance and composite hyperparameter configurations. We also derive the patterns of the number of parameters and computational costs varying with hyperparameters. Based on the results of the analysis, we give suggestions for scaling the two models and summarize two common trends.

关键词： Degradation Deep learning Analytical models Costs Computational modeling Market research Computational efficiency Speech processing Guidelines

来源：评论

学校读者我要写书评

暂无评论

label-Aware Auxiliary Learning for Dialogue State Tracking

Label-Aware Auxiliary Learning for Dialogue State Tracking

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Yuncong Liu Lu Chen Kai Yu Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence X-LANCE Lab SJTU AI Institute Shanghai Jiao Tong University Shanghai China

Dialogue State Tracking (DST) is an essential part of task-oriented dialogue systems. Many existing methods try to utilize external dialogue datasets to improve the performance of DST models. Instead of previous methods, in this paper, we propose label-Aware Auxiliary Learning for DST (LAL-DST) which focuses on exploiting the abundant internal information of the target DST dataset to improve the performance. We design label-aware auxiliary tasks, in which we apply noising functions to either the dialogue history or the belief state label and take the concatenation of them as input. The goal of each task is to restore the corrupted context. During the training process, we first further train the large pre-trained language model on the auxiliary tasks, then fine-tune it on DST. Through the experimental results, we empirically show the effect of LAL-DST by the performance improvements it brings to MultiWOZ2.0 and WOZ.

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：