检索结果-内蒙古大学图书馆

IEEE Conference on Multimedia Information processing and Retrieval (MIPR)

作者： Kratika Bhagtani Amit Kumar Singh Yadav Paolo Bestagini Edward J. Delp Video and Image Processing Lab (VIPER) School of Electrical and Computer Engineering Purdue University West Lafayette Indiana USA Dipartimento di Elettronica Informazione e Bioingegneria Politecnico Di Milano Milano Italy

ISBN: (数字)9798350351422

ISBN: (纸本)9798350351439

Deep learning methods can now generate high quality synthetic speech which is perceptually indistinguishable from real speech. As synthetic speech can be used for nefarious purposes, speech forensics methods to detect fully synthetic speech have been developed. Speech editing tools can also create partially synthetic speech in which only a part of the speech signal is synthetic. Detecting these short synthetic segments within a speech signal requires specialized methods to determine the tem-poral location of the synthetic speech. In this paper, we propose the Synthetic Speech Localization Convolutional Transformer (SSLCT), a neural network and transformer method for synthetic speech localization. SSLCT can temporally localize synthetic speech segments as small as 20 milliseconds. We demonstrate that SSLCT achieves less than 10% Equal Error Rate (EER), which is an improvement over several existing methods.

关键词： Location awareness Training Convolution Error analysis Synthesizers Forensics Neural networks Information processing Transformers Speech synthesis

来源：评论

学校读者我要写书评

暂无评论

DSVAE: Disentangled Representation Learning for Synthetic Speech Detection

DSVAE: Disentangled Representation Learning for Synthetic Sp...

引用

International Conference on Machine Learning and Applications (ICMLA)

作者： Amit Kumar Singh Yadav Kratika Bhagtani Ziyue Xiang Paolo Bestagini Stefano Tubaro Edward J. Delp Video and Image Processing Lab (VIPER) Purdue University West Lafayette Indiana USA Dipartimento di Elettronica Informazione e Bioingegneria Politecnico di Milano Milano Italy

Tools to generate high quality synthetic speech that is perceptually indistinguishable from speech recorded from hu-man speakers are easily available. Many incidents report misuse of synthetic speech for spreading misinformation and committing financial fraud. Several approaches have been proposed for detecting synthetic speech. Many of these approaches use deep learning methods without providing reasoning for the decisions they make. This limits the explainability of these approaches. In this paper, we use disentangled representation learning for developing a synthetic speech detector. We propose Disentangled Spectrogram Variational Auto Encoder (DSVAE) which is a two stage trained variational autoencoder that processes spectrograms of speech to generate features that disentangle synthetic and bona fide speech. We evaluated DSVAE using the ASVspoof2019 dataset. Our experimental results show high accuracy (> 98%) on detecting synthetic speech from 6 known and 10 unknown speech synthesizers. Further, the visualization of disentangled features obtained from DSVAE provides rea-soning behind the working principle of DSVAE, improving its explainability. DSVAE performs well compared to several existing methods. Additionally, DSVAE works in practical scenarios such as detecting synthetic speech uploaded on social platforms and against simple attacks such as removing silence regions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Simplified Skeleton Joints Based Approach For Human Action Recognition 7

A Simplified Skeleton Joints Based Approach For Human Action...

引用

7th IEEE International Conference on Signal and image processing Applications, ICSIPA 2021

作者： Malik, Najeeb Ur Rehman Abu Bakar, Syed A.R. Sheikh, Usman Ullah Computer Vision Video and Image Processing Research Lab School of Electrical Engineering Faculty of Engineering Universiti Teknologi Malaysia UTM Johor Bahru Campus Johor 81310 Malaysia

ISBN: (纸本)9781665435925

The growing technological development in the field of computer vision in general, and human action recognition (HAR), in particular, have attracted increasing number of researchers from various disciplines. Amid the variety of challenges in the field of human action recognition, one of the major issues is complex modelling which requires multiple parameters leading to troublesome training which further requires heavy configuration machines for real-time recognition. Therefore, there is a need to develop a simplified method that could result in reduced complexity, without compromising the performance accuracy. In order to address the mentioned issue, this paper proposes an approach that extracts the mean, variance and median from the skeleton joint locations and directly uses them in the classification process. The system used MCAD dataset for extracting 2D skeleton features with the help of OpenPose technique, which is suitable for the extraction of skeleton features from the 2D image instead of 3D image or using a depth sensor. Henceforth, we avoid using either the RGB images or the skeleton images in the recognition process. The method shows a promising performance with an accuracy of 73.8% when tested with MCAD dataset. © 2021 IEEE

关键词： image processing

来源：评论

学校读者我要写书评

暂无评论

Spacecraft Time-Series Online Anomaly Detection Using Deep Learning

Spacecraft Time-Series Online Anomaly Detection Using Deep L...

引用

IEEE Conference on Aerospace

作者： Sriram Baireddy Sundip R. Desai Richard H. Foster Moses W. Chan Mary L. Comer Edward J. Delp Video and Image Processing Lab (VIPER) School of Electrical and Computer Engineering Purdue University West Lafayette Indiana USA Advanced Technology Center Lockheed Martin Corporation Sunnyvale California USA

Anomaly detection in spacecraft telemetry channels is of great importance, especially considering the extremeness of the spacecraft operating environment. These anomalies often function as precursors for system failure. Currently, domain experts manually monitor telemetry channels, which is time-consuming and limited in scope. An automated approach to anomaly detection would be ideal, considering that each satellite system has thousands of channels to monitor. Deep learning models have been shown to be effective at capturing the normal behavior of the channels and flagging any abnormalities. However, each channel needs a unique model trained on it, and high performing models have been shown to require an increased training time. We instead propose training deep learning models in an online manner to quickly understand the behavior of a given channel and identify anomalies in real-time. This greatly reduces the amount of training time required to obtain a model for each channel. We present the results of our approach to show that we can achieve performance comparable to state-of-the-art spacecraft anomaly detection methods with minimal training time.

关键词： Training Space vehicles Deep learning Computational modeling Predictive models Real-time systems Behavioral sciences

来源：评论

学校读者我要写书评

暂无评论

Object Localization in the Presence of Noise

Object Localization in the Presence of Noise

引用

IEEE Conference on Aerospace

作者： Mridul Gupta Mary L. Comer Edward J. Delp Jonathan Chan Mitchell Krouss Paul Martens Moses W. Chan Video and Image Processing Lab (VIPER) School of Electrical and Computer Engineering Purdue University West Lafayette Indiana USA Advanced Technology Center Lockheed Martin Corporation Sunnyvale California USA

Detection and localization of small objects is crucial in many applications, such as surveillance, microscopy, and astronomy. In many space-based imaging applications, the spatial resolution of the imaging system is not enough to localize a small object (point source). Low signal-to-noise ratio (SNR) increases the difficulty such as when the objects are dim. We can model the noise in several ways and consider two cases in this paper. Noise is modeled as additive spatially invariant Gaussian distributed noise and spatially varying Poisson distributed noise. We assume that we have a coarse estimate for the spatial location of an object in an image and that a 2D symmetric Gaussian function approximates the point spread function of the imaging system and, thus, the gray-level distribution of an object. In this paper, we describe a machine learning method that minimizes a cost function derived from the maximum likelihood estimation of the observed image to determine an object's sub-pixel spatial location and amplitude. We call the proposed method Sub-Pixel Location Estimator for Small Objects (SPLEO). We compare the variance of SPLEO (both spatial location and object amplitude estimates) with the Cramer-Rao lower bound (CRLB).

关键词： Location awareness Training Maximum likelihood estimation Surveillance Microscopy Machine learning Cost function

来源：评论

学校读者我要写书评

暂无评论

Fast Low-parameter video Activity Localization in Collaborative Learning Environments

arXiv

引用

arXiv 2024年

作者： Jatla, Venkatesh Teeparthi, Sravani Egala, Ugesh Pattichis, Sylvia Celedón Pattichis, Marios S. Image and Video Processing and Communications Lab Dept. of Electrical and Computer Engineering University of New Mexico AlbuquerqueNM87131 United States Department of Curriculum and Instruction The University of Texas at Austin AustinTX78712-1293 United States

Research on video activity detection has primarily focused on identifying well-defined human activities in short video segments. The majority of the research on video activity recognition is focused on the development of large parameter systems that require training on large video datasets. This paper develops a low-parameter, modular system with rapid inferencing capabilities that can be trained entirely on limited datasets without requiring transfer learning from large-parameter systems. The system can accurately detect and associate specific activities with the students who perform the activities in real-life classroom videos. Additionally, the paper develops an interactive web-based application to visualize human activity maps over long real-life classroom videos. Long-term video activity detection in real-life classroom videos present unique challenges, such as the need to detect multiple simultaneous activities, rapid transitions between activities, long-term occlusions, durations exceeding 15 minutes, and numerous individuals performing similar activities in the background. Moreover, subtle hand movements further complicate the need to differentiate between actual typing and writing activities as opposed to unrelated hand movements. The system processes the input videos using fast activity initializations and current methods for object detection to determine the location and the the person performing the activities. These regions are then processed through an optimal low-parameter dyadic 3D-CNN classifier to identify the activity. The proposed system processes 1 hour of video in 15 minutes for typing and 50 minutes for writing activities. The system uses several methods to optimize the inference pipeline. For each activity, the system determines an optimal low-parameter 3D CNN architecture selected from a family of low-parameter architectures. The input video is broken into smaller video regions that are transcoded at an optimized frame rate. For inference, a

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Long-term Human Participation Assessment In Collaborative Learning Environments Using Dynamic Scene Analysis

arXiv

引用

arXiv 2024年

作者： Shi, Wenjing Tran, Phuong Celedón-Pattichis, Sylvia Pattichis, Marios S. Image and Video Processing and Communications Lab Dept. of Electrical and Computer Engineering University of New Mexico AlbuquerqueNM87131 United States Department of Curriculum and Instruction The University of Texas at Austin AustinTX78712-1293 United States

The paper develops datasets and methods to assess student participation in real-life collaborative learning environments. In collaborative learning environments, students are organized into small groups where they are free to interact within their group. Thus, students can move around freely causing issues with strong pose variation, move out and re-enter the camera scene, or face away from the camera. We formulate the problem of assessing student participation into two subproblems: (i) student group detection against strong background interference from other groups, and (ii) dynamic participant tracking within the group. A massive independent testing dataset of 12,518,250 student label instances, of total duration of 21 hours and 22 minutes of real-life videos, is used for evaluating the performance of our proposed method for student group detection. The proposed method of using multiple image representations is shown to perform equally or better than YOLO on all video instances. Over the entire dataset, the proposed method achieved an F1 score of 0.85 compared to 0.80 for YOLO. Following student group detection, the paper presents the development of a dynamic participant tracking system for assessing student group participation through long video sessions. The proposed dynamic participant tracking system is shown to perform exceptionally well, missing a student in just one out of 35 testing videos. In comparison, a state-of-the-art method fails to track students in 14 out of the 35 testing videos. The proposed method achieves 82.3% accuracy on an independent set of long, real-life collaborative videos. © 2024, CC BY.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

ASSD: Synthetic Speech Detection in the AAC Compressed Domain

ASSD: Synthetic Speech Detection in the AAC Compressed Domai...

引用

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

作者： Amit Kumar Singh Yadav Ziyue Xiang Emily R. Bartusiak Paolo Bestagini Stefano Tubaro Edward J. Delp Video and Image Processing Lab (VIPER) School of Electrical and Computer Engineering Purdue University West Lafayette Indiana USA Dipartimento di Elettronica Informazione e Bioingegneria Politecnico di Milano Milano Italy

Synthetic human speech signals have become very easy to generate given modern text-to-speech methods. When these signals are shared on social media they are often compressed using the Advanced Audio Coding (AAC) standard. Our goal is to study if a small set of coding metadata contained in the AAC compressed bit stream is sufficient to detect synthetic speech. This would avoid decompressing of the speech signals before analysis. We call our proposed method AAC Synthetic Speech Detection (ASSD). ASSD extracts information from the AAC compressed bit stream without decompressing the speech signal. ASSD analyzes the information using a transformer neural network. In our experiments, we compressed the ASVspoof2019 dataset according to the AAC standard using different data rates. We compared the performance of ASSD to a time domain based and a spectrogram based synthetic speech detection methods. We evaluated ASSD on approximately 71k compressed speech signals. The results show that our proposed method typically only requires 1000 bits per speech block/frame from the AAC compressed bit stream to detect synthetic speech. This is much lower than other reported methods. Our method also had a 9.7 percentage points higher detection accuracy compared to existing methods.

关键词： Social networking (online) Audio coding Neural networks Metadata Transformers Speech synthesis Data mining

来源：评论

学校读者我要写书评

暂无评论

FGSSAT : Unsupervised Fine-Grain Attribution of Unknown Speech Synthesizers Using Transformer Networks

FGSSAT : Unsupervised Fine-Grain Attribution of Unknown Spee...

引用

Asilomar Conference on Signals, Systems & Computers

作者： Kratika Bhagtani Amit Kumar Singh Yadav Ziyue Xiang Paolo Bestagini Edward J. Delp Video and Image Processing Lab (VIPER) School of Electrical and Computer Engineering Purdue University West Lafayette Indiana USA Dipartimento di Elettronica Informazione e Bioingegneria Politecnico di Milano Milano Italy

Synthetic speech generators can produce high quality speech. It can be difficult for humans to perceptually distinguish between synthesized speech and authentic human speech. Identifying the synthesizer used for generating synthetic speech, known as synthetic speech attribution, is an important problem. An open problem in synthetic speech attribution is attributing speech to new, unknown synthesizers, which are not present in the training set. Existing methods can identify known speech synthesizers but they cannot differentiate an unknown synthesizer from another unknown synthesizer. In this paper, we describe a system for attribution of unknown synthesizers i.e., assigning different labels to different unknown synthesizers. Our system is known as Fine-Grain Synthetic Speech Attribution Transformer (FGSSAT). FGSSAT is unsupervised and uses transformer, dimensionality reduction and clustering for attribution. Our experiments use the ASVspoof2019 dataset. We train on real speech and 6 synthesizers and evaluate on real speech and 17 synthesizers, which include 11 unknown synthesizers. FGSSAT identifies known synthesizers with 99.6% accuracy and classifies all speech generated from unknown synthesizers with 76.5% accuracy, which is an improvement on existing work.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MTN: Forensic Analysis of MP4 video Files Using Graph Neural Networks

MTN: Forensic Analysis of MP4 Video Files Using Graph Neural...

引用

IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Ziyue Xiang Amit Kumar Singh Yadav Paolo Bestagini Stefano Tubaro Edward J. Delp Video and Image Processing Lab (VIPER) School of Electrical and Computer Engineering Purdue University West Lafayette Indiana USA Dipartimento di Elettronica Informazione e Bioingegneria Politecnico di Milano Milano Italy

MP4 video files are stored using a tree data structure. These trees contain rich information that can be used for forensic analysis. In this paper, we propose MP4 Tree Network (MTN), an approach based on an end-to-end Graph Neural Networks (GNNs) that is used for forensic analysis of MP4 trees. MTN does not use any video pixel data. MTN is trained using Self-Supervised Learning (SSL), which generates semantic-preserving node embeddings for the nodes in an MP4 tree. We also propose a data augmentation technique for MP4 trees, which helps train MTN in data-scarce scenarios. MTN achieves good performance across 3 video forensics tasks on the EVA-7K dataset. We show that MTN can gain more comprehensive understanding about the MP4 trees and is more robust to potential attacks compared to existing methods.

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：