The absence of unknown timing information about the microphones recording start time and the sources emission time presents a challenge in several applications, including joint microphones and sources localization. Compared with traditional optimization methods that try to estimate unknown timing information directly, low rank property (LRP) contains an additional low rank structure that facilitates a linear constraint of unknown timing information for formulating corresponding low rank structure information, enabling the achievement of global optimal solutions of unknown timing information with suitable initialization. However, the initialization of unknown timing information is random, resulting in local minimal values for estimation of the unknown timing information. In this paper, we propose a combined low rank approximation method to alleviate the effect of random initialization on the estimation of unknown timing information. We define three new variants of LRP supported by proof that allows unknown timing information to benefit from more low rank structure information. Then, by utilizing the low rank structure information from both LRP and proposed variants of LRP, four linear constraints of unknown timing information are presented. Finally, we use the proposed combined low rank approximation algorithm to obtain global optimal solutions of unknown timing information through the four available linear constraints. Experimental results demonstrate superior performance of our method compared to state-of-the-art approaches in terms of recovery rate (the number of successful initialization for any configuration), convergency rate (the number of successfully recovered configurations), and estimation errors of unknown timing information.
相關內容
《計算機信息》雜志發表高質量的論文，擴大了運籌學和計算的范圍，尋求有關理論、方法、實驗、系統和應用方面的原創研究論文、新穎的調查和教程論文，以及描述新的和有用的軟件工具的論文。官網鏈接： ·
INFORMS
·
相似度
·
卷積
·
Extensibility
·
Partially spoofed audio detection is a challenging task, lying in the need to accurately locate the authenticity of audio at the frame level. To address this issue, we propose a fine-grained partially spoofed audio detection method, namely Temporal Deepfake Location (TDL), which can effectively capture information of both features and locations. Specifically, our approach involves two novel parts: embedding similarity module and temporal convolution operation. To enhance the identification between the real and fake features, the embedding similarity module is designed to generate an embedding space that can separate the real frames from fake frames. To effectively concentrate on the position information, temporal convolution operation is proposed to calculate the frame-specific similarities among neighboring frames, and dynamically select informative neighbors to convolution. Extensive experiments show that our method outperform baseline models in ASVspoof2019 Partial Spoof dataset and demonstrate superior performance even in the crossdataset scenario. The code is released online.
In this paper we consider the filtering of a class of partially observed piecewise deterministic Markov processes (PDMPs). In particular, we assume that an ordinary differential equation (ODE) drives the deterministic element and can only be solved numerically via a time discretization. We develop, based upon the approach in [20], a new particle and multilevel particle filter (MLPF) in order to approximate the filter associated to the discretized ODE. We provide a bound on the mean square error associated to the MLPF which provides guidance on setting the simulation parameter of that algorithm and implies that significant computational gains can be obtained versus using a particle filter. Our theoretical claims are confirmed in several numerical examples.
In backscatter communication (BC), a passive tag transmits information by just affecting an external electromagnetic field through load modulation. Thereby, the feed current of the excited tag antenna is modulated by adapting the passive termination load. This paper studies the achievable information rates with a freely adaptable passive load. As a prerequisite, we unify monostatic, bistatic, and ambient BC with circuit-based system modeling. We present the crucial insight that channel capacity is described by existing results on peak-power-limited quadrature Gaussian channels, because the steady-state tag current phasor lies on a disk. Consequently, we derive the channel capacity for the case of an unmodulated external field, for general passive, purely reactive, or purely resistive tag loads. We find that modulating both resistance and reactance is important for very high rates. We discuss the capacity-achieving load statistics, rate asymptotics, technical conclusions, and rate losses from value-range-constrained loads (which are found to be small for moderate constraints). We then demonstrate that near-capacity rates can be attained by more practical schemes: (i) amplitude-and-phase-shift keying on the reflection coefficient and (ii) simple load circuits of a few switched resistors and capacitors. Finally, we draw conclusions for the ambient BC channel capacity in important special cases.
This work develops a novel approach toward performance guarantees for all links in arbitrarily large wireless networks. It introduces a spatial network calculus, consisting of spatial regulation properties for stationary point processes and the first steps of a calculus for this regulation, which can be seen as an extension to space of the classical network calculus. Specifically, two classes of regulations are defined: one includes ball regulation and shot-noise regulation, which are shown to be equivalent and upper constraint interference; the other one includes void regulation, which lower constraints the signal power. These regulations are defined both in the strong and weak sense: the former requires the regulations to hold everywhere in space, whereas the latter only requires the regulations to hold as observed by a jointly stationary point process. Using this approach, we derive performance guarantees in device-to-device, ad hoc, and cellular networks under proper regulations. We give universal bounds on the SINR for all links, which gives link service guarantees based on information-theoretic achievability. They are combined with classical network calculus to provide end-to-end latency guarantees for all packets in wireless queuing networks. Such guarantees do not exist in networks that are not spatially regulated, e.g., Poisson networks.
Music source separation (MSS) aims to separate a music recording into multiple musically distinct stems, such as vocals, bass, drums, and more. Recently, deep learning approaches such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs) have been used, but the improvement is still limited. In this paper, we propose a novel frequency-domain approach based on a Band-Split RoPE Transformer (called BS-RoFormer). BS-RoFormer replies on a band-split module to project the input complex spectrogram into subband-level representations, and then arranges a stack of hierarchical Transformers to model the inner-band as well as inter-band sequences for multi-band mask estimation. To facilitate training the model for MSS, we propose to use the Rotary Position Embedding (RoPE). The BS-RoFormer system trained on MUSDB18HQ and 500 extra songs ranked the first place in the MSS track of Sound Demixing Challenge (SDX23). Benchmarking a smaller version of BS-RoFormer on MUSDB18HQ, we achieve state-of-the-art result without extra training data, with 9.80 dB of average SDR.
Robots must make and break contact to interact with the world and perform useful tasks. However, planning and control through contact remains a formidable challenge. In this work, we achieve real-time contact-implicit model predictive control with a surprisingly simple method: inverse dynamics trajectory optimization. While trajectory optimization with inverse dynamics is not new, we introduce a series of incremental innovations that collectively enable fast model predictive control on a variety of challenging manipulation and locomotion tasks. We implement these innovations in an open-source solver, and present a variety of simulation examples to support the effectiveness of the proposed approach. Additionally, we demonstrate contact-implicit model predictive control on hardware at over 100 Hz for a 20 degree-of-freedom bi-manual manipulation task.
We propose a novel end-to-end document understanding model called SeRum (SElective Region Understanding Model) for extracting meaningful information from document images, including document analysis, retrieval, and office automation. Unlike state-of-the-art approaches that rely on multi-stage technical schemes and are computationally expensive, SeRum converts document image understanding and recognition tasks into a local decoding process of the visual tokens of interest, using a content-aware token merge module. This mechanism enables the model to pay more attention to regions of interest generated by the query decoder, improving the model's effectiveness and speeding up the decoding speed of the generative scheme. We also designed several pre-training tasks to enhance the understanding and local awareness of the model. Experimental results demonstrate that SeRum achieves state-of-the-art performance on document understanding tasks and competitive results on text spotting tasks. SeRum represents a substantial advancement towards enabling efficient and effective end-to-end document understanding.
We present a method for zero-shot recommendation of multimodal non-stationary content that leverages recent advancements in the field of generative AI. We propose rendering inputs of different modalities as textual descriptions and to utilize pre-trained LLMs to obtain their numerical representations by computing semantic embeddings. Once unified representations of all content items are obtained, the recommendation can be performed by computing an appropriate similarity metric between them without any additional learning. We demonstrate our approach on a synthetic multimodal nudging environment, where the inputs consist of tabular, textual, and visual data.
Generative models are now capable of producing highly realistic images that look nearly indistinguishable from the data on which they are trained. This raises the question: if we have good enough generative models, do we still need datasets? We investigate this question in the setting of learning general-purpose visual representations from a black-box generative model rather than directly from data. Given an off-the-shelf image generator without any access to its training data, we train representations from the samples output by this generator. We compare several representation learning methods that can be applied to this setting, using the latent space of the generator to generate multiple "views" of the same semantic content. We show that for contrastive methods, this multiview data can naturally be used to identify positive pairs (nearby in latent space) and negative pairs (far apart in latent space). We find that the resulting representations rival those learned directly from real data, but that good performance requires care in the sampling strategy applied and the training method. Generative models can be viewed as a compressed and organized copy of a dataset, and we envision a future where more and more "model zoos" proliferate while datasets become increasingly unwieldy, missing, or private. This paper suggests several techniques for dealing with visual representation learning in such a future. Code is released on our project page: //ali-design.github.io/GenRep/
High spectral dimensionality and the shortage of annotations make hyperspectral image (HSI) classification a challenging problem. Recent studies suggest that convolutional neural networks can learn discriminative spatial features, which play a paramount role in HSI interpretation. However, most of these methods ignore the distinctive spectral-spatial characteristic of hyperspectral data. In addition, a large amount of unlabeled data remains an unexploited gold mine for efficient data use. Therefore, we proposed an integration of generative adversarial networks (GANs) and probabilistic graphical models for HSI classification. Specifically, we used a spectral-spatial generator and a discriminator to identify land cover categories of hyperspectral cubes. Moreover, to take advantage of a large amount of unlabeled data, we adopted a conditional random field to refine the preliminary classification results generated by GANs. Experimental results obtained using two commonly studied datasets demonstrate that the proposed framework achieved encouraging classification accuracy using a small number of data for training.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191