Search Results for author:
Found 253 papers, 70 papers with code
Multi-Task Dense Retrieval via Model Uncertainty Fusion for Open-Domain Question Answering
Our method reaches state-of-the-art performance on 5 benchmark QA datasets, with up to 10% improvement in top-100 accuracy compared to a joint-training multi-task DPR on SQuAD.
Unsupervised Chunking as Syntactic Structure Induction with a Knowledge-Transfer Approach
In this paper, we address unsupervised chunking as a new task of syntactic structure induction, which is helpful for understanding the linguistic structures of human languages as well as processing low-resource languages.
ConsistencyDet: A Robust Object Detector with a Denoising Paradigm of Consistency Model
In the present study, we introduce a novel framework designed to articulate object detection as a denoising diffusion process, which operates on the perturbed bounding boxes of annotated entities.
ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback
To this end, we propose ControlNet++, a novel approach that improves controllable generation by explicitly optimizing pixel-level cycle consistency between generated images and conditional controls.
MealRec$^+$: A Meal Recommendation Dataset with Meal-Course Affiliation for Personalization and Healthiness
Due to constraints related to user health privacy and meal scenario characteristics, the collection of data that includes both meal-course affiliation and two levels of interactions is impeded.
Scalable Model Editing via Customized Expert Networks
Our experiments on two different sizes of open-source large language models, the Llama2 7B and 13B, achieve state-of-the-art results compared to existing mainstream Model Editing methods.
CSST Strong Lensing Preparation: a Framework for Detecting Strong Lenses in the Multi-color Imaging Survey by the China Survey Space Telescope (CSST)
To overcome these challenges, we have developed a framework based on a hierarchical visual Transformer with a sliding window technique to search for strong lensing systems within entire images.
Voice EHR: Introducing Multimodal Audio Data for Health
This report introduces a consortium of partners for global work, presents the application used for data collection, and showcases the potential of informative voice EHR to advance the scalability and diversity of audio AI.
A Comparative Study of Artificial Potential Fields and Safety Filters
In this paper, we have demonstrated that the controllers designed by a classical motion planning tool, namely artificial potential fields (APFs), can be derived from a recently prevalent approach: control barrier function quadratic program (CBF-QP) safety filters.
KunquDB: An Attempt for Speaker Verification in the Chinese Opera Scenario
This work aims to promote Chinese opera research in both musical and speech domains, with a primary focus on overcoming the data limitations.
A Tunable Universal Formula for Safety-Critical Control
Finally, we demonstrate the efficacy of our method through a collision avoidance example, investigating the essential properties including safety, robustness, and smoothness under various tunable scaling terms.
Unifying Controller Design for Stabilizing Nonlinear Systems with Norm-Bounded Control Inputs
This paper revisits a classical challenge in the design of stabilizing controllers for nonlinear systems with a norm-bounded input constraint.
Pyramid Feature Attention Network for Monocular Depth Prediction
Deep convolutional neural networks (DCNNs) have achieved great success in monocular depth estimation (MDE).
Location-guided Head Pose Estimation for Fisheye Image
Camera with a fisheye or ultra-wide lens covers a wide field of view that cannot be modeled by the perspective projection.
A Survey on Knowledge Distillation of Large Language Models
In the era of Large Language Models (LLMs), Knowledge Distillation (KD) emerges as a pivotal methodology for transferring advanced capabilities from leading proprietary LLMs, such as GPT-4, to their open-source counterparts like LLaMA and Mistral.
Can LLMs Speak For Diverse People? Tuning LLMs via Debate to Generate Controllable Controversial Statements
To examine DEBATunE, we curate the largest dataset of debate topics so far, which covers 710 controversial topics and corresponding arguments for each topic.
Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning
Instruction tuning is critical to large language models (LLMs) for achieving better instruction following and task adaptation capabilities but its success heavily relies on the training data quality.
Deep Rib Fracture Instance Segmentation and Classification from CT on the RibFrac Challenge
The resulting FracNet+ demonstrates competitive performance in rib fracture detection, which lays a foundation for further research and development in AI-assisted rib fracture detection and diagnosis.
Zero-shot Explainable Mental Health Analysis on Social Media by Incorporating Mental Scales
Traditional discriminative approaches in mental health analysis are known for their strong capacity but lack interpretability and demand large-scale annotated data.
Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning
Data filtering for instruction tuning has proved important in improving both the efficiency and performance of the tuning process.
Leveraging Biases in Large Language Models: "bias-kNN'' for Effective Few-Shot Learning
Large Language Models (LLMs) have shown significant promise in various applications, including zero-shot and few-shot learning.
Multi-Input Multi-Output Target-Speaker Voice Activity Detection For Unified, Flexible, and Robust Audio-Visual Speaker Diarization
The proposed method can take audio-visual input and leverage the speaker's acoustic footprint or lip track to flexibly conduct audio-based, video-based, and audio-visual speaker diarization in a unified sequence-to-sequence framework.
End-to-End Learning for SLP-Based ISAC Systems
Integrated sensing and communication (ISAC) is an encouraging wireless technology which can simultaneously perform both radar and communication functionalities by sharing the same transmit waveform, spectral resource, and hardware platform.
A Practical Beamforming Design for Active RIS-assisted MU-MISO Systems
Motivated by this fact, in this paper we first investigate the amplification principle of typical active RIS and propose a more accurate amplification model based on amplifier hardware characteristics.
Self-supervised Reflective Learning through Self-distillation and Online Clustering for Speaker Representation Learning
Specifically, a teacher model continually refines pseudo labels through online clustering, providing dynamic supervision signals to train the student model.
IL-NeRF: Incremental Learning for Neural Radiance Fields with Camera Pose Alignment
This poses a paradox as the necessary camera pose must be estimated from the entire dataset, even though the data arrives sequentially and future chunks are inaccessible.
Safe Stabilization with Model Uncertainties: A Universal Formula with Gaussian Process Learning
In our previous research, we developed an analytical control strategy, namely the universal formula, that incorporates CLF and CBF conditions for safe stabilization.
ColonNeRF: High-Fidelity Neural Reconstruction of Long Colonoscopy
Specifically, to reconstruct the entire colon in a piecewise manner, our ColonNeRF introduces a region division and integration module, effectively reducing shape dissimilarity and ensuring geometric consistency in each segment.
LucidDreaming: Controllable Object-Centric 3D Generation
Nonetheless, achieving precise control over 3D generation continues to be an arduous task, as using text to control often leads to missing objects and imprecise locations.
Where to Begin? From Random to Foundation Model Instructed Initialization in Federated Learning for Medical Image Segmentation
In medical image analysis, Federated Learning (FL) stands out as a key technology that enables privacy-preserved, decentralized data processing, crucial for handling sensitive medical data.
Potential Societal Biases of ChatGPT in Higher Education: A Scoping Review
In this scoping review, we clarify the ways in which biases related to GAI in higher education settings have been discussed in recent academic publications and identify what type of potential biases are commonly reported in this body of literature.
Ethical implications of ChatGPT in higher education: A scoping review
This scoping review explores the ethical challenges of using ChatGPT in education, focusing particularly on issues related to higher education.
A Safer Vision-based Autonomous Planning System for Quadrotor UAVs with Dynamic Obstacle Trajectory Prediction and Its Application with LLMs
For intelligent quadcopter UAVs, a robust and reliable autonomous planning system is crucial.
Joint Sensing and Communication Optimization in Target-Mounted STARS-Assisted Vehicular Networks: A MADRL Approach
Extensive experimental results confirm the effectiveness of our proposed MADRL framework in improving both sensing and communication performance through the utilization of target-mounted STARS.
Instant3D: Instant Text-to-3D Generation
Once trained, Instant3D is able to create a 3D object for an unseen text prompt in less than one second with a single run of a feedforward network.
PRCA: Fitting Black-Box Large Language Models for Retrieval Question Answering via Pluggable Reward-Driven Contextual Adapter
The Retrieval Question Answering (ReQA) task employs the retrieval-augmented framework, composed of a retriever and generator.
Data-Free Distillation Improves Efficiency and Privacy in Federated Thorax Disease Analysis
Thorax disease analysis in large-scale, multi-centre, and multi-scanner settings is often limited by strict privacy policies.
Mitigating the missing-fragmentation problem in de novo peptide sequencing with a two-stage graph-based deep learning model
Here we reveal that in the process of peptide prediction, missing fragmentation results in the generation of incorrect amino acids within those regions and causes error accumulation thereafter.
Reflection-Tuning: Data Recycling Improves LLM Instruction-Tuning
Recent advancements in Large Language Models (LLMs) have expanded the horizons of natural language understanding and generation.
End-to-end Online Speaker Diarization with Target Speaker Tracking
During the inference process, we employ a front-end model to extract the frame-level speaker embeddings for each coming block of a signal.
ChatRadio-Valuer: A Chat Large Language Model for Generalizable Radiology Report Generation Based on Multi-institution and Multi-system Data
Radiology report generation, as a key step in medical image analysis, is critical to the quantitative analysis of clinically informed decision-making levels.
Multi-objective Progressive Clustering for Semi-supervised Domain Adaptation in Speaker Verification
Utilizing the pseudo-labeling algorithm with large-scale unlabeled data becomes crucial for semi-supervised domain adaptation in speaker verification tasks.
BiSinger: Bilingual Singing Voice Synthesis
We fuse monolingual singing datasets with open-source singing voice conversion techniques to generate bilingual singing voices while also exploring the potential use of bilingual speech data.
Haha-Pod: An Attempt for Laughter-based Non-Verbal Speaker Verification
It is widely acknowledged that discriminative representation for speaker verification can be extracted from verbal speech.
Semi-supervised News Discourse Profiling with Contrastive Learning
News Discourse Profiling seeks to scrutinize the event-related role of each sentence in a news article and has been proven useful across various downstream applications.
Cramer-Rao Bound Optimization for Active RIS-Empowered ISAC Systems
Integrated sensing and communication (ISAC), which simultaneously performs sensing and communication functions within a shared frequency band and hardware platform, has emerged as a promising technology for future wireless systems.
SdCT-GAN: Reconstructing CT from Biplanar X-Rays with Self-driven Generative Adversarial Networks
Computed Tomography (CT) is a medical imaging modality that can generate more informative 3D images than 2D X-rays.
RST-style Discourse Parsing Guided by Document-level Content Structures
Rhetorical Structure Theory based Discourse Parsing (RST-DP) explores how clauses, sentences, and large text spans compose a whole discourse and presents the rhetorical structure as a hierarchical tree.
DiffusionEngine: Diffusion Model is Scalable Data Engine for Object Detection
This paper reveals that the recently developed Diffusion Model is a scalable data engine for object detection.
Leveraging ASR Pretrained Conformers for Speaker Verification through Transfer Learning and Knowledge Distillation
This paper explores the use of ASR-pretrained Conformers for speaker verification, leveraging their strengths in modeling speech signals.
DLIP: Distilling Language-Image Pre-training
Furthermore, DLIP succeeds in retaining more than 95% of the performance with 22. 4% parameters and 24. 8% FLOPs compared to the teacher model and accelerates inference speed by 2. 7x.
From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning
In the realm of Large Language Models (LLMs), the balance between instruction data quality and quantity is a focal point.
The DKU-DUKEECE System for the Manipulation Region Location Task of ADD 2023
This paper introduces our system designed for Track 2, which focuses on locating manipulated regions, in the second Audio Deepfake Detection Challenge (ADD 2023).
The DKU-MSXF Speaker Verification System for the VoxCeleb Speaker Recognition Challenge 2023
For Track 1, we utilize a network structure based on ResNet for training.
The DKU-MSXF Diarization System for the VoxCeleb Speaker Recognition Challenge 2023
This paper describes the DKU-MSXF submission to track 4 of the VoxCeleb Speaker Recognition Challenge 2023 (VoxSRC-23).
Approximating Human-Like Few-shot Learning with GPT-based Compression
Leveraging the approximated information distance, our method allows the direct application of GPT models in quantitative text similarity measurements.
VoxBlink: A Large Scale Speaker Verification Dataset on Camera
In this paper, we introduce a large-scale and high-quality audio-visual speaker verification dataset, named VoxBlink.
A Novel Joint Angle-Range-Velocity Estimation Method for MIMO-OFDM ISAC Systems
Therefore, the proposed joint estimation algorithm can achieve larger processing gains and higher resolution by fully exploiting echo signals and jointly estimating the angle-range-velocity information.
Masked and Swapped Sequence Modeling for Next Novel Basket Recommendation in Grocery Shopping
In next basket recommendation (NBR), it is useful to distinguish between repeat items, i. e., items that a user has consumed before, and explore items, i. e., items that a user has not consumed before.
AlignDet: Aligning Pre-training and Fine-tuning in Object Detection
To this end, we propose AlignDet, a unified pre-training framework that can be adapted to various existing detectors to alleviate the discrepancies.
Robust Graph Structure Learning with the Alignment of Features and Adjacency Matrix
Overall, our research highlights the importance of integrating feature and graph information alignment in GSL, as inspired by our derived theoretical result, and showcases the superiority of our approach in handling noisy graph structures through comprehensive experiments on real-world datasets.
Thompson Sampling under Bernoulli Rewards with Local Differential Privacy
This paper investigates the problem of regret minimization for multi-armed bandit (MAB) problems with local differential privacy (LDP) guarantee.
First Place Solution to the CVPR'2023 AQTC Challenge: A Function-Interaction Centric Approach with Spatiotemporal Visual-Language Alignment
Affordance-Centric Question-driven Task Completion (AQTC) has been proposed to acquire knowledge from videos to furnish users with comprehensive and systematic instructions.
Permutation Equivariant Graph Framelets for Heterophilous Graph Learning
The nature of heterophilous graphs is significantly different from that of homophilous graphs, which causes difficulties in early graph neural network models and suggests aggregations beyond the 1-hop neighborhood.
A Feature Reuse Framework with Texture-adaptive Aggregation for Reference-based Super-Resolution
In this study, we propose a feature reuse framework that guides the step-by-step texture reconstruction process through different stages, reducing the negative impacts of perceptual and adversarial loss.
Low-Range-Sidelobe Waveform Design for MIMO-OFDM ISAC Systems
Integrated sensing and communication (ISAC) is a promising technology in future wireless systems owing to its efficient hardware and spectrum utilization.
AUC Optimization from Multiple Unlabeled Datasets
In this paper, we study the problem of building an AUC (area under ROC curve) optimization model from multiple unlabeled datasets, which maximizes the pairwise ranking ability of the classifier.
Weakly Supervised AUC Optimization: A Unified Partial AUC Approach
Since acquiring perfect supervision is usually difficult, real-world machine learning tasks often confront inaccurate, incomplete, or inexact supervision, collectively referred to as weak supervision.
Stability and Generalization of lp-Regularized Stochastic Learning for GCN
For a single-layer GCN, we establish an explicit theoretical understanding of GCN with the $\ell_p$-regularized stochastic learning by analyzing the stability of our SGD proximal algorithm.
Think Outside the Code: Brainstorming Boosts Large Language Models in Code Generation
We demonstrate that Brainstorm significantly enhances the ability of LLMs to solve competition-level programming problems, resulting in a more than 50% increase in the pass@$k$ metrics for ChatGPT on the CodeContests benchmark, achieving state-of-the-art performance.
A Unified Framework for Exploratory Learning-Aided Community Detection Under Topological Uncertainty
In social networks, the discovery of community structures has received considerable attention as a fundamental problem in various network analysis tasks.
FAN: Fatigue-Aware Network for Click-Through Rate Prediction in E-commerce Recommendation
Then the frequency spectrum is modulated by category information of the target item to model the bias that both the upper bound of fatigue and users' patience is different for different categories.
Moving Obstacle Collision Avoidance via Chance-Constrained MPC with CBF
Model predictive control (MPC) with control barrier functions (CBF) is a promising solution to address the moving obstacle collision avoidance (MOCA) problem.
FreeSeg: Unified, Universal and Open-Vocabulary Image Segmentation
Recently, open-vocabulary learning has emerged to accomplish segmentation for arbitrary categories of text-based descriptions, which popularizes the segmentation system to more general-purpose application scenarios.
Ranked #6 on
Open Vocabulary Panoptic Segmentation
on ADE20K
XVoxel-Based Parametric Design Optimization of Feature Models
As such, it can establish a direct mapping between design models and analysis models, which in turn enables automatic updates on simulation results for design modifications, and vice versa -- effectively a closed loop between CAD and CAE.
AERK: Aligned Entropic Reproducing Kernels through Continuous-time Quantum Walks
For pairwise graphs, the proposed AERK kernel is defined by computing a reproducing kernel based similarity between the quantum Shannon entropies of their each pair of aligned vertices.
RIS-Aided Integrated Sensing and Communication: Joint Beamforming and Reflection Design
Integrated sensing and communication (ISAC) has been envisioned as a promising technique to alleviate the spectrum congestion problem.
Joint Transceiver Beamforming and Reflecting Design for Active RIS-Aided ISAC Systems
Integrated sensing and communication (ISAC) is recognized as a promising technology with great potential in saving hardware and spectrum resources, since it simultaneously realizes radar detection and user communication functions in the fully-shared platform.
Language-Specific Representation of Emotion-Concept Knowledge Causally Supports Emotion Inference
Humans no doubt use language to communicate about their emotional experiences, but does language in turn help humans understand emotions, or is language just a vehicle of communication?
Self-supervised Geometric Features Discovery via Interpretable Attentio for Vehicle Re-Identification and Beyond (Complete Version)
To learn distinguishable patterns, most of recent works in vehicle re-identification (ReID) struggled to redevelop official benchmarks to provide various supervisions, which requires prohibitive human labors.
SNR/CRB-Constrained Joint Beamforming and Reflection Designs for RIS-ISAC Systems
Two optimization problems are formulated for maximizing the achievable sum-rate of the multi-user communications under an SNR constraint for target detection or a CRB constraint for parameter estimation, the transmit power budget, and the unit-modulus constraint of the RIS reflection coefficients.
STPrivacy: Spatio-Temporal Privacy-Preserving Action Recognition
For the first time, we introduce vision Transformers into PPAR by treating a video as a tubelet sequence, and accordingly design two complementary mechanisms, i. e., sparsification and anonymization, to remove privacy from a spatio-temporal perspective.
Deep Learning-Based UAV Aerial Triangulation without Image Control Points
The emerging drone aerial survey has the advantages of low cost, high efficiency, and flexible use.
A Theory of Human-Like Few-Shot Learning
We aim to bridge the gap between our common-sense few-sample human learning and large-data machine learning.
Class Balanced Adaptive Pseudo Labeling for Federated Semi-Supervised Learning
The second key element is that we design class balanced adaptive thresholds via considering the empirical distribution of all training data in local clients, to encourage a balanced training process.
Combining Photogrammetric Computer Vision and Semantic Segmentation for Fine-grained Understanding of Coral Reef Growth under Climate Change
Corals are the primary habitat-building life-form on reefs that support a quarter of the species in the ocean.
An operational framework to automatically evaluate the quality of weather observations from third-party stations
With increasing number of crowdsourced private automatic weather stations (called TPAWS) established to fill the gap of official network and obtain local weather information for various purposes, the data quality is a major concern in promoting their usage.
Joint Secure Transmit Beamforming Designs for Integrated Sensing and Communication Systems
Integrated sensing and communication (ISAC), which allows individual radar and communication systems to share the same spectrum bands, is an emerging and promising technique for alleviating spectrum congestion problems.
HAQJSK: Hierarchical-Aligned Quantum Jensen-Shannon Kernels for Graph Classification
In this work, we propose a family of novel quantum kernels, namely the Hierarchical Aligned Quantum Jensen-Shannon Kernels (HAQJSK), for un-attributed graphs.
Waveform Boundary Detection for Partially Spoofed Audio
The present paper proposes a waveform boundary detection system for audio spoofing attacks containing partially manipulated segments.
Target-Speaker Voice Activity Detection via Sequence-to-Sequence Prediction
Target-speaker voice activity detection is currently a promising approach for speaker diarization in complex acoustic environments.
Laugh Betrays You? Learning Robust Speaker Representation From Speech Containing Non-Verbal Fragments
We collect a set of clips with laughter components by conducting a laughter detection script on VoxCeleb and part of the CN-Celeb dataset.
End-to-End Learning for Symbol-Level Precoding and Detection with Adaptive Modulation
To overcome the performance bottleneck of these approaches, in this letter we propose an end-to-end learning based approach to jointly optimize the modulation orders, the transmit precoding and the receive detection for an SLP communication system.
Less is More: A Lightweight and Robust Neural Architecture for Discourse Parsing
Complex feature extractors are widely employed for text representation building.
RibSeg v2: A Large-scale Benchmark for Rib Labeling and Anatomical Centerline Extraction
Based on the RibSeg v2, we develop a pipeline including deep learning-based methods for rib labeling, and a skeletonization-based method for centerline extraction.
Deepfake Detection System for the ADD Challenge Track 3.2 Based on Score Fusion
The overfitting of the model to the training set leads to extreme values of the scores and low correlation of the score distributions, which makes score fusion difficult.
Joint Beamforming Designs for Active Reconfigurable Intelligent Surface: A Sub-Connected Array Architecture
Affected by the "double fading" effect, however, conventional passive RIS cannot bring considerable performance improvement when users are not close enough to RIS.
The DKU-DukeECE Diarization System for the VoxCeleb Speaker Recognition Challenge 2022
This paper discribes the DKU-DukeECE submission to the 4th track of the VoxCeleb Speaker Recognition Challenge 2022 (VoxSRC-22).
Data-driven and machine-learning based prediction of wave propagation behavior in dam-break flood
To show the performance of the RC-ESN model, we also provide a sensitivity analysis of the prediction accuracy concerning the key parameters including training set size, reservoir size, and spectral radius.
The 2022 Far-field Speaker Verification Challenge: Exploring domain mismatch and semi-supervised learning under the far-field scenario
In addition, a supplementary set for the FFSVC2020 dataset is released this year.
Optimization for Reflection and Transmission Dual-Functional Active RIS-Assisted Systems
Reconfigurable intelligent surface (RIS) has been deemed as one of potential components of future wireless communication systems because it can adaptively manipulate the wireless propagation environment with low-cost passive devices.
Multi-frequency PolSAR Image Fusion Classification Based on Semantic Interactive Information and Topological Structure
Finally, an adaptive weighting fusion (AWF) strategy is proposed to merge inference from different bands, so as to make the MF joint classification decisions of SIC and TPC.
Joint Beamforming Design for Intelligent Omni Surface Assisted Wireless Communication Systems
Intelligent reflecting surface (IRS) has been widely considered as one of the key enabling techniques for future wireless communication networks owing to its ability of dynamically controlling the phase shift of reflected electromagnetic (EM) waves to construct a favorable propagation environment.
Non-Cooperative Resource Management for Intelligent Reflecting Surface Aided Networks
Intelligent reflecting surface (IRS) has emerged as a promising and revolutionizing technology for future wireless networks.
Multi-Granularity Distillation Scheme Towards Lightweight Semi-Supervised Semantic Segmentation
Consequently, we offer the first attempt to provide lightweight SSSS models via a novel multi-granularity distillation (MGD) scheme, where multi-granularity is captured from three aspects: i) complementary teacher structure; ii) labeled-unlabeled data cooperative distillation; iii) hierarchical and multi-levels loss setting.
Knowledge Distillation
Semi-Supervised Semantic Segmentation
Reduced Implication-bias Logic Loss for Neuro-Symbolic Learning
Integrating logical reasoning and machine learning by approximating logical inference with differentiable operators is a widely used technique in Neuro-Symbolic systems.
User Association and Hybrid Beamforming Designs for Cooperative mmWave MIMO Systems
In an effort to further exploit multiple-antenna diversities, we also consider the dynamic subarray architecture and propose a novel antenna design algorithm for the analog beamforming design.
Partially Distributed Beamforming Design for RIS-Aided Cell-Free Networks
Cell-free networks are regarded as a promising technology to meet higher rate requirements for beyond fifth-generation (5G) communications.
Joint Beamforming Design for RIS-Assisted Integrated Sensing and Communication Systems
Integrated sensing and communication (ISAC) has been envisioned as a promising technology to tackle the spectrum congestion problem for future networks.
The DKU-OPPO System for the 2022 Spoofing-Aware Speaker Verification Challenge
For CM systems, we propose two methods on top of the challenge baseline to further improve the performance, namely Embedding Random Sampling Augmentation (ERSA) and One-Class Confusion Loss(OCCL).
Cross-Age Speaker Verification: Learning Age-Invariant Speaker Embeddings
In this paper, we mine cross-age test sets based on the VoxCeleb dataset and propose our age-invariant speaker representation(AISR) learning method.
Online Target Speaker Voice Activity Detection for Speaker Diarization
We iteratively extract the results for each block and update the target speaker embedding until reaching the end of the signal.
Discriminator-Guided Model-Based Offline Imitation Learning
In this paper, we propose the Discriminator-guided Model-based offline Imitation Learning (DMIL) framework, which introduces a discriminator to simultaneously distinguish the dynamics correctness and suboptimality of model rollout data against real expert demonstrations.
When to Trust Your Simulator: Dynamics-Aware Hybrid Offline-and-Online Reinforcement Learning
This brings up a new question: is it possible to combine learning from limited real data in offline RL and unrestricted exploration through imperfect simulators in online RL to address the drawbacks of both approaches?
Few-Shot Non-Parametric Learning with Deep Latent Variable Model
Most real-world problems that machine learning algorithms are expected to solve face the situation with 1) unknown data distribution; 2) little domain-specific knowledge; and 3) datasets with limited annotation.
Parallel Pre-trained Transformers (PPT) for Synthetic Data-based Instance Segmentation
Recently, Synthetic data-based Instance Segmentation has become an exceedingly favorable optimization paradigm since it leverages simulation rendering and physics to generate high-quality image-annotation pairs.
Identifying Source Speakers for Voice Conversion based Spoofing Attacks on Speaker Verification Systems
An automatic speaker verification system aims to verify the speaker identity of a speech signal.
Integrated Sensing and Communication with Reconfigurable Intelligent Surfaces: Opportunities, Applications, and Future Directions
Integrated sensing and communication (ISAC) is emerging as a key enabler to address the growing spectrum congestion problem and satisfy increasing demands for ubiquitous sensing and communication.
Simultaneous Speech Extraction for Multiple Target Speakers under the Meeting Scenarios
The common target speech separation directly estimate the target source, ignoring the interrelationship between different speakers at each frame.
Collaborative Knowledge Graph Fusion by Exploiting the Open Corpus
To alleviate the challenges of building Knowledge Graphs (KG) from scratch, a more general task is to enrich a KG using triples from an open corpus, where the obtained triples contain noisy entities and relations.
Embedding Graphs on Grassmann Manifold
Learning efficient graph representation is the key to favorably addressing downstream tasks on graphs, such as node or graph property prediction.
MealRec: A Meal Recommendation Dataset
A publicly available dataset specialising in meal recommendation research for the research community is in urgent demand.
IRS-assisted Multi-cell Multi-band Systems: Practical Reflection Model and Joint Beamforming Design
Intelligent reflecting surface (IRS) has been regarded as a promising and revolutionary technology for future wireless communication systems owing to its capability of tailoring signal propagation environment in an energy/spectrum/hardware-efficient manner.
Joint Beamforming and Reflection Design for RIS-assisted ISAC Systems
In this paper, we investigate the potential of employing reconfigurable intelligent surface (RIS) in integrated sensing and communication (ISAC) systems.
Fully-integrated multipurpose microwave frequency identification system on a single chip
We demonstrate a fully-integrated multipurpose microwave frequency identification system on silicon-on-insulator platform.
Graph Neural Networks for Graphs with Heterophily: A Survey
In the end, we point out the potential directions to advance and stimulate more future research and applications on heterophilic graph learning with GNNs.
Explainable COVID-19 Infections Identification and Delineation Using Calibrated Pseudo Labels
We demonstrate the effectiveness of our model with the combination of limited labelled data and sufficient unlabelled data or weakly-labelled data.
Cross-Channel Attention-Based Target Speaker Voice Activity Detection: Experimental Results for M2MeT Challenge
The multi-channel TS-VAD further reduces the DER by 28% and achieves a DER of 2. 26%.
Invertible Voice Conversion
In this paper, we propose an invertible deep learning framework called INVVC for voice conversion.
pvCNN: Privacy-Preserving and Verifiable Convolutional Neural Network Testing
First, a CNN model to be tested is strategically partitioned into a private part kept locally by the model developer, and a public part outsourced to an outside server.
CaFT: Clustering and Filter on Tokens of Transformer for Weakly Supervised Object Localization
Therefore, we propose Clustering and Filter of Tokens (CaFT) with Vision Transformer (ViT) backbone to solve this problem in another way.
MetaCVR: Conversion Rate Prediction via Meta Learning in Small-Scale Recommendation Scenarios
At last, we develop an Ensemble Prediction Network (EPN) which incorporates the output of FRN and DMN to make the final CVR prediction.
Joint Transmit Waveform and Passive Beamforming Design for RIS-Aided DFRC Systems
Reconfigurable intelligent surface (RIS) is a promising technology for 6G networks owing to its superior ability to enhance the capacity and coverage of wireless communications by smartly creating a favorable propagation environment.
Low-Latency Online Speaker Diarization with Graph-Based Label Generation
To ensure the low latency in the online setting, we introduce a variant of AHC, namely chkpt-AHC, to cluster the speakers.
Towards Graph Self-Supervised Learning with Contrastive Adjusted Zooming
To overcome the aforementioned problems, we introduce a novel self-supervised graph representation learning algorithm via Graph Contrastive Adjusted Zooming, namely G-Zoom, to learn node representations by leveraging the proposed adjusted zooming scheme.
SIG-VC: A Speaker Information Guided Zero-shot Voice Conversion System for Both Human Beings and Machines
Moreover, speaker information control is added to our system to maintain the voice cloning performance.
PRECAD: Privacy-Preserving and Robust Federated Learning via Crypto-Aided Differential Privacy
In this paper, we develop a framework called PRECAD, which simultaneously achieves differential privacy (DP) and enhances robustness against model poisoning attacks with the help of cryptography.
The Sigma-Max System Induced from Randomness and Fuzziness
This paper managed to induce probability theory (sigma system) and possibility theory (max system) respectively from randomness and fuzziness, through which the premature theory of possibility is expected to be well founded.
Automatic annotation of visual deep neural networks
Computer vision is widely used in the fields of driverless, face recognition and 3D reconstruction as a technology to help or replace human eye perception images or multidimensional data through computers.
A Time-Varying Endogenous Random Coefficient Model with an Application to Production Functions
This paper proposes a random coefficient panel model where the regressors are correlated with the time-varying random coefficients in each period, a critical feature in many economic applications.
A Next Basket Recommendation Reality Check
We propose a set of metrics that measure the repeat/explore ratio and performance of NBR models.
Two Birds, One Stone: Achieving both Differential Privacy and Certified Robustness for Pre-trained Classifiers via Input Perturbation
To solve this challenge, a reconstruction network is built before the public pre-trained classifiers to offer certified robustness and defend against adversarial examples through input perturbation.
The DKU-DukeECE System for the Self-Supervision Speaker Verification Task of the 2021 VoxCeleb Speaker Recognition Challenge
Taking advantage of DNN's ability to learn from data with label noise, we propose to cluster the speaker embedding obtained from the previous speaker network and use the subsequent class assignments as pseudo labels to train a new DNN.
The DKU-DukeECE-Lenovo System for the Diarization Task of the 2021 VoxCeleb Speaker Recognition Challenge
This report describes the submission of the DKU-DukeECE-Lenovo team to the VoxCeleb Speaker Recognition Challenge (VoxSRC) 2021 track 4.
Dual-Functional Radar-Communication Waveform Design: A Symbol-Level Precoding Approach
In this paper, we consider multi-input multi-output (MIMO) DFRC systems and focus on transmit beamforming designs to provide both radar sensing and multi-user communications.
Reflection and Relay Dual-Functional RIS Assisted MU-MISO Systems
Reconfigurable intelligent surfaces (RISs) have been deemed as one of potential components of future wireless communication systems because they can adaptively manipulate the wireless propagation environment with low-cost passive devices.
A Data-Driven Method for Recognizing Automated Negotiation Strategies
Our approach includes a data generation method for an agent to generate domain-independent sequences by negotiating with a variety of opponents across domains, a feature engineering method for representing negotiation data as time series with time-step features and overall features, and a hybrid (recurrent neural network-based) deep learning method for recognizing an opponent's strategy from the time series of bids.
BS-RIS-User Association and Beamforming Designs for RIS-aided Cellular Networks
During the dynamical access process, an iterative algorithm is proposed to alternatively obtain the active and passive beamforming.
A Feature Fusion-Net Using Deep Spatial Context Encoder and Nonstationary Joint Statistical Model for High Resolution SAR Image Classification
To address this problem, a novel end-to-end supervised classification method is proposed for HR SAR images by considering both spatial context and statistical features.
Building Bilingual and Code-Switched Voice Conversion with Limited Training Data Using Embedding Consistency Loss
We achieve cross-lingual VC between Mandarin speech with multiple speakers and English speech with multiple speakers by applying bilingual bottleneck features.
End-to-End Mandarin Tone Classification with Short Term Context Information
In this paper, we propose an end-to-end Mandarin tone classification method from continuous speech utterances utilizing both the spectrogram and the short-term context information as the input.
The DKU System Description for The Interspeech 2021 Auto-KWS Challenge
This paper introduces the system submitted by the DKU-SMIIP team for the Auto-KWS 2021 Challenge.
Binary Neural Network for Speaker Verification
Although deep neural networks are successful for many tasks in the speech domain, the high computational and memory costs of deep neural networks make it difficult to directly deploy highperformance Neural Network systems on low-resource embedded devices.
Computationally instrument-resolution-independent de novo peptide sequencing for high-resolution devices
De novo peptide sequencing is the key technology for finding novel peptides from mass spectra.
Grassmann Graph Embedding
Geometric deep learning that employs the geometric and topological features of data has attracted increasing attention in deep neural networks.
How Framelets Enhance Graph Neural Networks
The graph neural networks with the proposed framelet convolution and pooling achieve state-of-the-art performance in many node and graph prediction tasks.
First Saturation Correction in High Energy Proton-Nucleus Collisions: I. Time evolution of classical Yang-Mills fields beyond leading order
This paper is the first in a series of papers towards analytically completing the first saturation correction to physical observables in high energy proton-nucleus collisions.
High Energy Physics - Phenomenology Nuclear Theory
Intelligent reflecting surface assisted multi-cell multi-band wireless networks
Therefore, the practical phase shift model, which can describe the difference of IRS phase shift responses for the signals with different frequencies, should be utilized in the IRS optimization for wideband and multi-band systems.
Channel Estimation for Practical IRS-Assisted OFDM Systems
Different from the prior works which assume that IRS has an ideal reflection model, we perform channel estimation by considering amplitude-phase shift-frequency relationship for the response of practical IRS.
A Unified Deep Speaker Embedding Framework for Mixed-Bandwidth Speech Data
This paper proposes a unified deep speaker embedding framework for modeling speech data with different sampling rates.
Intelligent Reflecting Surface Aided MISO Uplink Communication Network: Feasibility and Power Minimization for Perfect and Imperfect CSI
In this paper, we consider the weighted sum-power minimization under quality-of-service (QoS) constraints in the multi-user multi-input-single-output (MISO) uplink wireless network assisted by intelligent reflecting surface (IRS).
Training Wake Word Detection with Synthesized Speech Data on Confusion Words
Confusing-words are commonly encountered in real-life keyword spotting applications, which causes severe degradation of performance due to complex spoken terms and various kinds of words that sound similar to the predefined keywords.
Self-supervised Geometric Features Discovery via Interpretable Attention for Vehicle Re-Identification and Beyond
To learn distinguishable patterns, most of recent works in vehicle re-identification (ReID) struggled to redevelop official benchmarks to provide various supervisions, which requires prohibitive human labors.
RNN Training along Locally Optimal Trajectories via Frank-Wolfe Algorithm
We propose to utilize the Frank-Wolfe (FW) algorithm in this context.
PointIso: Point Cloud Based Deep Learning Model for Detecting Arbitrary-Precision Peptide Features in LC-MS Map through Attention Based Segmentation
A promising technique of discovering disease biomarkers is to measure the relative protein abundance in multiple biofluid samples through liquid chromatography with tandem mass spectrometry (LC-MS/MS) based quantitative proteomics.
Temporal optical neurons for serial deep learning
This concept represents a novel one-dimensional realization of artificial neural networks, enabling an efficient application of optical deep learning methods to the analysis and processing of serial data signals, while offering a new overall perspective for the temporal signal processing.
LodoNet: A Deep Neural Network with 2D Keypoint Matchingfor 3D LiDAR Odometry Estimation
Deep learning based LiDAR odometry (LO) estimation attracts increasing research interests in the field of autonomous driving and robotics.
Don't Change Me! User-Controllable Selective Paraphrase Generation
The contribution of this work is a novel data generation technique using distant supervision that allows us to start with a pretrained sequence-to-sequence model and fine-tune a paraphrase generator that exhibits this behavior, allowing user-controllable paraphrase generation.
How Powerful are Shallow Neural Networks with Bandlimited Random Weights?
Despite the well-known fact that a neural network is a universal approximator, in this study, we mathematically show that when hidden parameters are distributed in a bounded domain, the network may not achieve zero approximation error.
Synergy between Machine/Deep Learning and Software Engineering: How Far Are We?
To improve the applicability and generalizability of research results, we analyzed what ingredients in a study would facilitate an understanding of why a ML/DL technique was selected for a specific SE problem.
Mask Detection and Breath Monitoring from Speech: on Data Augmentation, Feature Representation and Modeling
This paper introduces our approaches for the Mask and Breathing Sub-Challenge in the Interspeech COMPARE Challenge 2020.
Intelligent Reflecting Surface based Passive Information Transmission: A Symbol-Level Precoding Approach
Intelligent reflecting surfaces (IRS) have been proposed as a revolutionary technology owing to its capability of adaptively reconfiguring the propagation environment in a cost-effective and hardware-efficient fashion.
Intelligent reflecting surface enhanced wideband MIMO-OFDM communications: From practical model to reflection optimization
Simulation results demonstrate that the proposed algorithm can offer significant average sum-rate enhancement compared to that achieved using the ideal IRS reflection model, which confirms the importance of the use of the practical model for the design of wideband systems.
MathNet: Haar-Like Wavelet Multiresolution-Analysis for Graph Representation and Learning
In this paper, we propose a framework for graph neural networks with multiresolution Haar-like wavelets, or MathNet, with interrelated convolution and pooling strategies.
Prediction of the onset of cardiovascular diseases from electronic health records using multi-task gated recurrent units
The proposed approach is compared to a standard clinical risk predictor (QRISK) and machine learning alternatives using 5-year data from a NHS Foundation Trust.
Demo: iJam with Channel Randomization
Their secrecy rate (bit generation rate) depends heavily on the randomness of the channel, which may reduce significantly in a stable environment.
Intelligent Reflecting Surface Aided MISO Uplink Communication Network: Feasibility and Power Minimization for Perfect and Imperfect CSI
In this paper, we consider the weighted sum-power minimization under quality-of-service (QoS) constraints in the multi-user multi-input-single-output (MISO) uplink wireless network assisted by intelligent reflecting surface (IRS).
MSA-MIL: A deep residual multiple instance learning model based on multi-scale annotation for classification and visualization of glomerular spikes
Therefore, the proposed model can provide a good foundation for assisting the clinical doctors to diagnose the glomerular membranous nephropathy.
Path Integral Based Convolution and Pooling for Graph Neural Networks
Borrowing ideas from physics, we propose a path integral based graph neural networks (PAN) for classification and regression tasks on graphs.
TreeRNN: Topology-Preserving Deep GraphEmbedding and Learning
General graphs are difficult for learning due to their irregular structures.
Learning to Utilize Correlated Auxiliary Noise: A Possible Quantum Advantage
In effect, the network learns to use the correlated auxiliary noise as an approximate key to decipher its noisy input data.
Practical Modeling and Beamforming for Intelligent Reflecting Surface Aided Wideband Systems
In this letter, we aim to investigate the phase-amplitude-frequency relationship of the reflected signals and propose a practical model of reflection coefficient for an IRS-aided wideband system.
Acoustic Word Embedding System for Code-Switching Query-by-example Spoken Term Detection
In this paper, we propose a deep convolutional neural network-based acoustic word embedding system on code-switching query by example spoken term detection.
Cross-lingual Multispeaker Text-to-Speech under Limited-Data Scenario
In addition, we investigate the model's performance on the cross-lingual synthesis, with and without a bilingual dataset during training.
From Speaker Verification to Multispeaker Speech Synthesis, Deep Transfer with Feedback Constraint
The constraint is taken by an added loss related to the speaker identity, which is centralized to improve the speaker similarity between the synthesized speech and its natural reference audio.
Domain Aware Training for Far-field Small-footprint Keyword Spotting
In this paper, we focus on the task of small-footprint keyword spotting under the far-field scenario.
MV-RAN: Multiview recurrent aggregation network for echocardiographic sequences segmentation and full cardiac cycle analysis
In addition, for a better interpretation of pathophysiological processes, clinical decision-making and prognosis, such cardiac anatomy segmentation and quantitative analysis of various clinical indices should ideally be performed for the data covering the full cardiac cycle.
Segatron: Segment-Aware Transformer for Language Modeling and Understanding
To verify this, we propose a segment-aware Transformer (Segatron), by replacing the original token position encoding with a combined position encoding of paragraph, sentence, and token.
Ranked #20 on
Language Modelling
on WikiText-103
Resource-Optimized Fermionic Local-Hamiltonian Simulation on Quantum Computer for Quantum Chemistry
This framework, based on perturbation theory, is capable of improving the energy estimate at each cycle of the VQE progression, by about a factor of three closer to the known ground-state energy compared to the standard VQE approach in the test-bed, classically-accessible system of the water molecule.
Quantum Physics Emerging Technologies
Semantics of the Unwritten: The Effect of End of Paragraph and Sequence Tokens on Text Generation with GPT2
Experimental results show that the Chinese GPT2 can generate better essay endings with \eop.
DIHARD II is Still Hard: Experimental Results and Discussions from the DKU-LENOVO Team
Our diarization system includes multiple modules, namely voice activity detection (VAD), segmentation, speaker embedding extraction, similarity scoring, clustering, resegmentation and overlap detection.
Wireless Federated Learning with Local Differential Privacy
In this paper, we study the problem of federated learning (FL) over a wireless channel, modeled by a Gaussian multiple access channel (MAC), subject to local differential privacy (LDP) constraints.
Cryptography and Security Information Theory Information Theory
Diversity-Achieving Slow-DropBlock Network for Person Re-Identification
In particular, we show that the feature diversity can be well achieved with the use of multiple dropping branches by setting individual dropping ratio for each branch.
Learning Diverse Features with Part-Level Resolution for Person Re-Identification
Learning diverse features is key to the success of person re-identification.
Ranked #3 on
Person Re-Identification
on Market-1501-C
GhostImage: Remote Perception Attacks against Camera-based Image Classification Systems
In vision-based object classification systems imaging sensors perceive the environment and machine learning is then used to detect and classify objects for decision-making purposes; e. g., to maneuver an automated vehicle around an obstacle or to raise an alarm to indicate the presence of an intruder in surveillance settings.
Deep Time-Stream Framework for Click-Through Rate Prediction by Tracking Interest Evolution
Click-through rate (CTR) prediction is an essential task in industrial applications such as video recommendation.
Logical Differencing in Dyadic Network Formation Models with Nontransferable Utilities
This paper considers a semiparametric model of dyadic network formation under nontransferable utilities (NTU).
RWF-2000: An Open Large Scale Video Database for Violence Detection
In recent years, surveillance cameras are widely deployed in public places, and the general crime rate has been reduced significantly due to these ubiquitous devices.
Ranked #6 on
Activity Recognition
on RWF-2000
Variational Quantum Algorithms for Dimensionality Reduction and Classification
In this work, we present a quantum neighborhood preserving embedding and a quantum local discriminant embedding for dimensionality reduction and classification.
Parameter-Transferred Wasserstein Generative Adversarial Network (PT-WGAN) for Low-Dose PET Image Denoising
The contributions of this paper are twofold: i) a PT-WGAN framework is designed to denoise low-dose PET images without compromising structural details, and ii) a task-specific initialization based on transfer learning is developed to train PT-WGAN using trainable parameters transferred from a pretrained model, which significantly improves the training efficiency of PT-WGAN.
