Search Results for author:
Found 81 papers, 34 papers with code
Video-based Sign Language Recognition without Temporal Segmentation
Worse still, isolated SLR methods typically require strenuous labeling of each word separately in a sentence, severely limiting the amount of attainable training data.
PIRM Challenge on Perceptual Image Enhancement on Smartphones: Report
This paper reviews the first challenge on efficient perceptual image enhancement with the focus on deploying deep learning models on smartphones.
Hyper-Path-Based Representation Learning for Hyper-Networks
Then a carefully designed algorithm, Hyper-gram, utilizes these random walks to capture both pairwise relationships and tuplewise relationships in the whole hyper-networks.
A Big Data Enabled Channel Model for 5G Wireless Communication Systems
This paper investigates various applications of big data analytics, especially machine learning algorithms in wireless communications and channel modeling.
Multi-Frequency Multi-Scenario Millimeter Wave MIMO Channel Measurements and Modeling for B5G Wireless Communication Systems
Millimeter wave (mmWave) bands have been utilized for the fifth generation (5G) communication systems and will no doubt continue to be deployed for beyond 5G (B5G).
6G Oriented Wireless Communication Channel Characteristics Analysis and Modeling
Based on the vision on the 6G wireless communication network, i. e., global coverage, all spectrums and all applications, we comprehensively survey 6G related wireless channel measurements, channel characteristics, and channel models for all frequency bands and all scenarios.
A 3D Non-Stationary Channel Model for 6G Wireless Systems Employing Intelligent Reflecting Surface
The evolution of clusters on the linear array and planar array is also considered in the proposed model.
GAN-Based Interactive Reinforcement Learning from Demonstration and Human Evaluative Feedback
Deep reinforcement learning (DRL) has achieved great successes in many simulated tasks.
A General 3D Space-Time-Frequency Non-Stationary THz Channel Model for 6G Ultra-Massive MIMO Wireless Communication Systems
The proposed THz channel model is very general having the capability to capture different channel characteristics in multiple THz application scenarios such as indoor scenarios, device-to-device (D2D) communications, ultra-massive multiple-input multiple-output (MIMO) communications, and long traveling paths of users.
A Multi-Size Neural Network with Attention Mechanism for Answer Selection
The experimental results show that (1) multi-size neural network (MSNN) is a more useful method to capture abstract features on different levels of granularities than single/multi-layer CNNs; (2) the attention mechanism (AM) is a better strategy to derive more informative representations; (3) AM-MSNN is a better architecture for the answer selection task for the moment.
A 3D Non-Stationary Channel Model for 6G Wireless Systems Employing Intelligent Reflecting Surfaces with Practical Phase Shifts
In this paper, a three-dimensional (3D) geometry based stochastic model (GBSM) for a massive multiple-input multiple-output (MIMO) communication system employing practical discrete intelligent reflecting surface (IRS) is proposed.
EDPN: Enhanced Deep Pyramid Network for Blurry Image Restoration
Image deblurring has seen a great improvement with the development of deep neural networks.
Measuring Fine-Grained Domain Relevance of Terms: A Hierarchical Core-Fringe Approach
To support a fine-grained domain without relying on a matching corpus for supervision, we develop hierarchical core-fringe learning, which learns core and fringe terms jointly in a semi-supervised manner contextualized in the hierarchy of the domain.
Space-Time Distillation for Video Super-Resolution
In this paper, we aim to improve the performance of compact VSR networks without changing their original architectures, through a knowledge distillation approach that transfers knowledge from a complicated VSR network to a compact one.
Three-dimensional instantaneous orbit map for rotor-bearing system based on a novel multivariate complex variational mode decomposition algorithm
It can simultaneously extract the forward and backward components of multiple bearing sections and realize non-stationary complex signal decomposition of multiple bearing sections of the rotor.
A Novel 3D Non-Stationary GBSM for 6G THz Ultra-Massive MIMO Wireless Systems
Terahertz (THz) communication is now being considered as one of possible technologies for the sixth generation (6G) wireless communication systems.
Multi-Frequency Wireless Channel Measurements and Characteristics Analysis in Indoor Corridor Scenarios
In this paper, we conduct wireless channel measurements in indoor corridor scenarios at 2. 4, 5 and 6 GHz bands with bandwidth of 320 MHz.
Open Relation Modeling: Learning to Define Relations between Entities
Relations between entities can be represented by different instances, e. g., a sentence containing both entities or a fact in a Knowledge Graph (KG).
Understanding Jargon: Combining Extraction and Generation for Definition Modeling
From the composition of this phrase, machines may guess twin prime is a certain kind of prime, but it is still difficult to deduce exactly what twin stands for without additional knowledge.
Exposure Normalization and Compensation for Multiple-Exposure Correction
However, the procedures of correcting underexposure and overexposure to normal exposures are much different from each other, leading to large discrepancies for the network in correcting multiple exposures, thus resulting in poor performance.
Bijective Mapping Network for Shadow Removal
Shadow removal, which aims to restore the background in the shadow regions, is challenging due to the highly ill-posed nature.
Mutual Information-Driven Pan-Sharpening
Despite the remarkable progress, existing state-of-the-art Pan-sharpening methods don't explicitly enforce the complementary information learning between two modalities of PAN and MS images.
CD-GAN: a robust fusion-based generative adversarial network for unsupervised remote sensing change detection with heterogeneous sensors
In the context of Earth observation, change detection boils down to comparing images acquired at different times by sensors of possibly different spatial and/or spectral resolutions or different modalities (e. g., optical or radar).
Domain Representative Keywords Selection: A Probabilistic Approach
We propose a probabilistic approach to select a subset of a \textit{target domain representative keywords} from a candidate set, contrasting with a context domain.
A Novel 3D Non-Stationary Channel Model for 6G Indoor Visible Light Communication Systems
The visible light communication (VLC) technology has attracted much attention in the research of the sixth generation (6G) communication systems.
An unsupervised approach for semantic place annotation of trajectories based on the prior probability
The Bayesian Criterion is specifically employed to decompose the spatiotemporal probability of the candidate place into spatial probability, duration probability, and visiting time probability.
DEER: Descriptive Knowledge Graph for Explaining Entity Relationships
Experiments demonstrate that our system can extract and generate high-quality relation descriptions for explaining entity relationships.
Are Large Pre-Trained Language Models Leaking Your Personal Information?
Are Large Pre-Trained Language Models Leaking Your Personal Information?
Reconfigurable intelligent surfaces: Channel characterization and modeling
Reconfigurable intelligent surfaces (RISs) are two dimensional (2D) metasurfaces which can intelligently manipulate electromagnetic waves by low-cost near passive reflecting elements.
Source-Free Domain Adaptation for Real-world Image Dehazing
Although certain Domain Adaptation (DA) dehazing methods have been presented, they inevitably require access to the source dataset to reduce the gap between the source synthetic and target real domains.
Enhancement by Your Aesthetic: An Intelligible Unsupervised Personalized Enhancer for Low-Light Images
Low-light image enhancement is an inherently subjective process whose targets vary with the user's aesthetic.
An SBR Based Ray Tracing Channel Modeling Method for THz and Massive MIMO Communications
Terahertz (THz) communication and the application of massive multiple-input multiple-output (MIMO) technology have been proved significant for the sixth generation (6G) communication systems, and have gained global interests.
An Improved Equiangular Division Algorithm for SBR based Ray Tracing Channel Modeling
With the proposed iterative precise algorithm, error of angle of departure (AOD) and angle of arrival (AOA) is below 0. 01 degree.
An Improved Ray Tracing Acceleration Algorithm Based on Bounding Volume Hierarchies
Ray tracing is an efficient channel modeling method.
A Weighted Random Forest Based PositioningAlgorithm for 6G Indoor Communications
Due to the indoor none-line-of-sight (NLoS) propagation and multi-access interference (MAI), it is a great challenge to achieve centimeter-level positioning accuracy in indoor scenarios.
CNSNet: A Cleanness-Navigated-Shadow Network for Shadow Removal
The key to shadow removal is recovering the contents of the shadow regions with the guidance of the non-shadow regions.
Deep Fourier Up-Sampling
Existing convolutional neural networks widely adopt spatial down-/up-sampling for multi-scale modeling.
Can Language Models Be Specific? How?
We hope this work can bring to awareness the notion of specificity of language models and encourage the research community to further explore this important but understudied problem.
Panchromatic and Multispectral Image Fusion via Alternating Reverse Filtering Network
Panchromatic (PAN) and multi-spectral (MS) image fusion, named Pan-sharpening, refers to super-resolve the low-resolution (LR) multi-spectral (MS) images in the spatial domain to generate the expected high-resolution (HR) MS images, conditioning on the corresponding high-resolution PAN images.
Coordinated Topic Modeling
It then uses the axes to model a corpus for easily understandable representation.
MetaASSIST: Robust Dialogue State Tracking with Meta Learning
Experimental results demonstrate that all three schemes can achieve competitive performance.
VER: Unifying Verbalizing Entities and Relations
To know the relationship between two entities, humans tend to create a sentence to connect them.
DimonGen: Diversified Generative Commonsense Reasoning for Explaining Concept Relationships
MoREE consists of a mixture of retrievers model that retrieves diverse context sentences related to the given concepts, and a mixture of generators model that generates diverse sentences based on the retrieved contexts.
Towards Reasoning in Large Language Models: A Survey
Reasoning is a fundamental aspect of human intelligence that plays a crucial role in activities such as problem solving, decision making, and critical thinking.
Ingredient-Oriented Multi-Degradation Learning for Image Restoration
Learning to leverage the relationship among diverse image restoration tasks is quite beneficial for unraveling the intrinsic ingredients behind the degradation.
Learning Sample Relationship for Exposure Correction
Exposure correction task aims to correct the underexposure and its adverse overexposure images to the normal exposure in a single network.
Visual Recognition-Driven Image Restoration for Multiple Degradation With Intrinsic Semantics Recovery
Deep image recognition models suffer a significant performance drop when applied to low-quality images since they are trained on high-quality images.
Exploring Temporal Frequency Spectrum in Deep Video Deblurring
Video deblurring aims to restore the latent video frames from their blurred counterparts.
Unlocking Masked Autoencoders as Loss Function for Image and Video Restoration
We investigate the efficacy of our belief from three perspectives: 1) from task-customized MAE to native MAE, 2) from image task to video task, and 3) from transformer structure to convolution neural network structure.
Random Weights Networks Work as Loss Prior Constraint for Image Restoration
In this paper, orthogonal to the existing data and model studies, we instead resort our efforts to investigate the potential of loss function in a new perspective and present our belief ``Random Weights Networks can Be Acted as Loss Prior Constraint for Image Restoration''.
Region-Aware Portrait Retouching with Sparse Interactive Guidance
Specifically, we propose a region-aware retouching framework with two branches: an automatic branch and an interactive branch.
Multi-step Jailbreaking Privacy Attacks on ChatGPT
With the rapid progress of large language models (LLMs), many downstream NLP tasks can be well solved given appropriate prompts.
Why Does ChatGPT Fall Short in Providing Truthful Answers?
To better understand the model's particular weaknesses in providing truthful answers, we embark an in-depth exploration of open-domain question answering.
Expository Text Generation: Imitate, Retrieve, Paraphrase
Expository documents are vital resources for conveying complex information to readers.
CCGen: Explainable Complementary Concept Generation in E-Commerce
We propose and study Complementary Concept Generation (CCGen): given a concept of interest, e. g., "Digital Cameras", generating a list of complementary concepts, e. g., 1) Camera Lenses 2) Batteries 3) Camera Cases 4) Memory Cards 5) Battery Chargers.
Quantifying Association Capabilities of Large Language Models and Its Implications on Privacy Leakage
The advancement of large language models (LLMs) brings notable improvements across various applications, while simultaneously raising concerns about potential private data exposure.
Mastering the ABCDs of Complex Questions: Answer-Based Claim Decomposition for Fine-grained Self-Evaluation
When answering complex questions, large language models (LLMs) may produce answers that do not satisfy all criteria of the question.
Citation: A Key to Building Responsible and Accountable Large Language Models
Despite the complexity of implementing such a citation mechanism, along with the potential pitfalls, we advocate for its development.
Unsupervised Image Denoising in Real-World Scenarios via Self-Collaboration Parallel Generative Adversarial Branches
Although unsupervised approaches based on generative adversarial networks offer a promising solution for denoising without paired datasets, they are difficult in surpassing the performance limitations of conventional GAN-based unsupervised frameworks without significantly modifying existing structures or increasing the computational complexity of denoisers.
RAVEN: In-Context Learning with Retrieval-Augmented Encoder-Decoder Language Models
In this paper, we investigate the in-context learning ability of retrieval-augmented encoder-decoder language models.
High-quality Image Dehazing with Diffusion Model
The latter stage exploits the strong generation ability of DDPM to compensate for the haze-induced huge information loss, by working in conjunction with the physical modelling.
Generalized Lightness Adaptation with Channel Selective Normalization
Existing methods typically work well on their trained lightness conditions but perform poorly in unknown ones due to their limited generalization ability.
Situated Natural Language Explanations
Situated NLE provides a perspective and facilitates further research on the generation and evaluation of explanations.
Bearing-based Formation with Disturbance Rejection
For the case of the known frequencies, we employ the canonical internal model to solve the problem, and, for the case of the unknown frequencies, we combine the canonical internal model and {some} distributed adaptive control technique to deal with the problem.
Learned Image Reasoning Prior Penetrates Deep Unfolding Network for Panchromatic and Multi-Spectral Image Fusion
Such designs penetrate the image reasoning prior into deep unfolding networks while improving its interpretability and representation capability.
Empowering Low-Light Image Enhancer through Customized Learnable Priors
In this work, we propose a paradigm for low-light image enhancement that explores the potential of customized learnable priors to improve the transparency of the deep unfolding paradigm.
Large Language Models Cannot Self-Correct Reasoning Yet
Large Language Models (LLMs) have emerged as a groundbreaking technology with their unparalleled text generation capabilities across various applications.
Debias the Training of Diffusion Models
Diffusion models have demonstrated compelling generation quality by optimizing the variational lower bound through a simple denoising score matching loss.
Configuration Validation with Large Language Models
We present a first analysis on the feasibility and effectiveness of using LLMs for configuration validation.
Descriptive Knowledge Graph in Biomedical Domain
We present a novel system that automatically extracts and generates informative and descriptive sentences from the biomedical corpus and facilitates the efficient search for relational knowledge.
Neural Degradation Representation Learning for All-In-One Image Restoration
To this end, we propose to learn a neural degradation representation (NDR) that captures the underlying characteristics of various degradations.
Ask To The Point: Open-Domain Entity-Centric Question Generation
We introduce a new task called *entity-centric question generation* (ECQG), motivated by real-world applications such as topic-specific learning, assisted reading, and fact-checking.
Text Fact Transfer
Text style transfer is a prominent task that aims to control the style of text without inherently changing its factual content.
Let the Pretrained Language Models "Imagine" for Short Texts Topic Modeling
Besides, we provide a simple solution extending a neural topic model to reduce the effect of noisy out-of-topics text generation from PLMs.
A Novel 3D Non-stationary Localization-assisted ISAC Channel Model
Integrated sensing and communication (ISAC) has attracted wide attention as an emerging application scenario for the sixth generation (6G) wireless communication system.
A WINNER+ Based 3-D Non-Stationary Wideband MIMO Channel Model
In this paper, a three-dimensional (3-D) non-stationary wideband multiple-input multiple-output (MIMO) channel model based on the WINNER+ channel model is proposed.
Decoupling Degradation and Content Processing for Adverse Weather Image Restoration
The former facilitates channel-dependent degradation removal operation, allowing the network to tailor responses to various adverse weather types; the latter, by integrating Fourier's global properties into channel-independent content features, enhances network capacity for consistent global content reconstruction.
Cascade Speculative Drafting for Even Faster LLM Inference
Introduced to enhance the efficiency of large language model (LLM) inference, speculative decoding operates by having a smaller model generate a draft.
Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents
This iterative cycle of exploration and training fosters continued improvement in the agents.
Long-form factuality in large language models
Empirically, we demonstrate that LLM agents can outperform crowdsourced human annotators - on a set of ~16k individual facts, SAFE agrees with crowdsourced human annotators 72% of the time, and on a random subset of 100 disagreement cases, SAFE wins 76% of the time.
