39 accepted papers
Existing diffusion models have made significant progress in generating realistic images. However, their direct adaptation to remote sensing imagery often disregards intrinsic physical laws. This oversight frequently leads to spectral distortion and radiometric inconsistency, severely limiting the sc…
Real-time 3D reconstruction is crucial for robotics and augmented reality, yet current simultaneous localization and mapping(SLAM) approaches often struggle to maintain structural consistency and robust pose estimation in the presence of depth noise. This work introduces PointSLAM++, a novel RGB-D S
Robots performing collaborative, long-horizon dexterity cell micromanipulation tasks are challenging and practically significant, such as stripping intact cell membranes, which is considered as one of the most technically demanding procedures. Imitation learning approach is expected to address the c
Time series forecasting (TSF) plays a crucial role in many real-world applications, such as weather prediction and economic planning. While Transformer-based models have shown strong capabilities in modeling long-range dependencies, effectively capturing the multi-scale temporal dynamics inherent in
Large Multimodal Models have achieved remarkable progress in integrating vision and language, enabling strong performance across perception, reasoning, and domain-specific tasks. However, their capacity to reason over multiple, visually similar inputs remains insufficiently explored. Such fine-grain…
Semantic map models (SMMs) construct a network-like conceptual space from cross-linguistic instances or forms, based on the connectivity hypothesis. This approach has been widely used to represent similarity and entailment relationships in cross-linguistic concept comparisons. However, most SMMs are…
Intelligent putty coating technology is the main way to improve the degree of automation of railroad vehicle painting workshops. The two-component putty, which is currently used in the vehicle coating system, has extremely low fluidity, which requires improving the full coverage of the spray path wh
Open-vocabulary detectors are proposed to locate and recognize objects in novel classes. However, variations in vision-aware language vocabulary data used for open-vocabulary learning can lead to unfair and unreliable evaluations. Recent evaluation methods have attempted to address this issue by inc
Generative models are widely used to produce synthetic images with annotations, alleviating the burden of image collection and annotation for training deep visual models. However, challenges such as limited image diversity, noisy pseudo labels, and domain gaps between synthetic and real images often…
Classical neural ODEs trained with explicit methods are intrinsically limited by stability, crippling their efficiency and robustness for stiff learning problems that are common in graph learning and scientific machine learning. We present a semi-implicit neural ODE approach that exploits the partit…
3D Gaussian Splatting (3D-GS) has exhibited impressive progress in novel view synthesis. When given the sparse views, its performance degrades severely, causing many problems like novel views collapse and excessive floaters. Many recent methods take into account fitting input views, inferring missin…
Color correction (CC) plays a pivotal role in camera imaging. Existing approaches usually conduct CC tuning by minimizing ∆E (e.g. ∆E2000), a standard metric proposed by CIE for representing color differences in LAB space. However, we observe that not all the colors with identical ∆E error to the ta…
Due to the huge scale of literary works, automatic text analysis technologies are urgently needed for literary studies such as Digital Humanities. However, the domain-generality of existing NLP technologies limits their effectiveness on in-depth literary studies. It is valuable to explore how to ada…
Multiple-choice question answering (MCQA) requires the model to select the correct answer from a set of candidate options when given a passage and a question. Previous research has achieved promising results with the assistance of Pre-trained Language Models(PrLMs). However, it has been observed tha…
Mitigating linguistic bias and attaining modal equilibrium in Visual Question Answering (VQA) tasks constitute a pivotal concern. Previous work has mainly focused on data augmentation or a uni-modal approach, which is insufficient to fully utilize bi-modal information. In this work, we propose a new…
Cross-domain few-shot Relation Extraction (RE) aims to transfer knowledge from a source domain to a different target domain to address low-resource problems.Previous work utilized label descriptions and entity information to leverage the knowledge of the source domain.However, these models are prone…
Proper moral beliefs are fundamental for language models, yet assessing these beliefs poses a significant challenge. This study introduces a novel three-module framework to evaluate the moral beliefs of four prominent large language models. Initially, we constructed a dataset containing 472 moral ch…
Large language models have achieved remarkable success in general language understanding tasks. However, as a family of generative methods with the objective of next token prediction, the semantic evolution with the depth of these models are not fully explored, unlike their predecessors, such as BER…
Predicting unseen relations that cannot be observed during the training phase is a challenging task in relation extraction. Previous works have made progress by matching the semantics between input instances and label descriptions. However, fine-grained matching often requires laborious manual annot…
While nationality is a pivotal demographic element that enhances the performance of language models, it has received far less scrutiny regarding inherent biases. This study investigates nationality bias in ChatGPT (GPT-3.5), a large language model (LLM) designed for text generation. The research cov…
With the growing applications of water operations, water surface object detection tasks are facing new challenges. In this paper, we focus on improving the performance of water surface small object detection. Due to the limitations of single-sensor in water environments, we propose RCFNet, a novel s…
Metaphor detection (MD) suffers from limited training data. In this paper, we started with a linguistic rule called Metaphor Identification Procedure and then proposed a novel multi-task learning framework to transfer knowledge in basic sense discrimination (BSD) to MD. BSD is constructed from word…
Cross-domain Relation Extraction aims to transfer knowledge from a source domain to a different target domain to address low-resource challenges. However, the semantic gap caused by data bias between domains is a major challenge, especially in few-shot scenarios. Previous work has mainly focused on…
Word sense disambiguation (WSD), which aims to determine an appropriate sense for a target word given its context, is crucial for natural language understanding. Existing supervised methods treat WSD as a classification task and have achieved remarkable performance. However, they ignore uncertainty…
The recently proposed identifiable variational autoencoder (iVAE) framework provides a promising approach for learning latent independent components (ICs). iVAEs use auxiliary covariates to build an identifiable generation structure from covariates to ICs to observations, and the posterior network a…
The automatic Brain CT reports generation can improve the efficiency and accuracy of diagnosing cranial diseases. However, current methods are limited by 1) coarse-grained supervision: the training data in image-text format lacks detailed supervision for recognizing subtle abnormalities, and 2) coup…
Medical report automatic generation has gained increasing interest recently as a way to help radiologists write reports more efficiently. However, this image-to-text task is rather challenging due to the typical data biases: 1) Normal physiological structures dominate the images, with only tiny abno…
This paper presents a domain robust deep embedding learning method for speaker verification (SV) tasks. Most recent methods utilize deep neural networks (DNN) to learn compact and discriminative speaker embeddings from large-scale labeled datasets such as VoxCeleb and the NIST SRE corpus. Despite th…
In this paper we present MisNet, a novel model for word level metaphor detection. MisNet converts two linguistic rules, i.e., Metaphor Identification Procedure (MIP) and Selectional Preference Violation (SPV) into semantic matching tasks. MIP module computes the similarity between the contextual mea…
In this paper, we present an effective end-to-end deep embedding learning method based on Dense-Residual networks, which combine the advantages of a densely connected convolutional network (DenseNet) and a residual network (ResNet), for speaker verification (SV). Unlike a model ensemble strategy whi…
Existing pre-trained language models (PLMs) have demonstrated the effectiveness of self-supervised learning for a broad range of natural language processing (NLP) tasks. However, most of them are not explicitly aware of domain-specific knowledge, which is essential for downstream tasks in many domai…
Radar-based sensors provide an attractive choice for hand gesture recognition (HGR). The very challenging problems in radar-based HGR are radar echo data preprocessing and recognition accuracy. In this paper, we propose a convolutional neural network (CNN) for dynamic HGR based on a millimeter-wave…
Texture feature is important in describing tire pattern image which provides useful clue in solving crime cases and traffic accidents. In this paper, we propose a novel texture feature extraction method based on HOG (Histogram of Oriented Gradient) and dominant gradient (DG) in tire pattern images,…
In this paper, we study the problem of distributed blind equalization in single-input multi-output (SIMO) systems, wherein the channels of networked systems share some similarities. This corresponds to a multi-task optimization problem. To tackle this problem, an adaptive distributed generalized Sat…
We develop a novel joint-view Kalman filter for causal reconstruction of compressed-sensed multiview videos. Compressed-sensed multiview video frames are initially reconstructed individually via ℓ <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</inf>…
This paper focuses on the challenge of maintaining reliable connectivity in an ad hoc network, where interference is possible. To cope with such interference, the paper introduces throughput connectivity and weighted throughput connectivity. Throughput connectivity reflects the possibility of establ…
In this work we present a novel scheme for load management in microgrids based on stochastic scheduling of loads under risk-limiting constraints. When trying to enforce adequate power supply in a microgrid, the volatility of renewable resources such as wind energy has to be considered. In the risk o…
Compressed sensing (CS) is the theory and practice of sub-Nyquist sampling of sparse signals of interest. Perfect reconstruction may then be possible with much fewer than the Nyquist required number of data. In this paper, we consider a distributed multi-view imaging system where each camera at a di…
Jamming attacks are a class of network denial of service attacks that can easily be carried out in wireless networks. In order to be able to repair a network in the presence of such attacks, it is desirable to identify the location of jammed nodes and the congested area that is affected by the jamme…