Search Results for author:
Found 38 papers, 15 papers with code
面向微博文本的融合字词信息的轻量级命名实体识别(Lightweight Named Entity Recognition for Weibo Based on Word and Character)
中文社交媒体命名实体识别由于其领域特殊性, 一直广受关注。非正式且无结构的微博文本存在以下两个问题:一是词语边界模糊;二是语料规模有限。针对问题一, 本文将同维度的字词进行融合, 获得丰富的文本序列表征;针对问题二, 提出了基于Star-Transformer框架的命名实体识别模型, 借助星型拓扑结构更好地捕获动态特征;同时利用高速网络优化Star-Transformer中的信息桥接, 提升模型的鲁棒性。本文提出的轻量级命名实体识别模型取得了目前Weibo语料上最好的效果。
Sparse Adversarial Attack via Perturbation Factorization
Based on this factorization, we formulate the sparse attack problem as a mixed integer programming (MIP) to jointly optimize the binary selection factors and continuous perturbation magnitudes of all pixels, with a cardinality constraint on selection factors to explicitly control the degree of sparsity.
SFOD: Spiking Fusion Object Detector
Thereby, we establish state-of-the-art classification results based on SNNs, achieving 93. 7\% accuracy on the NCAR dataset.
VEglue: Testing Visual Entailment Systems via Object-Aligned Joint Erasing
Visual entailment (VE) is a multimodal reasoning task consisting of image-sentence pairs whereby a promise is defined by an image, and a hypothesis is described by a sentence.
Adversarial Testing for Visual Grounding via Image-Aware Property Reduction
To this end, we propose PEELING, a text perturbation approach via image-aware property reduction for adversarial testing of the VG model.
Enhancing Steganographic Text Extraction: Evaluating the Impact of NLP Models on Accuracy and Semantic Coherence
This study discusses a new method combining image steganography technology with Natural Language Processing (NLP) large models, aimed at improving the accuracy and robustness of extracting steganographic text.
Play Guessing Game with LLM: Indirect Jailbreak Attack with Implicit Clues
With the development of LLMs, the security threats of LLMs are getting more and more attention.
Intelligent Diagnosis of Alzheimer's Disease Based on Machine Learning
Overall, this study successfully overcomes the challenge of missing data and provides valuable insights into early detection of Alzheimer's disease, demonstrating its unique research value and practical significance.
SemanticSLAM: Learning based Semantic Map Construction and Robust Camera Localization
This approach enables the creation of a semantic map of the environment and ensures reliable camera localization.
FMGS: Foundation Model Embedded 3D Gaussian Splatting for Holistic 3D Scene Understanding
This is achieved by distilling feature maps generated from image-based foundation models into those rendered from our 3D model.
A New Benchmark and Model for Challenging Image Manipulation Detection
Existing Image Manipulation Detection (IMD) methods are mainly based on detecting anomalous features arisen from image editing or double compression artifacts.
Closed-Loop Transcription via Convolutional Sparse Coding
Our method is arguably the first to demonstrate that a concatenation of multiple convolution sparse coding/decoding layers leads to an interpretable and effective autoencoder for modeling the distribution of large-scale natural image datasets.
Form 10-K Itemization
With the segmented Item sections, NLP techniques can directly apply on those Item sections related to downstream tasks.
Unsupervised Learning of Structured Representations via Closed-Loop Transcription
This paper proposes an unsupervised method for learning a unified representation that serves both discriminative and generative purposes.
Revisiting Sparse Convolutional Model for Visual Recognition
We show that such models have equally strong empirical performance on CIFAR-10, CIFAR-100, and ImageNet datasets when compared to conventional neural networks.
SuperLine3D: Self-supervised Line Segmentation and Description for LiDAR Point Cloud
To repetitively extract them as features and perform association between discrete LiDAR frames for registration, we propose the first learning-based feature segmentation and description model for 3D lines in LiDAR point cloud.
DuMLP-Pin: A Dual-MLP-dot-product Permutation-invariant Network for Set Feature Extraction
We strictly prove that any permutation-invariant function implemented by DuMLP-Pin can be decomposed into two or more permutation-equivariant ones in a dot-product way as the cardinality of the given input set is greater than a threshold.
Translation Invariant Global Estimation of Heading Angle Using Sinogram of LiDAR Point Cloud
Global point cloud registration is an essential module for localization, of which the main difficulty exists in estimating the rotation globally without initial value.
Incremental Learning of Structured Memory via Closed-Loop Transcription
Our method is simpler than existing approaches for incremental learning, and more efficient in terms of model size, storage, and computation: it requires only a single, fixed-capacity autoencoding network with a feature space that is used for both discriminative and generative purposes.
Closed-Loop Data Transcription to an LDR via Minimaxing Rate Reduction
In particular, we propose to learn a closed-loop transcription between a multi-class multi-dimensional data distribution and a linear discriminative representation (LDR) in the feature space that consists of multiple independent multi-dimensional linear subspaces.
CATRO: Channel Pruning via Class-Aware Trace Ratio Optimization
Deep convolutional neural networks are shown to be overkill with high parametric and computational redundancy in many application scenarios, and an increasing number of works have explored model pruning to obtain lightweight and efficient networks.
IMU Data Processing For Inertial Aided Navigation: A Recurrent Neural Network Based Approach
In this work, we propose a novel method for performing inertial aided navigation, by using deep neural networks (DNNs).
MirrorAlign: A Super Lightweight Unsupervised Word Alignment Model via Cross-Lingual Contrastive Learning
Recently, the performance of the neural word alignment models has exceeded that of statistical models.
Studying Politeness across Cultures Using English Twitter and Mandarin Weibo
We study the linguistic features associated with politeness across US English and Mandarin Chinese.
Social and Information Networks Computers and Society
From A Glance to "Gotcha": Interactive Facial Image Retrieval with Progressive Relevance Feedback
Facial image retrieval plays a significant role in forensic investigations where an untrained witness tries to identify a suspect from a massive pool of images.
Interpretable Foreground Object Search As Knowledge Distillation
As for the proposed method, we first train a foreground encoder to learn representations of interchangeable foregrounds.
SEKD: Self-Evolving Keypoint Detection and Description
Researchers have attempted utilizing deep neural network (DNN) to learn novel local features from images inspired by its recent successes on a variety of vision tasks.
Semi-supervised deep learning for high-dimensional uncertainty quantification
Conventional uncertainty quantification methods usually lacks the capability of dealing with high-dimensional problems due to the curse of dimensionality.
Accelerating Neural Network Inference by Overflow Aware Quantization
The inherent heavy computation of deep neural networks prevents their widespread applications.
MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationships
Monocular 3D object detection is an essential component in autonomous driving while challenging to solve, especially for those occluded samples which are only partially visible.
Ranked #11 on
Vehicle Pose Estimation
on KITTI Cars Hard
LE-HGR: A Lightweight and Efficient RGB-based Online Gesture Recognition Network for Embedded AR Devices
Finally, we provide a variety of experimental results to show that the proposed framework is able to achieve state-of-the-art accuracy with significantly reduced computational cost, which are the key properties for enabling real-time applications in low-cost commercial devices such as mobile devices and AR/VR headsets.
Visual-Inertial Localization for Skid-Steering Robots with Kinematic Constraints
While visual localization or SLAM has witnessed great progress in past decades, when deploying it on a mobile robot in practice, few works have explicitly considered the kinematic (or dynamic) constraints of the real robotic system when designing state estimators.
Sem-LSD: A Learning-based Semantic Line Segment Detector
Combined with high-level semantics, Sem-LS is more robust under cluttered environment compared with existing line-shaped representations.
Pose Estimation for Ground Robots: On Manifold Representation, Integration, Re-Parameterization, and Optimization
In this paper, we focus on motion estimation dedicated for non-holonomic ground robots, by probabilistically fusing measurements from the wheel odometer and exteroceptive sensors.
Seq-SG2SL: Inferring Semantic Layout from Scene Graph Through Sequence to Sequence Learning
The framework, called Seq-SG2SL, derives sequence proxies for the two modality and a Transformer-based seq-to-seq model learns to transduce one into the other.
Learning Local Feature Descriptor with Motion Attribute for Vision-based Localization
For better performance, the features used for open-loop localization are required to be short-term globally static, and the ones used for re-localization or loop closure detection need to be long-term static.
Studying Cultural Differences in Emoji Usage across the East and the West
Global acceptance of Emojis suggests a cross-cultural, normative use of Emojis.
2D LiDAR Map Prediction via Estimating Motion Flow with GRU
To tackle this problem, we resort to the motion flow between adjacent maps, as motion flow is a powerful tool to process and analyze the dynamic data, which is named optical flow in video processing.
