Search Results for author:
Found 103 papers, 35 papers with code
Improved Named Entity Recognition for Noisy Call Center Transcripts
We explore the application of state-of-the-art NER algorithms to ASR-generated call center transcripts.
A Knowledge-driven Generative Model for Multi-implication Chinese Medical Procedure Entity Normalization
Medical entity normalization, which links medical mentions in the text to entities in knowledge bases, is an important research topic in medical natural language processing.
Masked and Permuted Implicit Context Learning for Scene Text Recognition
Scene Text Recognition (STR) is a challenging task due to variations in text style, shape, and background.
Joint Generative-Contrastive Representation Learning for Anomalous Sound Detection
In this paper, we propose a joint generative and contrastive representation learning method (GeCo) for anomalous sound detection (ASD).
Visual Information Extraction in the Wild: Practical Dataset and End-to-end Solution
We evaluate the existing end-to-end methods for VIE on the proposed dataset and observe that the performance of these methods has a distinguishable drop from SROIE (a widely used English dataset) to our proposed dataset due to the larger variance of layout and entities.
Multi-Teacher Knowledge Distillation For Text Image Machine Translation
Text image machine translation (TIMT) has been widely used in various real-world applications, which translates source language texts in images into another target language sentence.
E2TIMT: Efficient and Effective Modal Adapter for Text Image Machine Translation
Furthermore, the ablation studies verify the generalization of our method, where the proposed modal adapter is effective to bridge various OCR and MT models.
A Lightweight Recurrent Learning Network for Sustainable Compressed Sensing
While the initial reconstruction sub-network has a hierarchical structure to progressively recover the image, reducing the number of parameters, the residual reconstruction sub-network facilitates recurrent residual feature extraction via recurrent learning to perform both feature fusion and deep reconstructions across different scales.
Quaternion Orthogonal Transformer for Facial Expression Recognition in the Wild
Firstly, to reduce redundancy among features extracted from pre-trained ResNet-50, we use the orthogonal loss to decompose and compact these features into three sets of orthogonal sub-features.
Overview and Performance Analysis of Various Waveforms in High Mobility Scenarios
In the high-mobility scenarios of next-generation wireless communication systems (beyond 5G/6G), the performance of orthogonal frequency division multiplexing (OFDM) deteriorates drastically due to the loss of orthogonality between the subcarriers caused by large Doppler frequency shifts.
Cyclic Delay-Doppler Shift: A Simple Transmit Diversity Technique for Delay-Doppler Waveforms in Doubly Selective Channels
Delay-Doppler waveform design has been considered as a promising solution to achieve reliable communication under high-mobility channels for the space-air-ground-integrated networks (SAGIN).
UATVR: Uncertainty-Adaptive Text-Video Retrieval
In the refined embedding space, we represent text-video pairs as probabilistic distributions where prototypes are sampled for matching evaluation.
Even Order Explicit Symplectic Geometric Algorithms for Quaternion Kinematical Differential Equation in Guidance Navigation and Control via Diagonal Padè Approximation and Cayley Transform
Although explicit symplectic geometric algorithms (ESGA) for this problem are available, there is a lack of a unified way for constructing high order symplectic difference schemes with configurable order parameter.
Life-long Learning for Multilingual Neural Machine Translation with Knowledge Distillation
To alleviate the CF, we investigate knowledge distillation based life-long learning methods.
Renewing Iterative Self-labeling Domain Adaptation with Application to the Spine Motion Prediction
The area of transfer learning comprises supervised machine learning methods that cope with the issue when the training and testing data have different input feature spaces or distributions.
Beyond Instance Discrimination: Relation-aware Contrastive Self-supervised Learning
In this paper, we present relation-aware contrastive self-supervised learning (ReCo) to integrate instance relations, i. e., global distribution relation and local interpolation relation, into the CSL framework in a plug-and-play fashion.
Dual-distribution discrepancy with self-supervised refinement for anomaly detection in medical images
Due to the high-cost annotations of abnormal images, most methods utilize only known normal images during training and identify samples deviating from the normal profile as anomalies in the testing phase.
Improving End-to-End Text Image Translation From the Auxiliary Text Translation Task
End-to-end text image translation (TIT), which aims at translating the source language embedded in images to the target language, has attracted intensive attention in recent research.
Generalized Homogeneous Rigid-BodyAttitude Control
The attitude tracking problem for a full-actuated rigid body in 3D is studied using a impulsive system model based on Lie algebra so(3).
Automatic Analysis of Available Source Code of Top Artificial Intelligence Conference Papers
Some organizations and researchers manually collect AI papers with available source code to contribute to the AI community.
Weakly Supervised Semantic Segmentation via Progressive Patch Learning
"Progressive Patch Learning" further extends the feature destruction and patch learning to multi-level granularities in a progressive manner.
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
Towards Personalized Healthcare in Cardiac Population: The Development of a Wearable ECG Monitoring System, an ECG Lossy Compression Schema, and a ResNet-Based AF Detector
This system continuously monitors the users' ECG information to provide personalized health warnings/feedbacks.
Field Evaluation of Four Low-cost PM Sensors and Design, Development and Field Evaluation of A Wearable PM Exposure Monitoring System
To mitigate the significant biases/errors in research studying the associations between PM and health, which are introduced by the coarse/inadequate assessments of PM exposure from conventional PM monitoring paradigm, a personalized monitoring system consisting of a low-cost wearable PM device is proposed.
Dual-Distribution Discrepancy for Anomaly Detection in Chest X-Rays
Subsequently, inter-discrepancy between the two modules, and intra-discrepancy inside the module that is trained on only normal images are designed as anomaly scores to indicate anomalies.
Other Roles Matter! Enhancing Role-Oriented Dialogue Summarization via Role Interactions
Therefore, we propose a novel role interaction enhanced method for role-oriented dialogue summarization.
UNITS: Unsupervised Intermediate Training Stage for Scene Text Detection
Recent scene text detection methods are almost based on deep learning and data-driven.
GitNet: Geometric Prior-based Transformation for Birds-Eye-View Segmentation
Birds-eye-view (BEV) semantic segmentation is critical for autonomous driving for its powerful spatial representation ability.
MARF: Multiscale Adaptive-switch Random Forest for Leg Detection with 2D Laser Scanners
Moreover, we further apply the proposed MARF to the people detection and tracking system, achieving a considerable gain in all metrics.
Towards Escaping from Language Bias and OCR Error: Semantics-Centered Text Visual Question Answering
Texts in scene images convey critical information for scene understanding and reasoning.
Look\&Listen: Multi-Modal Correlation Learning for Active Speaker Detection and Speech Enhancement
Active speaker detection and speech enhancement have become two increasingly attractive topics in audio-visual scenario understanding.
Imagine by Reasoning: A Reasoning-Based Implicit Semantic Data Augmentation for Long-Tailed Classification
Since the covariance matrix of each category represents the feature transformation directions, we can sample new directions from similar categories to generate definitely different instances.
Ranked #47 on
Long-tail Learning
on CIFAR-10-LT (ρ=10)
Learning to Select the Next Reasonable Mention for Entity Linking
To address the problem, we propose a novel model, called DyMen, to dynamically adjust the subsequent linking target based on the previously linked entities via reinforcement learning, enabling the model to select a link target that can fully use previously linked information.
Ghost Imaging Based on Recurrent Neural Network
The testing results show that the proposed method can achieve image reconstruction at a very low sampling rate (0. 38$\%$).
Tiny Obstacle Discovery by Occlusion-Aware Multilayer Regression
Edges are the fundamental visual element for discovering tiny obstacles using a monocular camera.
Video Text Tracking With a Spatio-Temporal Complementary Model
We leverage a Siamese ComplementaryModule to fully exploit the continuity characteristic of the textinstances in the temporal dimension, which effectively alleviatesthe missed detection of the text instances, and hence ensuresthe completeness of each text trajectory.
TPSNet: Reverse Thinking of Thin Plate Splines for Arbitrary Shape Scene Text Representation
The research focus of scene text detection and recognition has shifted to arbitrary shape text in recent years, where the text shape representation is a fundamental problem.
Dense Semantic Contrast for Self-Supervised Visual Representation Learning
Concretely, these downstream tasks require more accurate representation, in other words, the pixels from the same object must belong to a shared semantic category, which is lacking in the previous methods.
PIMNet: A Parallel, Iterative and Mimicking Network for Scene Text Recognition
In this paper, we propose a Parallel, Iterative and Mimicking Network (PIMNet) to balance accuracy and efficiency.
Which and Where to Focus: A Simple yet Accurate Framework for Arbitrary-Shaped Nearby Text Detection in Scene Images
In this paper, we propose a simple yet effective method for accurate arbitrary-shaped nearby scene text detection.
Mask is All You Need: Rethinking Mask R-CNN for Dense and Arbitrary-Shaped Scene Text Detection
We propose to use an MLP decoder instead of the "deconv-conv" decoder in the mask head, which alleviates the issue and promotes robustness significantly.
CSDS: A Fine-Grained Chinese Dataset for Customer Service Dialogue Summarization
Therefore, in this paper, we introduce a novel Chinese dataset for Customer Service Dialogue Summarization (CSDS).
Augmenting Slot Values and Contexts for Spoken Language Understanding with Pretrained Models
We propose two strategies for finetuning process: value-based and context-based augmentation.
0.8% Nyquist computational ghost imaging via non-experimental deep learning
We present a framework for computational ghost imaging based on deep learning and customized pink noise speckle patterns.
Video 3D Sampling for Self-supervised Representation Learning
As a result, we can leverage the spatial information (the size of objects), temporal information (the direction and magnitude of motions) as our learning target.
Multi-View Correlation Distillation for Incremental Object Detection
Due to the storage burden and the privacy of old data, sometimes it is impractical to train the model from scratch with both old and new data.
MMF: Multi-Task Multi-Structure Fusion for Hierarchical Image Classification
Hierarchical classification is significant for complex tasks by providing multi-granular predictions and encouraging better mistakes.
Rail-5k: a Real-World Dataset for Rail Surface Defects Detection
This paper presents the Rail-5k dataset for benchmarking the performance of visual algorithms in a real-world application scenario, namely the rail surface defects detection task.
Cross-hospital Sepsis Early Detection via Semi-supervised Optimal Transport with Self-paced Ensemble
To address this issue, we propose a novel semi-supervised transfer learning framework based on optimal transport theory and self-paced ensemble for Sepsis early detection, called SPSSOT, which can efficiently transfer knowledge from the source hospital (with rich labeled data) to the target hospital (with scarce labeled data).
Exploring Instance Relations for Unsupervised Feature Embedding
Despite the great progress achieved in unsupervised feature embedding, existing contrastive learning methods typically pursue view-invariant representations through attracting positive sample pairs and repelling negative sample pairs in the embedding space, while neglecting to systematically explore instance relations.
TransCrowd: weakly-supervised crowd counting with transformers
Current weakly-supervised counting methods adopt the CNN to regress a total count of the crowd by an image-to-count paradigm.
A Physics-based and Data-driven Linear Three-Phase Power Flow Model for Distribution Power Systems
Case studies have demonstrated that our model generally has 2 to over 10-fold smaller average errors than other linear power flow models, enjoys a satisfying accuracy against bad data, and facilitates a faster solution to DPS analysis and optimization problems.
Boundary-induced and scene-aggregated network for monocular depth prediction
However, two issues remain unresolved: (1) The deep feature encodes the wrong farthest region in a scene, which leads to a distorted 3D structure of the predicted depth; (2) The low-level features are insufficient utilized, which makes it even harder to estimate the depth near the edge with sudden depth change.
Focal Inverse Distance Transform Maps for Crowd Localization
Most regression-based methods utilize convolution neural networks (CNN) to regress a density map, which can not accurately locate the instance in the extremely dense scene, attributed to two crucial reasons: 1) the density map consists of a series of blurry Gaussian blobs, 2) severe overlaps exist in the dense region of the density map.
Streaming from the Air: Enabling Drone-sourced Video Streaming Applications on 5G Open-RAN Architectures
This may result in uplink inter-cell interference and uplink performance degradation for the neighboring ground UEs when drones transmit at high data-rates (e. g., video streaming).
Networking and Internet Architecture Signal Processing
Quick Annotator: an open-source digital pathology based rapid image annotation tool
Image based biomarker discovery typically requires an accurate segmentation of histologic structures (e. g., cell nuclei, tubules, epithelial regions) in digital pathology Whole Slide Images (WSI).
Graph Neural Networks: Taxonomy, Advances and Trends
Graph neural networks provide a powerful toolkit for embedding real-world graphs into low-dimensional spaces according to specific tasks.
Dual Attention Network for Cross-lingual Entity Alignment
The hierarchical attention adaptively aggregates the low-hierarchy and the high-hierarchy information, which is beneficial to balance the neighborhood information of counterpart entities and distinguish non-counterpart entities with similar structures.
Knowledge Graph Enhanced Neural Machine Translation via Multi-task Learning on Sub-entity Granularity
Previous studies combining knowledge graph (KG) with neural machine translation (NMT) have two problems: i) Knowledge under-utilization: they only focus on the entities that appear in both KG and training sentence pairs, making much knowledge in KG unable to be fully utilized.
Gaussian Constrained Attention Network for Scene Text Recognition
In this paper, we propose Gaussian Constrained Attention Network to deal with this problem.
Exploring Relations in Untrimmed Videos for Self-Supervised Learning
Then a designed sampling strategy is used to model relations for video clips.
Two-Level Residual Distillation based Triple Network for Incremental Object Detection
Modern object detection methods based on convolutional neural network suffer from severe catastrophic forgetting in learning new classes without original data.
Expert Training: Task Hardness Aware Meta-Learning for Few-Shot Classification
Some works in the optimization of deep neural networks have shown that a better arrangement of training data can make the classifier converge faster and perform better.
FC2RN: A Fully Convolutional Corner Refinement Network for Accurate Multi-Oriented Scene Text Detection
Accurate detection of multi-oriented text with large variations of scales, orientations, and aspect ratios is of great significance.
Progressive Cluster Purification for Unsupervised Feature Learning
In this work, we propose a novel clustering based method, which, by iteratively excluding class inconsistent samples during progressive cluster formation, alleviates the impact of noise samples in a simple-yet-effective manner.
Attend, Translate and Summarize: An Efficient Method for Neural Cross-Lingual Summarization
Cross-lingual summarization aims at summarizing a document in one language (e. g., Chinese) into another language (e. g., English).
Video Playback Rate Perception for Self-supervisedSpatio-Temporal Representation Learning
The generative perception model acts as a feature decoder to focus on comprehending high temporal resolution and short-term representation by introducing a motion-attention mechanism.
Self-Training for Domain Adaptive Scene Text Detection
To address this problem, we propose a self-training framework to automatically mine hard examples with pseudo-labels from unannotated videos or images.
SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition
Scene text recognition is a hot research topic in computer vision.
Boosting API Recommendation with Implicit Feedback
In this paper, we propose a framework, BRAID (Boosting RecommendAtion with Implicit FeeDback), which leverages learning-to-rank and active learning techniques to boost recommendation performance.
Video Cloze Procedure for Self-Supervised Spatio-Temporal Learning
As a proxy task, it converts rich self-supervised representations into video clip operations (options), which enhances the flexibility and reduces the complexity of representation learning.
Ranked #11 on
Self-supervised Video Retrieval
on HMDB51
TANet: Robust 3D Object Detection from Point Clouds with Triple Attention
In this paper, we focus on exploring the robustness of the 3D object detection in point clouds, which has been rarely discussed in existing approaches.
Neural Topic Model with Reinforcement Learning
In recent years, advances in neural variational inference have achieved many successes in text processing.
DeepVS: An Efficient and Generic Approach for Source Code Modeling Usage
The source code suggestions provided by current IDEs are mostly dependent on static type learning.
Deep Transfer Learning for Source Code Modeling
A challenging issue of these approaches is that they require training from starch for a different related problem.
NCLS: Neural Cross-Lingual Summarization
Moreover, we propose to further improve NCLS by incorporating two related tasks, monolingual summarization and machine translation, into the training process of CLS under multi-task learning.
Curved Text Detection in Natural Scene Images with Semi- and Weakly-Supervised Learning
The performance of the proposed method is comparable with the state-of-the-art methods with only 10% pixel-level annotated data and 90% rectangle-level weakly annotated data.
Occlusion-shared and Feature-separated Network for Occlusion Relationship Reasoning
On one hand, considering the relevance between edge and orientation, two sub-networks are designed to share the occlusion cue.
Understanding Memory Modules on Learning Simple Algorithms
Recent work has shown that memory modules are crucial for the generalization ability of neural networks on learning simple algorithms.
Memory Consolidation for Contextual Spoken Language Understanding with Dialogue Logistic Inference
Dialogue contexts are proven helpful in the spoken language understanding (SLU) system and they are typically encoded with explicit memory representations.
A Novel Multi-layer Framework for Tiny Obstacle Discovery
For tiny obstacle discovery in a monocular image, edge is a fundamental visual element.
Context-Constrained Accurate Contour Extraction for Occlusion Edge Detection
Occlusion edge detection requires both accurate locations and context constraints of the contour.
CodeGRU: Context-aware Deep Learning with Gated Recurrent Unit for Source Code Modeling
We evaluate CodeGRU with real-world data set and it shows that CodeGRU outperforms the state-of-the-art language models and help reduce the vocabulary size up to 24. 93\%.
Neural Abstract Style Transfer for Chinese Traditional Painting
In experiments, the proposed method shows more appealing stylized results in transferring the style of Chinese traditional painting than state-of-the-art neural style transfer methods.
MSMO: Multimodal Summarization with Multimodal Output
In this paper, we propose a novel task, multimodal summarization with multimodal output (MSMO).
Source-Critical Reinforcement Learning for Transferring Spoken Language Understanding to a New Language
This paper focuses on the language transferring task given a tiny in-domain parallel SLU corpus.
Cultural Vocal Bursts Intensity Prediction
General Classification
+5
Source Critical Reinforcement Learning for Transferring Spoken Language Understanding to a New Language
An SLU corpus is a monolingual corpus with domain/intent/slot labels.
Cultural Vocal Bursts Intensity Prediction
General Classification
+6
Decorated marked surfaces III: The derived category of a decorated marked surface
As an application, we show that the spherical twist group $\operatorname{ST}(\mathbf{S}_\bigtriangleup)$ associated to $\mathcal{D}_{fd}(\mathbf{S}_\bigtriangleup)$ acts faithfully on its space of stability conditions.
Representation Theory Rings and Algebras
Learning from Parenthetical Sentences for Term Translation in Machine Translation
Terms extensively exist in specific domains, and term translation plays a critical role in domain-specific machine translation (MT) tasks.
Imaging around corners with single-pixel detector by computational ghost imaging
We have designed a single-pixel camera with imaging around corners based on computational ghost imaging.
Matching-Based Selection with Incomplete Lists for Decomposition Multi-Objective Optimization
In particular, the stable matching between subproblems and solutions, which achieves an equilibrium between their mutual preferences, implicitly strikes a balance between the convergence and diversity.
Decorated marked surfaces II: Intersection numbers and dimensions of Homs
We study the 3-Calabi-Yau categories $\mathcal{D}$ arising from quivers with potential associated to a decorated marked surface $\mathbf{S}_\bigtriangleup$ introduced by the first author.
Representation Theory Category Theory Geometric Topology
Cluster categories for marked surfaces: punctured case
We study the cluster categories arising from marked surfaces (with punctures and non-empty boundaries).
Representation Theory Geometric Topology 16G20, 18E30, 16E30, 57M50 (primary), 16G70 (secondary)
Unsupervised Tree Induction for Tree-based Translation
In current research, most tree-based translation models are built directly from parse trees.
Fusion with Diffusion for Robust Visual Tracking
A key feature of our approach is that the time complexity of the dif-fusion on the TPG is the same as the diffusion process on each of the original graphs, Moreover, it is not necessary to explicitly construct the TPG in our frame-work.
