22 Result(s)
-
Article
Unsupervised Domain Adaptation on Sentence Matching Through Self-Supervision
Although neural approaches have yielded state-of-the-art results in the sentence matching task, their performance inevitably drops dramatically when applied to unseen domains. To tackle this cross-domain chall...
-
Article
Unsupervised Dialogue State Tracking for End-to-End Task-Oriented Dialogue with a Multi-Span Prediction Network
This paper focuses on end-to-end task-oriented dialogue systems, which jointly handle dialogue state tracking (DST) and response generation. Traditional methods usually adopt a supervised paradigm to learn DST...
-
Chapter and Conference Paper
A Distilled 2D CNN-LSTM Framework with Temporal Attention Mechanism for Action Recognition
Action Recognition has been studied for many years. In recent years, there are some methods using 3D-CNN (C3D, I3D, R2 + 1D), which have high accuracy, but it is hard to train and quite time-consuming due to t...
-
Article
Graph fusion network for multi-oriented object detection
In object detection, non-maximum suppression (NMS) methods are extensively adopted to remove horizontal duplicates of detected dense boxes for generating final object instances. However, due to the degraded qu...
-
Article
A Unified Shared-Private Network with Denoising for Dialogue State Tracking
Dialogue state tracking (DST) leverages dialogue information to predict dialogues states which are generally represented as slot-value pairs. However, previous work usually has limitations to efficiently predi...
-
Article
Heterogeneous defect prediction with two-stage ensemble learning
Heterogeneous defect prediction (HDP) refers to predicting defect-prone software modules in one project (target) using heterogeneous data collected from other projects (source). Recently, several HDP methods h...
-
Article
A Large Chinese Text Dataset in the Wild
In this paper, we introduce a very large Chinese text dataset in the wild. While optical character recognition (OCR) in document images is well studied and many commercial tools are available, the detection an...
-
Chapter and Conference Paper
Pick-and-Learn: Automatic Quality Evaluation for Noisy-Labeled Image Segmentation
Deep learning methods have achieved promising performance in many areas, but they are still struggling with noisy-labeled images during the training process. Considering that the annotation quality indispensab...
-
Article
Approximate Continuous Top-k Query over Sliding Window
Continuous top-k query over sliding window is a fundamental problem in database, which retrieves k objects with the highest scores when the window slides. Existing studies mainly adopt exact algorithms to tackle ...
-
Article
xBreeze/ADL: A language for software architecture specification and analysis
Architecture description languages play an important role in modelling software architectures. However, many architecture description languages (ADLs) are either unable to deal with the verification and dynami...
-
Article
Open AccessPanorama completion for street views
This paper considers panorama images used for street views. Their viewing angle of 360° causes pixels at the top and bottom to appear stretched and warped. Although current image completion algorithms work wel...
-
Chapter and Conference Paper
A Digital Lock-In Amplifier Based Contact Detection Technique for Electrochemical Nanolithography
This paper presents a digital lock-in amplifier (DLIA) based technique to detect the template-substrate contact in electrochemical nanolithography. This technique is applied to a specially designed electrochem...
-
Chapter and Conference Paper
CMMB Image Sequences Measurement Based on Computation in High-Dimension Space
At present, video contents from the Internet are accessed with increasing frequency. In this paper, combined with China Mobile Multimedia Broadcasting (CMMB) system characteristics is presented based on high-d...
-
Chapter and Conference Paper
Flame Alarm Annotation in Video Based on Gabor Filter
Alarm is often been watched out in videos monitor. In this paper, it gives a method of annotation of Flame. In Gabor space, an image can be translated into different channels. With different frequency spaces, ...
-
Chapter and Conference Paper
Image Annotation Based on Central Region Features Reduction
Automatic image annotation is an important and useful approach to narrow the semantic gap between visual features and semantics. However, it is time-consuming job since it extracting the visual features from a...
-
Chapter and Conference Paper
Video Frame Quality Assessment Using Points Calculation in High Dimensional Space
Video quality assessment is widely used for signal measure. Classic method is often use algebra method for make a compute model, such as PSNR, which often lead to difficult for alignment of video sequence numb...
-
Chapter and Conference Paper
Two Natural Heuristics for 3D Packing with Practical Loading Constraints
In this paper, we describe two heuristics for the Single Vehicle Loading Problem (SVLP), which can handle practical constraints that are frequently encountered in the freight transportation industry, such as t...
-
Article
Generalized block triangular preconditioner for symmetric saddle point problems
In this paper, spectral properties and computational performance of a generalized block triangular preconditioner for symmetric saddle point problems are discussed in detail. We will provide estimates for the ...
-
Chapter and Conference Paper
A Multi-Scale Algorithm for Graffito Advertisement Detection from Images of Real Estate
There is a significant need to detect and extract the graffito advertisement embedded in the housing images automatically. However, it is a hard job to separate the advertisement region well since housing imag...
-
Chapter and Conference Paper
Mining Knowledge from Multiple Criteria Linear Programming Models
As a promising data mining tool, Multiple Criteria Linear Programming (MCLP) has been widely used in business intelligence. However, a possible limitation of MCLP is that it generates unexplainable black-box m...
