![Loading...](https://link.springer.com/static/c4a417b97a76cc2980e3c25e2271af3129e08bbe/images/pdf-preview/spacer.gif)
-
Chapter and Conference Paper
Semi-End-to-End Nested Named Entity Recognition from Speech
There are two approaches for Named Entity Recognition (NER) from speech: two-step pipeline and End-to-End (E2E). In the pipeline approach, cascading errors are inevitable. In the E2E approach, its annotation m...
-
Chapter and Conference Paper
Pessimistic Adversarially Regularized Learning for Graph Embedding
Autoencoder frameworks have been effectively employed for graph embedding, resulting in successful analysis of graph in low-dimensional space. Recently, generative models (GANs), which learn data distribution ...
-
Chapter and Conference Paper
Lightweight Image Compression Based on Deep Learning
Deep learning based image compression (DLIC) algorithms have achieved higher compression gain than conventional algorithms. However, the large parameters and float-point operations (FLOPs) of DLIC severely lim...
-
Chapter and Conference Paper
Dynamic Motion Graphic Innovation in Mid-digital Era
During the mid-digital era as we are in, computer science and Internet technology are develo** rapidly, we can see the fusion of numerous academic subjects and forms of art, and the collusion of digital medi...
-
Chapter and Conference Paper
Optical Flow-Guided Multi-level Connection Network for Video Deraining
Video deraining, which aims at removing rain streaks from video, has drawn increasing attention in computer vision task. In this paper, we present an optical flow guided multi-level connection network for vide...
-
Chapter and Conference Paper
Weakly Supervised Liver Tumor Segmentation Based on Anchor Box and Adversarial Complementary Learning
Segmentation of liver tumors plays an important role in the subsequent treatment of liver cancer. At present, the mainstream method is the fully supervised method based on deep learning, which requires medical...
-
Chapter and Conference Paper
Cultural Gene: The New Enlightenment from the Display Design of University History Museum
In the context of globalization, “mobile modernity” has become the norm in modern society. In today’s cultural integration, how to make designs with “personal characteristics”, “local characteristics” and “nat...
-
Chapter and Conference Paper
Label-Free Fluorescence Detection of Carbohydrate Antigen 15-3 via DNA AND Logic Gate Based on Graphene Oxide
In this work, we have developed a DNA AND logic gate based on graphene oxide (GO) absorbing single DNA and G-quadruplex interacting with N-methyl mesoporphyrin IX(NMM) for detecting breast cancer biomarker car...
-
Chapter and Conference Paper
Research on Face Degraded Image Generation Algorithm for Practical Application Scenes
In general face super-resolution (FSR) networks, the degraded model usually adopts a simple bicubic down-sampling, without considering more complex degradation conditions and actual scenes. Although this can v...
-
Chapter and Conference Paper
A Novel Autonomous Molecular Mechanism Based on Spatially Localized DNA Computation
Contemporary DNA synthesis technology matures, and the development provides intriguing possibilities for dynamic manipulation of DNA self-assembly, which plays a pivotal role in the behavior of designing versa...
-
Chapter and Conference Paper
LuMiRa: An Integrated Lung Deformation Atlas and 3D-CNN Model of Infiltrates for COVID-19 Prognosis
Although, recently convolutional neural networks (CNNs) based prognostic models have been developed for COVID-19 severity prediction, most of these studies have analyzed characteristics of lung infiltrates (gr...
-
Chapter and Conference Paper
Recommendation Based on Attention Degree and Entropy
With the development of the Internet, the problem of information overload becomes more and more serious. The personalized recommendation technology can establish user profiles through the user’s behavior and o...
-
Chapter and Conference Paper
Generating Videos of Zero-Shot Compositions of Actions and Objects
Human activity videos involve rich, varied interactions between people and objects. In this paper we develop methods for generating such videos – making progress toward addressing the important, open problem o...
-
Chapter and Conference Paper
Piggyback GAN: Efficient Lifelong Learning for Image Conditioned Generation
Humans accumulate knowledge in a lifelong fashion. Modern deep neural networks, on the other hand, are susceptible to catastrophic forgetting: when adapted to perform new tasks, they often fail to preserve the...
-
Chapter and Conference Paper
Deep Learning of Appearance Models for Online Object Tracking
This paper introduces a deep learning based approach for vision based single target tracking. We address this problem by proposing a network architecture which takes the input video frames and directly compute...
-
Chapter and Conference Paper
Viewpoint Estimation for Objects with Convolutional Neural Network Trained on Synthetic Images
In this paper, we propose a method to estimate object viewpoint from a single RGB image and address two problems in estimation: generating training data with viewpoint annotations and extracting powerful featu...
-
Chapter and Conference Paper
Single-Image Expression Invariant Face Recognition Based on Sparse Representation
Face recognition under expression variation has been paid few attentions and remains a difficult problem. This is because the nonlinear shape variation makes it infeasible to match two images linearly. This pa...
-
Chapter and Conference Paper
PEAQ Compatible Audio Quality Estimation Using Computational Auditory Model
This paper proposed an improved objective audio quality estimation system compatible with PEAQ (Perceptual Evaluation of Audio Quality). Based on the computational auditory model, we used a novel psychoacousti...
-
Chapter and Conference Paper
A Novel Multiple Description Approach to Predictive Video Coding
Multiple description coding (MDC) is a source coding technique that exploits path diversity to combat packet losses over error-prone channels. In this paper, we proposed a novel drift-free multi-state MDC meth...
-
Chapter and Conference Paper
Error Concealment for INTRA-Frame Losses over Packet Loss Channels
In this paper, we propose an Error Concealment algorithm for INTRA-frame losses over packet loss channels. The novelty is that not only the INTRA-frame but also the subsequent INTER-frames are error concealed. We...