scholarly journals An Efficient Hierarchical Layered Graph Approach for Multi-Region Segmentation

2019 ◽  
Author(s):  
Leissi M. Castañeda Leon ◽  
Krzysztof Chris Ciesielski ◽  
Paulo A. Vechiatto Miranda
Keyword(s):  
State Of The Art ◽  
Region Segmentation ◽  
Hierarchical Segmentation ◽  
Image Objects ◽  
Hierarchical Relations ◽  
Flow Algorithm ◽  
Segmentation Of Images ◽  
High Level ◽  
Layered Graph ◽  
Weighted Digraph

We proposed a novel efficient seed-based method for the multiple region segmentation of images based on graphs, named Hierarchical Layered Oriented Image Foresting Transform (HLOIFT). It uses a tree of the relations between the image objects, represented by a node. Each tree node may contain different individual high-level priors and defines a weighted digraph, named as layer. The layer graphs are then integrated into a hierarchical graph, considering the hierarchical relations of inclusion and exclusion. A single energy optimization is performed in the hierarchical layered weighted digraph leading to globally optimal results satisfying all the high-level priors. The experimental evaluations of HLOIFT and its extensions, on medical, natural and synthetic images, indicate promising results comparable to the state-of-the-art methods, but with lower computational complexity. Compared to hierarchical segmentation by the min-cut/max-flow algorithm, our approach is less restrictive, leading to globally optimal results in more general scenarios, and has a better running time.

Efficient Hierarchical Multi-Object Segmentation in Layered Graphs

2021 ◽  
Vol 5 (1) ◽  
pp. 21-42
Author(s):  
Leissi M.C. Leon ◽  
Krzysztof C. Ciesielski ◽  
Paulo A.V. Miranda
Keyword(s):  
Object Segmentation ◽  
Structural Information ◽  
Hierarchical Segmentation ◽  
Image Objects ◽  
Hierarchical Relations ◽  
Flow Algorithm ◽  
Segmentation Of Images ◽  
High Level ◽  
Min Cut ◽  
Weighted Digraph

Abstract We propose a novel efficient seed-based method for the multi-object segmentation of images based on graphs, named Hierarchical Layered Oriented Image Foresting Transform (HLOIFT). It uses a tree of the relations between the image objects, with each node in the tree representing an object. Each tree node may contain different individual high-level priors of its corresponding object and defines a weighted digraph, named as layer. The layer graphs are then integrated into a hierarchical graph, considering the hierarchical relations of inclusion and exclusion. A single energy optimization is performed in the hierarchical layered weighted digraph leading to globally optimal results satisfying all the high-level priors. The experimental evaluations of HLOIFT, on medical, natural, and synthetic images, indicate promising results comparable to the related baseline methods that include structural information, but with lower computational complexity. Compared to the hierarchical segmentation by the min-cut/max-flow algorithm, our approach is less restrictive, leading to globally optimal results in more general scenarios, and has a better running time.

scholarly journals Expressing Objects Just Like Words: Recurrent Visual Embedding for Image-Text Matching

2020 ◽  
Vol 34 (07) ◽  
pp. 10583-10590
Author(s):  
Tianlang Chen ◽  
Jiebo Luo
Keyword(s):  
Recurrent Neural Networks ◽  
State Of The Art ◽  
Input Image ◽  
Word Embeddings ◽  
Retrieval Task ◽  
Image Objects ◽  
High Level ◽  
Object Features ◽  
Cross Matching ◽  
Text Matching

Existing image-text matching approaches typically infer the similarity of an image-text pair by capturing and aggregating the affinities between the text and each independent object of the image. However, they ignore the connections between the objects that are semantically related. These objects may collectively determine whether the image corresponds to a text or not. To address this problem, we propose a Dual Path Recurrent Neural Network (DP-RNN) which processes images and sentences symmetrically by recurrent neural networks (RNN). In particular, given an input image-text pair, our model reorders the image objects based on the positions of their most related words in the text. In the same way as extracting the hidden features from word embeddings, the model leverages RNN to extract high-level object features from the reordered object inputs. We validate that the high-level object features contain useful joint information of semantically related objects, which benefit the retrieval task. To compute the image-text similarity, we incorporate a Multi-attention Cross Matching Model into DP-RNN. It aggregates the affinity between objects and words with cross-modality guided attention and self-attention. Our model achieves the state-of-the-art performance on Flickr30K dataset and competitive performance on MS-COCO dataset. Extensive experiments demonstrate the effectiveness of our model.

scholarly journals Efficient End-to-End Sentence-Level Lipreading with Temporal Convolutional Networks

2021 ◽  
Vol 11 (15) ◽  
pp. 6975
Author(s):  
Tao Zhang ◽  
Lun He ◽  
Xudong Li ◽  
Guoqing Feng
Keyword(s):  
Performance Improvement ◽  
State Of The Art ◽  
Error Rates ◽  
Convolutional Network ◽  
Convolutional Networks ◽  
Sentence Level ◽  
End To End ◽  
High Level ◽  
Improved Accuracy ◽  
Talking Face

Lipreading aims to recognize sentences being spoken by a talking face. In recent years, the lipreading method has achieved a high level of accuracy on large datasets and made breakthrough progress. However, lipreading is still far from being solved, and existing methods tend to have high error rates on the wild data and have the defects of disappearing training gradient and slow convergence. To overcome these problems, we proposed an efficient end-to-end sentence-level lipreading model, using an encoder based on a 3D convolutional network, ResNet50, Temporal Convolutional Network (TCN), and a CTC objective function as the decoder. More importantly, the proposed architecture incorporates TCN as a feature learner to decode feature. It can partly eliminate the defects of RNN (LSTM, GRU) gradient disappearance and insufficient performance, and this yields notable performance improvement as well as faster convergence. Experiments show that the training and convergence speed are 50% faster than the state-of-the-art method, and improved accuracy by 2.4% on the GRID dataset.

Caged-electron States and Split-electron States in Endohedral Alkali C60

2021 ◽  
Author(s):  
yifan yang ◽  
Lorenz S Cederbaum
Keyword(s):  
State Of The Art ◽  
Electronic States ◽  
Electron States ◽  
The Common ◽  
High Level

The low-lying electronic states of neutral X@C60(X=Li, Na, K, Rb) have been computed and analyzed by employing state-of-the-art high level many-electron methods. Apart from the common charge-separated states, well known...

scholarly journals France’s State of the Art Distributed Optical Fibre Sensors Qualified for the Monitoring of the French Underground Repository for High Level and Intermediate Level Long Lived Radioactive Wastes

Sensors ◽  
2017 ◽  
Vol 17 (6) ◽  
pp. 1377 ◽  
Author(s):  
Sylvie Delepine-Lesoille ◽  
Sylvain Girard ◽  
Marcel Landolt ◽  
Johan Bertrand ◽  
Isabelle Planes ◽  
...  
Keyword(s):  
Optical Fibre ◽  
State Of The Art ◽  
Radioactive Wastes ◽  
Intermediate Level ◽  
Optical Fibre Sensors ◽  
High Level

scholarly journals Sub-Diffraction Visible Imaging Using Macroscopic Fourier Ptychography and Regularization by Denoising

Sensors ◽  
2018 ◽  
Vol 18 (9) ◽  
pp. 3154 ◽  
Author(s):  
Zhixin Li ◽  
Desheng Wen ◽  
Zongxi Song ◽  
Gang Liu ◽  
Weikang Zhang ◽  
...  
Keyword(s):  
Phase Retrieval ◽  
State Of The Art ◽  
Imaging Technique ◽  
Speckle Noise ◽  
Laser Speckle ◽  
Coherent Imaging ◽  
Quantitative Metrics ◽  
Visible Imaging ◽  
Flow Algorithm ◽  
Diffraction Imaging

Imaging past the diffraction limit is of significance to an optical system. Fourier ptychography (FP) is a novel coherent imaging technique that can achieve this goal and it is widely used in microscopic imaging. Most phase retrieval algorithms for FP reconstruction are based on Gaussian measurements which cannot extend straightforwardly to long range, sub-diffraction imaging setup because of laser speckle noise corruption. In this work, a new FP reconstruction framework is proposed for macroscopic visible imaging. When compared with existing research, the reweighted amplitude flow algorithm is adopted for better signal modeling, and the Regularization by Denoising (RED) scheme is introduced to reduce the effects of speckle. Experiments demonstrate that the proposed method can obtain state-of-the-art recovered results on both visual and quantitative metrics without increasing computation cost, and it is flexible for real imaging applications.

scholarly journals Saliency Detection by Multilevel Deep Pyramid Model

2018 ◽  
Vol 2018 ◽  
pp. 1-11 ◽  
Author(s):  
Hai Wang ◽  
Lei Dai ◽  
Yingfeng Cai ◽  
Long Chen ◽  
Yong Zhang
Keyword(s):  
Background Noise ◽  
State Of The Art ◽  
Saliency Detection ◽  
Saliency Map ◽  
Multiple Features ◽  
Low Level ◽  
Pyramid Model ◽  
High Level ◽  
Different Levels ◽  
Better Than

Traditional salient object detection models are divided into several classes based on low-level features and contrast between pixels. In this paper, we propose a model based on a multilevel deep pyramid (MLDP), which involves fusing multiple features on different levels. Firstly, the MLDP uses the original image as the input for a VGG16 model to extract high-level features and form an initial saliency map. Next, the MLDP further extracts high-level features to form a saliency map based on a deep pyramid. Then, the MLDP obtains the salient map fused with superpixels by extracting low-level features. After that, the MLDP applies background noise filtering to the saliency map fused with superpixels in order to filter out the interference of background noise and form a saliency map based on the foreground. Lastly, the MLDP combines the saliency map fused with the superpixels with the saliency map based on the foreground, which results in the final saliency map. The MLDP is not limited to low-level features while it fuses multiple features and achieves good results when extracting salient targets. As can be seen in our experiment section, the MLDP is better than the other 7 state-of-the-art models across three different public saliency datasets. Therefore, the MLDP has superiority and wide applicability in extraction of salient targets.

scholarly journals A Survey of Graphical Page Object Detection with Deep Neural Networks

2021 ◽  
Author(s):  
Jwalin Bhatt ◽  
Khurram Azeem Hashmi ◽  
Muhammad Zeshan Afzal ◽  
Didier Stricker
Keyword(s):  
Deep Learning ◽  
Object Detection ◽  
Conceptual Understanding ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
Learning Approaches ◽  
Document Images ◽  
Essential Information ◽  
Current State ◽  
High Level

In any document, graphical elements like tables, figures, and formulas contain essential information. The processing and interpretation of such information require specialized algorithms. Off-the-shelf OCR components cannot process this information reliably. Therefore, an essential step in document analysis pipelines is to detect these graphical components. It leads to a high-level conceptual understanding of the documents that makes digitization of documents viable. Since the advent of deep learning, the performance of deep learning-based object detection has improved many folds. In this work, we outline and summarize the deep learning approaches for detecting graphical page objects in the document images. Therefore, we discuss the most relevant deep learning-based approaches and state-of-the-art graphical page object detection in document images. This work provides a comprehensive understanding of the current state-of-the-art and related challenges. Furthermore, we discuss leading datasets along with the quantitative evaluation. Moreover, it discusses briefly the promising directions that can be utilized for further improvements.

scholarly journals Laboratory findings in SARS-CoV-2 infections: State of the art

2020 ◽  
Vol 66 (8) ◽  
pp. 1152-1156 ◽  
Author(s):  
Miguel Augusto Martins Pereira ◽  
Isabella Carolina de Almeida Barros ◽  
Ana Luiza Veríssimo Jacob ◽  
Mayara Lopes de Assis ◽  
Salim Kanaan ◽  
...  
Keyword(s):  
State Of The Art ◽  
Case Definitions ◽  
Laboratory Findings ◽  
Laboratory Markers ◽  
Tnf Α ◽  
The Subject ◽  
Ifn Γ ◽  
High Level ◽  
Laboratory Changes ◽  
Worse Prognosis

SUMMARY OBJECTIVE The scientific community is constantly assessing the clinical and laboratory manifestations of COVID-19 in the organism. In view of the fragmentation of the large amount of information, knowledge gaps in relation to laboratory markers, and scarcity of papers in Portuguese, we propose a Literature review on laboratory changes observed in patients infected with SARS-CoV-2. METHODS Analysis of articles published between December 2019 and May 2020 on the PubMed and SciELO databases. The articles were identified, filtered, and evaluated based on the approach to the subject, language, and impact. Then, the articles were subjected to a thorough reading, in full, by 4 (four) independent researchers. RESULTS Leukopenia and lymphopenia were included in most studies, even in case definitions. Platelet count and platelet-lymphocyte ratio, at peak platelet, were associated with advanced age and longer hospital stay. Eosinopenia showed a sensitivity of 74.7% and specificity of 68.7% and, together with increased CRP, these are one of the future prospects for screening for disease. A high level of procalcitonin may indicate bacterial co-infection, leading to a worse prognosis. COVID-19 manifests itself with increased levels of many inflammatory markers such as IL-1, IL-2, IL-6, IL-7, IL-12, IP10, IFN-γ, MIP1A, MCP1, GSCF, TNF-α, and MCP1/CCL2, as well as LDH, ESR, D-dimer, CK, ALT, and AST. CONCLUSION There is a need for further studies on the new SARS-CoV-2. So far, there is no consensus regarding laboratory findings and their usefulness, whether as a prognostic marker, mortality, or disease severity.

scholarly journals Towards High-Level Intrinsic Exploration in Reinforcement Learning

2020 ◽  
Author(s):  
Nicolas Bougie ◽  
Ryutaro Ichise
Keyword(s):  
Reinforcement Learning ◽  
Time Horizon ◽  
State Of The Art ◽  
Experimental Results ◽  
Prior Work ◽  
Extrinsic Rewards ◽  
Intrinsic Reward ◽  
Long Time ◽  
End To End ◽  
High Level

Deep reinforcement learning (DRL) methods traditionally struggle with tasks where environment rewards are sparse or delayed, which entails that exploration remains one of the key challenges of DRL. Instead of solely relying on extrinsic rewards, many state-of-the-art methods use intrinsic curiosity as exploration signal. While they hold promise of better local exploration, discovering global exploration strategies is beyond the reach of current methods. We propose a novel end-to-end intrinsic reward formulation that introduces high-level exploration in reinforcement learning. Our curiosity signal is driven by a fast reward that deals with local exploration and a slow reward that incentivizes long-time horizon exploration strategies. We formulate curiosity as the error in an agent’s ability to reconstruct the observations given their contexts. Experimental results show that this high-level exploration enables our agents to outperform prior work in several Atari games.

Sign in / Sign up

Export Citation Format

Share Document