Early and Late Fusion of Temporal Information for Classification of Surgical Actions in Laparoscopic Gynecology

2018 ◽  
Author(s):  
Stefan Petscharnig ◽  
Klaus Schoffmann ◽  
Jenny Benois-Pineau ◽  
Souad Chaabouni ◽  
Jorg Keckstein
Keyword(s):  
Temporal Information ◽  
Late Fusion

A cross-linguistic investigation of the combinational possibilities of the ‘for X time’ adverbial with different aspectual verb classes

2012 ◽  
Vol 12 (2) ◽  
pp. 211-231
Author(s):  
Athina Sioupi
Keyword(s):  
Temporal Information ◽  
Perfective Aspect ◽  
Imperfective Aspect ◽  
Verb Classes ◽  
Change Of State ◽  
Viewpoint Aspect

The paper observes that the Vendler classification is not sufficient as a classification of verbs, since it cannot explain why some telic verbs, such as change of state (COS) verbs and degree achievements (DAs) appear with the durational adverbial (d-adverbial) ‘for X time’ in Greek, in English and in German, while some atelics like semelfactives appear with the frame adverbial (f-adverbial) se X ora (‘in X time’) in Greek. In the spirit of Iatridou et al. (2003) it is proposed that the d-adverbial ‘for X time’ tests not only for (a)telicity but also for (im)perfectivity. It also argues that the two d-adverbials in Greek ja X ora and epi X ora (‘for X time’) are to be found with different grammatical (viewpoint) aspect: the former with perfective aspect and the latter with imperfective aspect. This is due to the fact that the ja X ora gives not only durative temporal information but also a lexical aspectual one, while the epi X ora gives only a durative temporal.

scholarly journals Multi-View Attention-based Late Fusion (MVALF) CADx system for breast cancer using deep learning

2020 ◽  
Vol 29 (1) ◽  
pp. 55-78
Author(s):  
Hina Iftikhar ◽  
Hasan Khan ◽  
Basit Raza ◽  
Ahmad Shahir
Keyword(s):  
Breast Cancer ◽  
Feature Fusion ◽  
Predictive Ability ◽  
Late Fusion ◽  
Fusion Strategy ◽  
Single View ◽  
Normal Mass ◽  
Issue Attention ◽  
Aided Diagnosis

Breast cancer is a leading cause of death among women. Early detection can significantly reduce the mortality rate among women and improve their prognosis. Mammography is the first line procedure for early diagnosis. In the early era, conventional Computer-Aided Diagnosis (CADx) systems for breast lesion diagnosis were based on just single view information. The last decade evidence the use of two views mammogram: Medio-Lateral Oblique (MLO) and Cranio-Caudal (CC) view for the CADx systems. Most recent studies show the effectiveness of four views of mammogram to train CADx system with feature fusion strategy for classification task. In this paper, we proposed an end-to-end Multi-View Attention-based Late Fusion (MVALF) CADx system that fused the obtained predictions of four view models, which is trained for each view separately. These separate models have different predictive ability for each class. The appropriate fusion of multi-view models can achieve better diagnosis performance. So, it is necessary to assign the proper weights to the multi-view classification models. To resolve this issue, attention-based weighting mechanism is adopted to assign the proper weights to trained models for fusion strategy. The proposed methodology is used for the classification of mammogram into normal, mass, calcification, malignant masses and benign masses. The publicly available datasets CBIS-DDSM and mini-MIAS are used for the experimentation. The results show that our proposed system achieved 0.996 AUC for normal vs. abnormal, 0.922 for mass vs. calcification and 0.896 for malignant vs. benign masses. Superior results are seen for the classification of malignant vs benign masses with our proposed approach, which is higher than the results using single view, two views and four views early fusion-based systems. The overall results of each level show the potential of multi-view late fusion with transfer learning in the diagnosis of breast cancer.

scholarly journals A Low-Compexity Deep Learning FrameworkFor Acoustic Scene Classification

2021 ◽  
Author(s):  
Lam Pham ◽  
Hieu Tang ◽  
Anahid Jalal ◽  
Alexander Schindler ◽  
Ross King
Keyword(s):  
Audio Signal ◽  
Low Complexity ◽  
Scene Classification ◽  
Late Fusion ◽  
Classification Result ◽  
Urban Scenes ◽  
Model Compression ◽  
Front End ◽  
Learning Frameworks

In this paper, we presents a low-complexitydeep learning frameworks for acoustic scene classification(ASC). The proposed framework can be separated into threemain steps: Front-end spectrogram extraction, back-endclassification, and late fusion of predicted probabilities.First, we use Mel filter, Gammatone filter and ConstantQ Transfrom (CQT) to transform raw audio signal intospectrograms, where both frequency and temporal featuresare presented. Three spectrograms are then fed into threeindividual back-end convolutional neural networks (CNNs),classifying into ten urban scenes. Finally, a late fusion ofthree predicted probabilities obtained from three CNNs isconducted to achieve the final classification result. To reducethe complexity of our proposed CNN network, we applytwo model compression techniques: model restriction anddecomposed convolution. Our extensive experiments, whichare conducted on DCASE 2021 (IEEE AASP Challenge onDetection and Classification of Acoustic Scenes and Events)Task 1A development dataset, achieve a low-complexity CNNbased framework with 128 KB trainable parameters andthe best classification accuracy of 66.7%, improving DCASEbaseline by 19.0%.

scholarly journals SI-STSAR-7: A Large SAR Images Dataset with Spatial and Temporal Information for Classification of Winter Sea Ice in Hudson Bay

2021 ◽  
Vol 14 (1) ◽  
pp. 168
Author(s):  
Wei Song ◽  
Wen Gao ◽  
Qi He ◽  
Antonio Liotta ◽  
Weiqi Guo
Keyword(s):  
Remote Sensing ◽  
Deep Learning ◽  
Sea Ice ◽  
Incidence Angle ◽  
Temporal Information ◽  
Hudson Bay ◽  
Sar Images ◽  
Learning Methods ◽  
Image Patches

Remote sensing satellites have been broadly applied to sea ice monitoring. The substantial increase in satellite imagery provides a large amount of data support for deep learning methods in the sea ice classification field. However, there is a lack of public remote sensing datasets to facilitate sea ice classification with spatial and temporal information and to benchmark the deep learning methods. In this paper, we provide a labeled large sea ice dataset derived from time-series sentinel-1 SAR images, dubbed SI-STSAR-7, and a validated dataset construction method for sea ice classification research. The SI-STSAR-7 dataset includes seven different sea ice types corresponding to different sea ice development stages in Hudson Bay during winter, and its samples are time sequences of SAR image patches in order to embody the differences of backscattering intensity and textures between different sea ice types, as well as the change of sea ice with time. We construct the dataset by first performing noise reduction and mitigation of incidence angle dependence on SAR images, and then producing data samples and labeling them based on our proposed sample-producing principles and the weekly regional ice charts provided by Canadian Ice Service. Three baseline classification methods are developed on SI-STSAR-7 to establish benchmarks, which are evaluated with accuracy and kappa coefficient. The sample-producing principles are verified through experiments. Based on the experimental results, sea ice classification can be implemented well on SI-STSAR-7.

Sub-pixel classification of anthropogenic features using deep-learning on Sentinel-2 data

2020 ◽  
Author(s):  
Nikolaos Ioannis Bountos ◽  
Melanie Brandmeier ◽  
Mark Günter
Keyword(s):  
Deep Learning ◽  
Spectral Band ◽  
Large Field ◽  
Total Output ◽  
High Temporal Resolution ◽  
Late Fusion ◽  
Pixel Classification ◽  
Fusion Approach ◽  
Sentinel 2

<p>Urban landscapes are characterized as the fastest changing areas on the planet. However, regularly monitoring of larger areas it is not feasible using UAVs or costly air borne data. In these situations, satellite data with a high temporal resolution and large field of view are more appropriate but suffer from the lower spatial resolution (deca-meters). In the present study we show that by using freely available Sentinel-2 data from the Copernicus program, we can extract anthropogenic features such as roads, railways and building footprints that are partly or completely on a sub-pixel level in this kind of data. Additionally, we propose a new metric for the evaluation of our methods on the sub-pixel objects. This metric measures the performance of the detection of an object while penalizing the false positive classification. Given that our training samples contain one class, we define two thresholds that represent the lower bound of accuracy for the object to be classified and the background. We thus avoid a good score in occasions where we classify correctly our object, but a wide area of the background has been included in our prediction. We investigate the performance of different deep-learning architectures for sub-pixel classification of the different infrastructure elements based on Sentinel-2 multispectral data and the labels derived from the UAV data. Our study area is located in the Rhone valley in Switzerland where very high-resolution UAV data was available from the University of Applied Sciences. Highly accurate labels for the respective classes were digitized in ArcGIS Pro and used as ground-truth for the Sentinel data. We trained different deep learning models based on state-of-the-art architectures for semantic segmentation, such as DeepLab and U-Net. Our approach focuses on the exploitation of the multi spectral information to increase the performance of the RGB channels. For that purpose, we make use of the NIR and SWIR 10m and 20m bands of the Sentinel-2 data. We investigate early and late fusion approaches and the behavior and contribution of each multi spectral band to improve the performance in comparison to only using the RGB channels. In the early fusion approach, we stack nine (RGB, NIR, SWIR) Sentinel-2 bands together, pass them from two convolutions followed by batch normalization and relu layers and then feed the tiles to DeepLab. In the late fusion approach, we create a CNN with two branches with the first branch processing the RGB channels and the second branch the NIR/SWIR bands. We use modified DeepLab layers for the two branches and then concatenate the outputs into a total output of 512 feature maps. We then reduce the dimensionality of the result into the finaloutput equal to the number of classes. The dimension reduction step happens in two convolution layers. We experiment on different settings for all of the mentioned architectures. In the best-case scenario, we achieve 89% overall accuracy. Moreover, we measure 60% building accuracy, streets accuracy 60%, railway accuracy 73%, river accuracy 92% and background accuracy 94%.</p>

Note on the spectral classification of carbon stars in the photographic infrared region

1966 ◽  
Vol 24 ◽  
pp. 21-23
Author(s):  
Y. Fujita
Keyword(s):  
Infrared Region ◽  
Spectral Classification ◽  
Carbon Stars

We have investigated the spectrograms (dispersion: 8Å/mm) in the photographic infrared region fromλ7500 toλ9000 of some carbon stars obtained by the coudé spectrograph of the 74-inch reflector attached to the Okayama Astrophysical Observatory. The names of the stars investigated are listed in Table 1.

Sign in / Sign up

Export Citation Format

Share Document