Vo Thi Hong Tuyet

This chapter aims to provide an overview of deep learning methods for video classification and tagging. Videos contain not only spatial but also temporal information, making it more complex than static image data. Firstly, the chapter will introduce the basic concepts of video classification, video tagging, single-label classification, multi-label classification and challenges of video data. Secondly, the main part of the chapter will review major deep learning architectures used for video understanding, including CNN-based methods, CNN-RNN models, 3D CNNs, two-stream networks, SlowFast networks, video transformers, and self-supervised learning and discuss multi-modal learning methods that combine visual, audio, textual, and metadata features for more effective video tagging. Finally, the following evaluation metrics such as accuracy, precision, recall, F1-score, etc. will be introduced in this chapter. Moreover, practical use cases in education, surveillance, intelligent transportation systems, social media, and digital content management will be discussed.

Colon polyp segmentation is important in the early detection of colorectal cancer. Advances in artificial intelligence and computer‐aided diagnosis systems have dramatically improved the capabilities of colonoscopy by enhancing the segmentation and detection of colonic polyps. Accurate segmentation is essential, as it allows for the differentiation of polyps from surrounding tissues and aids in assessing their potential malignancy. This paper proposed a method for segmenting colon polyp images by improving the Recalling U‐Net model based on the original U‐Net and U‐Net++ models. The new model aims to take full advantage of multiscale features by introducing full‐scale skip connections, combining low‐level details with high‐level semantics from full‐scale feature maps, but with fewer parameters. The model can develop deep supervision to learn hierarchical representations from full‐scale aggregated feature maps in order to optimize the combined loss function to enhance organ boundaries. Specifically, the proposed method improves four major changes compared to Recalling U‐Net: separate down sampling process, improved encoding path, upgraded bridge and improved recalling block layers. These changes help improve the learning ability and efficiency of the proposed method, resulting in more accurate segmentation results. The proposed method is tested on the Kvasir‐SEG, CVC‐ClinicDB and CVC‐ColonDB datasets with evaluation metrics such as Dice coefficient, Intersection over Union and accuracy. Experimental results presented that the proposed method achieved an accuracy of 98.992%, 97.628%, and 97.695% on these datasets, respectively, and outperforms the results of several recent methods on the same dataset.

Neural networks overcome drawbacks of vision tasks by becoming convolutional in a wide range of layers. The salient map is affected by multilevels of strong pixels (superpixels) in global images and that is dependent on the hard threshold for their dividing. Deep neural networks have been established for saliency prediction of segmentation because the feature extraction must be suited to the input data. The convolutional neural network (CNN) also endures conflict between spatial pattern and a likeness of salient objects. Semantic segmentation is one of the approaches to continue classification based on these features. Therefore, upgrading the extraction process can be of use in saliency. In this work, we optimize DeepLab based on an atrous convolutional and a conditional random field (CRF) with a bottleneck in the semantic segmentation method, which serves for classification. The backbone of deep feature extraction is atrous convolution and the bottleneck based on CRF for hybrid saliency in the encoder-decoder system. The classification results are compared with some approaches for saliency prediction of recent deeper methods in an ISIC 2017 dataset. The results give better values not only for saliency prediction for segmentation but also for training and testing for classification.

Summary: Image diagnosis is a very significant medical specialty. Thereby, the doctor will see the form and function of the structure inside the body. The recorded images will be an important basis to help doctors find the disease and treatment more effectively. However, the quality of medical images is a vital factor. Improving the quality of medical images and object contour are the major challenges, because each tiny detail of medical images can contain much information. Object contour in good medical image quality is hard work and it is more difficult in low‐quality medical image. The organs in the image are not clear, which is difficult for the doctor to distinguish the border of the organs in the image. In this paper, we proposed a method for object contour based on improving region growing in bandelet domain in low‐quality medical images. The method includes two stages: increasing the quality of medical image in bandelet domain and object contour by improving region growing combined with context border condition in medical images in the first stage. The result of the proposed method is better than the other methods.