다중혈관 관상동맥 환자에서 y-문합을 이용하여 양쪽 내흉동맥만을 사용한 우회술의 조기 성적

In this work, we revisit atrous convolution, a powerful tool to explicitly adjust filter's field-of-view as well as control the resolution of feature responses computed by Deep Convolutional Neural Networks, in the application of semantic image segmentation. To handle the problem of segmenting objects at multiple scales, we design modules which employ atrous convolution in cascade or in parallel to capture multi-scale context by adopting multiple atrous rates. Furthermore, we propose to augment our previously proposed Atrous Spatial Pyramid Pooling module, which probes convolutional features at multiple scales, with image-level features encoding global context and further boost performance. We also elaborate on implementation details and share our experience on training our system. The proposed `DeepLabv3' system significantly improves over our previous DeepLab versions without DenseCRF post-processing and attains comparable performance with other state-of-art models on the PASCAL VOC 2012 semantic image segmentation benchmark.

Rethinking Atrous Convolution for Semantic Image Segmentation

“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

The PASCAL Visual Object Classes Challenge

Semantic segmentation requires both rich spatial information and sizeable receptive field. However, modern approaches usually compromise spatial resolution to achieve real-time inference speed, which leads to poor performance. In this paper, we address this dilemma with a novel Bilateral Segmentation Network (BiSeNet). We first design a Spatial Path with a small stride to preserve the spatial information and generate high-resolution features. Meanwhile, a Context Path with a fast downsampling strategy is employed to obtain sufficient receptive field. On top of the two paths, we introduce a new Feature Fusion Module to combine features efficiently. The proposed architecture makes a right balance between the speed and segmentation performance on Cityscapes, CamVid, and COCO-Stuff datasets. Specifically, for a 2048 \(\times \) 1024 input, we achieve 68.4% Mean IOU on the Cityscapes test dataset with speed of 105 FPS on one NVIDIA Titan XP card, which is significantly faster than the existing methods with comparable performance.

/pdf/bisenet-bilateral-segmentation-network-for-real-time-2pc7rh0tw1.pdf

BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation

With the rapid growth of multimedia application technologies and network technologies, especially the proliferation of Web 2.0 and digital cameras, there has been an explosion of images and videos in the Internet. For example, the volume of videos uploaded to the YouTube every minute is amounting to 48 hours by May 2011, having doubled in the last two years. Such huge video collections hold useful yet implicit and nontrivial knowledge about various domains. To manage and utilize these resources effectively, video concept detection becomes a very important subject of intensive research by a large research community (Over et al., 2008). It is an integral part of visual data mining that is automatically extracting such knowledge from the huge unstructured visual data. It aims to automatically annotate video shots or keyframes with respect to a semantic concept (Tang et al., 2012). Ranging from objects like airplane and car to scenes like urban street and sky, semantic concepts serve as good intermediate semantic features for video content indexing and understanding, and thus, spurring much research attention (Jiang et al., 2010; Naphade & Smith, 2004; Snoek et al., 2006; Zheng et al., 2008). Essentially, concept detection is a classification task, in which a binary classifier is usually learned to predict the presence of a certain concept in a video shot or keyframe (image). Traditional concept detection methods are mainly global classification: use supervised machine learning techniques, such as single Support Vector Machine (SVM), etc., over whole training dataset.

/pdf/ensemble-learning-with-lda-topic-models-for-visual-concept-3qw0z6dgoy.pdf

Ensemble Learning with LDA Topic Models for Visual Concept Detection

Detection and tracking based tubelet generation for video object detection

In our rushes exploitation task of TRECVID 2006, we propose a novel and interactive rushes video selection and editing method based on hierarchical browsing of key frames, where high level features of each key frame such as face, interview, person, crowd, building, outdoor, waterbody, and other information about redundancy and repetition are displayed at same time for helping editors to select what they really want. During high level feature extraction, we propose a multi-modal interview detection method based on audio classification and face detection, and a new repetition detection method based on spatio-temporal slice. We also detect some concepts such as crowd, building, outdoor, waterbody based on SVM classifiers. Additionally, we characterize rushes by categorizing camera motion for inferring intention. Due to the difficulty of high level feature extraction and the diversity of editor’s requirements, our hierarchical browsing method along with extracted information may be a good choice for rushes exploitation.

/pdf/trecvid-2006-rushes-exploitation-by-cas-mcg-4ogeo3s5bi.pdf

TRECVID 2006 Rushes Exploitation By CAS MCG

In our rushes exploitation task of TRECVID 2006, we propose a novel and interactive rushes video selection and editing method based on hierarchical browsing of key frames, where high level features of each key frame such as face, interview, person, crowd, building, outdoor, waterbody, and other information about redundancy and repetition are displayed at same time for helping editors to select what they really want. During high level feature extraction, we propose a multi-modal interview detection method based on audio classification and face detection, and a new repetition detection method based on spatio-temporal slice. We also detect some concepts such as crowd, building, outdoor, waterbody based on SVM classifiers. Additionally, we characterize rushes by categorization camera motion for inferring intention. Due to the difficulty of high level feature extraction and the diversity of editor’s requirements, our hierarchical browsing method along with extracted information may be a good choice for rushes exploitation.

/pdf/rushes-exploitation-2006-by-cas-mcg-28a74b1gll.pdf

Rushes Exploitation 2006 By CAS MCG

Nowadays, automatic detection of highlights for movies is indispensable for video management and browsing. In this paper, we specifically present the formulation of human attention model and its application for action movie analysis. Depending on the relationship between stimuli in both visual and audio modalities and the change of human attention, we construct the visual and audio attention sub-models respectively. By integrating both sub-models, human attention model is formulated and attention flow plot is derived to simulate the change of human attention in the time domain. Based on video structuralization and human attention analysis, we realize action concept annotation for interest-oriented navigation of viewers. The large-scale experiments demonstrate the effectiveness and generality of human attention model for action movie analysis.

Sheng Tang

Papers

Ensemble Learning with LDA Topic Models for Visual Concept Detection

Detection and tracking based tubelet generation for video object detection

TRECVID 2006 Rushes Exploitation By CAS MCG

Rushes Exploitation 2006 By CAS MCG

Human Attention Model for Action Movie Analysis