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

[신간의 별자리x] 우리/미술, 그리고 ‘슬픔의 박물관’

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

The PASCAL Visual Object Classes Challenge

Theory of fuzzy integrals and its applications

Underwater object detection (UOD) plays a significant role in aquaculture and marine environmental protection. Considering the challenges posed by low contrast and low-light conditions in underwater environments, several underwater image enhancement (UIE) methods have been proposed to improve the quality of underwater images. However, only using the enhanced images does not improve the performance of UOD, since it may unavoidably remove or alter critical patterns and details of underwater objects. In contrast, we believe that exploring the complementary information from the two domains is beneficial for UOD. The raw image preserves the natural characteristics of the scene and texture information of the objects, while the enhanced image improves the visibility of underwater objects. Based on this perspective, we propose a Gated Cross-domain Collaborative Network (GCC-Net) to address the challenges of poor visibility and low contrast in underwater environments, which comprises three dedicated components. Firstly, a real-time UIE method is employed to generate enhanced images, which can improve the visibility of objects in low-contrast areas. Secondly, a cross-domain feature interaction module is introduced to facilitate the interaction and mine complementary information between raw and enhanced image features. Thirdly, to prevent the contamination of unreliable generated results, a gated feature fusion module is proposed to adaptively control the fusion ratio of cross-domain information. Our method presents a new UOD paradigm from the perspective of cross-domain information interaction and fusion. Experimental results demonstrate that the proposed GCC-Net achieves state-of-the-art performance on four underwater datasets.

A Gated Cross-domain Collaborative Network for Underwater Object Detection

Graph Convolutional Network (GCN) has achieved high success in the skeleton-based human action recognition task by modeling the human skeleton as a graph. However, it remains a problem for GCN-based methods to learn distinctive action features from a limited number of training samples. Via taking full advantage of the body prior knowledge, this paper presents a Body Prior Guided Graph Convolutional Network (BPG-GCN) to jointly meet the demand for large-scale training data and effective model architecture. Unlike standard GCN-based methods, our BPG-GCN additionally involves both Body Prior Guided Drop (BPGD) and Body Prior Guided Attention (BPGA) modules. Specifically, the BPGD module generates diverse augmented skeleton sequences by selectively dropping spatial-temporal skeleton joints. Moreover, the BPGA module combines body structure and attention mechanism to learn distinctive action features for specific body parts. Extensive experiments on NTU-60 and NW-UCLA datasets consistently verify the effectiveness of our proposed BPG-GCN by outperforming state-of-the-art GCN-based methods. Our code is publicly available at https://github.com/519542630/BPG-GCN. 

Body Prior Guided Graph Convolutional Neural Network for Skeleton-Based Action Recognition

The noise attenuation of seismic data is an indispensable part of seismic data processing, directly impacting the following inversion and imaging. This paper focuses on two bottlenecks in the AI-based denoising method of seismic data: the destruction of structural information of seismic data and the inferior generalizability. We propose a flexible attention-CNN (FACNN) and realized the denoising work of seismic data. This paper’s main work and advantages were concentrated on the following three aspects: (i) We propose attention gates (AGs), which progressively suppressed features in irrelevant background parts and improved the denoising performance. (ii) We added a noise level map M as an additional channel, making a single CNN model expected to inherit the flexibility of handling noise models with different parameters, even spatially variant noises. (iii) We propose a mixed loss function based on MS_SSIM to improve the performance of FACNN further. Adding the noise level map can improve the network’s generalization ability, and adding the attention structure with the mixed loss function can better protect the structural information of the seismic data. The numerical tests showed that our method has better generalization and can better protect the details of seismic events.

/pdf/structure-preserving-random-noise-attenuation-method-for-13n7gxcw.pdf

Structure-Preserving Random Noise Attenuation Method for Seismic Data Based on a Flexible Attention CNN

This paper proposes a new scheme for solving real-time motion planning problems between a human arm and a robot manipulator. These problems are very important towards real-time human-robot interaction. For solving the real-time motion planning problems in dynamic interaction environments, a new method of obstacle direct mapping (ODM) is proposed. In preprocessing phase, a mapping from cells in workspace to nodes and edges in the road map of configuration space is constructed. The roadmap of C-space is constructed based on a PRM framework. In query phase, some determinate points on obstacles (human arm) surface are sampled, only the cells which contain at least one sampled point are mapped into the roadmap. Based on the points sampling on moving object's surface, translation and rotation of the object can be easily and rapidly expressed. Compared with the methods using online collision detection and A* searching technique, simulation experiments with real parameters of Kawasaki manipulator are implemented. The experimental results show that the proposed scheme is efficient and feasible for motion planning between a human arm and a robot manipulator

Real-time Motion Planning for Interaction between Human Arm and Robot Manipulator

This paper aims to conduct a comprehensive study on the facial sketch synthesis (FSS) problem. However, due to the high costs in obtaining hand-drawn sketch datasets, there lacks a complete benchmark for assessing the development of FSS algorithms over the last decade. As such, we first introduce a high-quality dataset for FSS, named FS2K, which consists of 2,104 image-sketch pairs spanning three types of sketch styles, image backgrounds, lighting conditions, skin colors, and facial attributes. FS2K differs from previous FSS datasets in difficulty, diversity, and scalability and should thus facilitate the progress of FSS research. Second, we present the largest-scale FSS study by reviewing 139 classical methods, including 24 handcrafted feature-based facial sketch synthesis approaches, 37 general neural-style transfer methods, 43 deep image-to-image translation methods, and 35 image-to-sketch approaches. Besides, we elaborate comprehensive experiments on the existing 19 cutting-edge models. Third, we present a simple baseline for FSS, named FSGAN. With only two straightforward components, i.e., facial-aware masking and style-vector expansion, FSGAN surpasses the performance of all previous state-of-the-art models on the proposed FS2K dataset by a large margin. Finally, we conclude with lessons learned over the past years and point out several unsolved challenges. Our open-source code is available at https://github.com/DengPingFan/FSGAN.

Hong Liu

Papers

A Gated Cross-domain Collaborative Network for Underwater Object Detection

Body Prior Guided Graph Convolutional Neural Network for Skeleton-Based Action Recognition

Structure-Preserving Random Noise Attenuation Method for Seismic Data Based on a Flexible Attention CNN

Real-time Motion Planning for Interaction between Human Arm and Robot Manipulator

Sketch-based Facial Synthesis: A New Challenge