计算机视觉论文-2021-07-06

本专栏是计算机视觉方向论文收集积累，时间：2021年7月6日，来源：paper digest

欢迎关注原创公众号 【计算机视觉联盟】，回复 【西瓜书手推笔记】 可获取我的机器学习纯手推笔记！

直达笔记地址：机器学习手推笔记（GitHub地址）

1, TITLE: Imaging Dynamics Beneath Turbid Media Via Parallelized Single-photon Detection
AUTHORS: SHIQI XU et. al.
CATEGORY: physics.optics [physics.optics, cs.CV, eess.IV, q-bio.TO]
HIGHLIGHT: In this work, we take advantage of a single-photon avalanche diode (SPAD) array camera, with over one thousand detectors, to simultaneously detect speckle fluctuations at the single-photon level from 12 different phantom tissue surface locations delivered via a customized fiber bundle array.

2, TITLE: SM-SGE: A Self-Supervised Multi-Scale Skeleton Graph Encoding Framework for Person Re-Identification
AUTHORS: Haocong Rao ; Xiping Hu ; Jun Cheng ; Bin Hu
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: In this paper, we for the first time propose a Self-supervised Multi-scale Skeleton Graph Encoding (SM-SGE) framework that comprehensively models human body, component relations, and skeleton dynamics from unlabeled skeleton graphs of various scales to learn an effective skeleton representation for person Re-ID.

3, TITLE: Faster-LTN: A Neuro-symbolic, End-to-end Object Detection Architecture
AUTHORS: Francesco Manigrasso ; Filomeno Davide Miro ; Lia Morra ; Fabrizio Lamberti
CATEGORY: cs.CV [cs.CV, cs.AI, cs.LO]
HIGHLIGHT: We here propose Faster-LTN, an object detector composed of a convolutional backbone and an LTN.

4, TITLE: Part2Word: Learning Joint Embedding of Point Clouds and Text By Matching Parts to Words
AUTHORS: Chuan Tang ; Xi Yang ; Bojian Wu ; Zhizhong Han ; Yi Chang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To resolve this issue, we propose a method to learn joint embedding of point clouds and text by matching parts from shapes to words from sentences in a common space.

5, TITLE: OPA: Object Placement Assessment Dataset
AUTHORS: LIU LIU et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we focus on object placement assessment task, which verifies whether a composite image is plausible in terms of the object placement.

6, TITLE: Self-Contrastive Learning with Hard Negative Sampling for Self-supervised Point Cloud Learning
AUTHORS: Bi'an Du ; Xiang Gao ; Wei Hu ; Xin Li
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To address this issue, we propose a novel self-contrastive learning for self-supervised point cloud representation learning, aiming to capture both local geometric patterns and nonlocal semantic primitives based on the nonlocal self-similarity of point clouds.

7, TITLE: Learning from Scarce Information: Using Synthetic Data to Classify Roman Fine Ware Pottery
AUTHORS: Santos J. N��ez Jare�o ; Dani�l P. van Helden ; Evgeny M. Mirkes ; Ivan Y. Tyukin ; Penelope M. Allison
CATEGORY: cs.CV [cs.CV, 68T07, 68T45]
HIGHLIGHT: In this article we consider a version of the challenging problem of learning from datasets whose size is too limited to allow generalisation beyond the training set.

8, TITLE: Ray-ONet: Efficient 3D Reconstruction From A Single RGB Image
AUTHORS: Wenjing Bian ; Zirui Wang ; Kejie Li ; Victor Adrian Prisacariu
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We propose Ray-ONet to reconstruct detailed 3D models from monocular images efficiently.

9, TITLE: Depth Quality-Inspired Feature Manipulation for Efficient RGB-D Salient Object Detection
AUTHORS: Wenbo Zhang ; Ge-Peng Ji ; Zhuo Wang ; Keren Fu ; Qijun Zhao
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To tackle this dilemma and also inspired by the fact that depth quality is a key factor influencing the accuracy, we propose a novel depth quality-inspired feature manipulation (DQFM) process, which is efficient itself and can serve as a gating mechanism for filtering depth features to greatly boost the accuracy.

10, TITLE: Continual Contrastive Self-supervised Learning for Image Classification
AUTHORS: Zhiwei Lin ; Yongtao Wang ; Hongxiang Lin
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: In this paper, we make the first attempt to implement the continual contrastive self-supervised learning by proposing a rehearsal method, which keeps a few exemplars from the previous data.

11, TITLE: Drone Detection Using Convolutional Neural Networks
AUTHORS: Fatemeh Mahdavi ; Roozbeh Rajabi
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we detect the flying drone using a fisheye camera.

12, TITLE: Multi-View Correlation Distillation for Incremental Object Detection
AUTHORS: Dongbao Yang ; Yu Zhou ; Weiping Wang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a novel \textbf{M}ulti-\textbf{V}iew \textbf{C}orrelation \textbf{D}istillation (MVCD) based incremental object detection method, which explores the correlations in the feature space of the two-stage object detector (Faster R-CNN).

13, TITLE: Learning A Model for Inferring A Spatial Road Lane Network Graph Using Self-Supervision
AUTHORS: Robin Karlsson ; David Robert Wong ; Simon Thompson ; Kazuya Takeda
CATEGORY: cs.CV [cs.CV, cs.LG, stat.ML, I.2.10; I.2.9]
HIGHLIGHT: This paper presents the first self-supervised learning method to train a model to infer a spatially grounded lane-level road network graph based on a dense segmented representation of the road scene generated from onboard sensors.

14, TITLE: Learning Hierarchical Graph Neural Networks for Image Clustering
AUTHORS: YIFAN XING et. al.
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: We propose a hierarchical graph neural network (GNN) model that learns how to cluster a set of images into an unknown number of identities using a training set of images annotated with labels belonging to a disjoint set of identities.

15, TITLE: Scene-aware Learning Network for Radar Object Detection
AUTHORS: Zangwei Zheng ; Xiangyu Yue ; Kurt Keutzer ; Alberto Sangiovanni Vincentelli
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a scene-aware radar learning framework for accurate and robust object detection.

16, TITLE: Data Uncertainty Guided Noise-aware Preprocessing Of Fingerprints
AUTHORS: INDU JOSHI et. al.
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: Towards this, we propose a data uncertainty-based framework which enables the state-of-the-art fingerprint preprocessing models to quantify noise present in the input image and identify fingerprint regions with background noise and poor ridge clarity.

17, TITLE: Super Resolution in Human Pose Estimation: Pixelated Poses to A Resolution Result?
AUTHORS: Peter Hardy ; Srinandan Dasmahapatra ; Hansung Kim
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To address this we introduced a novel Mask-RCNN approach, utilising a segmentation area threshold to decide when to use SR during the keypoint detection step.

18, TITLE: SPI-GAN: Towards Single-Pixel Imaging Through Generative Adversarial Network
AUTHORS: Nazmul Karim ; Nazanin Rahnavard
CATEGORY: cs.CV [cs.CV, cs.LG, eess.IV, eess.SP]
HIGHLIGHT: In this paper, we propose a generative adversarial network-based reconstruction framework for single-pixel imaging, referred to as SPI-GAN.

19, TITLE: RATCHET: Medical Transformer for Chest X-ray Diagnosis and Reporting
AUTHORS: Benjamin Hou ; Georgios Kaissis ; Ronald Summers ; Bernhard Kainz
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We propose RATCHET: RAdiological Text Captioning for Human Examined Thoraces.

20, TITLE: Sensor-invariant Fingerprint ROI Segmentation Using Recurrent Adversarial Learning
AUTHORS: INDU JOSHI et. al.
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: In order to save the human effort in generating annotations required by state-of-the-art, we propose a fingerprint roi segmentation model which aligns the features of fingerprint images derived from the unseen sensor such that they are similar to the ones obtained from the fingerprints whose ground truth roi masks are available for training.

21, TITLE: Visual Time Series Forecasting: An Image-driven Approach
AUTHORS: Naftali Cohen ; Srijan Sood ; Zhen Zeng ; Tucker Balch ; Manuela Veloso
CATEGORY: cs.CV [cs.CV, cs.LG, q-fin.ST, q-fin.TR]
HIGHLIGHT: In this work, we address time-series forecasting as a computer vision task.

22, TITLE: FFR_FD: Effective and Fast Detection of DeepFakes Based on Feature Point Defects
AUTHORS: Gaojian Wang ; Qian Jiang ; Xin Jin ; Xiaohui Cui
CATEGORY: cs.CV [cs.CV, I.4; I.5]
HIGHLIGHT: Inspired by feature point detector-descriptors to extract discriminative features at the pixel level, we propose the Fused Facial Region_Feature Descriptor (FFR_FD) for effective and fast DeepFake detection.

23, TITLE: Semi-supervised Learning for Dense Object Detection in Retail Scenes
AUTHORS: Jaydeep Chauhan ; Srikrishna Varadarajan ; Muktabh Mayank Srivastava
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Hence, we propose semi-supervised learning to effectively use the large amount of unlabeled data available in the retail domain.

24, TITLE: No-Reference Quality Assessment for Colored Point Cloud and Mesh Based on Natural Scene Statistics
AUTHORS: Zicheng Zhang
CATEGORY: cs.CV [cs.CV, cs.GR, eess.IV]
HIGHLIGHT: In this paper, quality-aware features are extracted from the aspects of color and geometry directly from the 3D models.

25, TITLE: Recovering The Unbiased Scene Graphs from The Biased Ones
AUTHORS: MENG-JIUN CHIOU et. al.
CATEGORY: cs.CV [cs.CV, cs.MM]
HIGHLIGHT: In this paper we show that, due to the missing labels, SGG can be viewed as a "Learning from Positive and Unlabeled data" (PU learning) problem, where the reporting bias can be removed by recovering the unbiased probabilities from the biased ones by utilizing label frequencies, i.e., the per-class fraction of labeled, positive examples in all the positive examples.

26, TITLE: A Topological Solution to Object Segmentation and Tracking
AUTHORS: Thomas Tsao ; Doris Y. Tsao
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: We describe how to generate this surface representation from continuous visual input, and demonstrate that our approach can segment and invariantly track objects in cluttered synthetic video despite severe appearance changes, without requiring learning.

27, TITLE: A Novel Disaster Image Dataset and Characteristics Analysis Using Attention Model
AUTHORS: FAHIM FAISAL NILOY et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this research, we have carefully accumulated a relatively challenging dataset that contains images collected from various sources for three different disasters: fire, water and land.

28, TITLE: MixStyle Neural Networks for Domain Generalization and Adaptation
AUTHORS: Kaiyang Zhou ; Yongxin Yang ; Yu Qiao ; Tao Xiang
CATEGORY: cs.CV [cs.CV, cs.AI, cs.LG]
HIGHLIGHT: In this work, we address domain generalization with MixStyle, a plug-and-play, parameter-free module that is simply inserted to shallow CNN layers and requires no modification to training objectives.

29, TITLE: 6D Object Pose Estimation Using Keypoints and Part Affinity Fields
AUTHORS: Moritz Zappel ; Simon Bultmann ; Sven Behnke
CATEGORY: cs.CV [cs.CV, cs.RO]
HIGHLIGHT: In this work, we present a two-step pipeline for estimating the 6 DoF translation and orientation of known objects.

30, TITLE: Distance-based Hyperspherical Classification for Multi-source Open-Set Domain Adaptation
AUTHORS: Silvia Bucci ; Francesco Cappio Borlino ; Barbara Caputo ; Tatiana Tommasi
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work we tackle multi-source Open-Set domain adaptation by introducing HyMOS: a straightforward supervised model that exploits the power of contrastive learning and the properties of its hyperspherical feature space to correctly predict known labels on the target, while rejecting samples belonging to any unknown class.

31, TITLE: One-Cycle Pruning: Pruning ConvNets Under A Tight Training Budget
AUTHORS: Nathan Hubens ; Matei Mancas ; Bernard Gosselin ; Marius Preda ; Titus Zaharia
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: In our work, we propose to get rid of the first step of the pipeline and to combine the two other steps in a single pruning-training cycle, allowing the model to jointly learn for the optimal weights while being pruned.

32, TITLE: Deep Edge-Aware Interactive Colorization Against Color-Bleeding Effects
AUTHORS: EUNGYEUP KIM et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a novel edge-enhancing framework for the regions of interest, by utilizing user scribbles that indicate where to enhance.

33, TITLE: Efficient Vision Transformers Via Fine-Grained Manifold Distillation
AUTHORS: DING JIA et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Compared with the existing knowledge distillation approaches, we propose to excavate useful information from the teacher transformer through the relationship between images and the divided patches.

34, TITLE: Demiguise Attack: Crafting Invisible Semantic Adversarial Perturbations with Perceptual Similarity
AUTHORS: YAJIE WANG et. al.
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: To solve these problems, we propose Demiguise Attack, crafting ``unrestricted'' perturbations with Perceptual Similarity.

35, TITLE: Test-Time Personalization with A Transformer for Human Pose Estimation
AUTHORS: Miao Hao ; Yizhuo Li ; Zonglin Di ; Nitesh B. Gundavarapu ; Xiaolong Wang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We propose to personalize a human pose estimator given a set of test images of a person without using any manual annotations.

36, TITLE: Web-Scale Generic Object Detection at Microsoft Bing
AUTHORS: STEPHEN XI CHEN et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we present Generic Object Detection (GenOD), one of the largest object detection systems deployed to a web-scale general visual search engine that can detect over 900 categories for all Microsoft Bing Visual Search queries in near real-time.

37, TITLE: Exploring Data Pipelines Through The Process Lens: A Reference Model ForComputer Vision
AUTHORS: Agathe Balayn ; Bogdan Kulynych ; Seda Guerses
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We present here a preliminary result: a reference model of CV data pipelines.

38, TITLE: Conditional Identity Disentanglement for Differential Face Morph Detection
AUTHORS: Sudipta Banerjee ; Arun Ross
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We present the task of differential face morph attack detection using a conditional generative network (cGAN).

39, TITLE: Do Different Tracking Tasks Require Different Appearance Models?
AUTHORS: ZHONGDAO WANG et. al.
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: To understand to what extent this specialisation is actually necessary, in this work we present UniTrack, a unified tracking solution to address five different tasks within the same framework.

40, TITLE: What Makes for Hierarchical Vision Transformer?
AUTHORS: Yuxin Fang ; Xinggang Wang ; Rui Wu ; Jianwei Niu ; Wenyu Liu
CATEGORY: cs.CV [cs.CV, cs.AI, cs.LG]
HIGHLIGHT: Recent studies show that hierarchical Vision Transformer with interleaved non-overlapped intra window self-attention \& shifted window self-attention is able to achieve state-of-the-art performance in various visual recognition tasks and challenges CNN's dense sliding window paradigm.

41, TITLE: On Model Calibration for Long-Tailed Object Detection and Instance Segmentation
AUTHORS: TAI-YU PAN et. al.
CATEGORY: cs.CV [cs.CV, cs.AI, cs.LG]
HIGHLIGHT: In this paper, we investigate a largely overlooked approach -- post-processing calibration of confidence scores.

42, TITLE: Towards Better Adversarial Synthesis of Human Images from Text
AUTHORS: Rania Briq ; Pratika Kochar ; Juergen Gall
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This paper proposes an approach that generates multiple 3D human meshes from text.

43, TITLE: Cognitive Visual Commonsense Reasoning Using Dynamic Working Memory
AUTHORS: Xuejiao Tang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper we propose a dynamic working memory based cognitive VCR network, which stores accumulated commonsense between sentences to provide prior knowledge for inference.

44, TITLE: Bag of Instances Aggregation Boosts Self-supervised Learning
AUTHORS: HAOHANG XU et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a simple but effective distillation strategy for unsupervised learning.

45, TITLE: SSPNet: Scale Selection Pyramid Network for Tiny Person Detection from UAV Images
AUTHORS: MINGBO HONG et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a Scale Selection Pyramid network (SSPNet) for tiny person detection, which consists of three components: Context Attention Module (CAM), Scale Enhancement Module (SEM), and Scale Selection Module (SSM).

46, TITLE: Robust End-to-End Offline Chinese Handwriting Text Page Spotter with Text Kernel
AUTHORS: Zhihao Wang ; Yanwei Yu ; Yibo Wang ; Haixu Long ; Fazheng Wang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a robust end-to-end Chinese text page spotter framework.

47, TITLE: Direct Measure Matching for Crowd Counting
AUTHORS: HUI LIN et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a new measure-based counting approach to regress the predicted density maps to the scattered point-annotated ground truth directly.

48, TITLE: Similarity-Aware Fusion Network for 3D Semantic Segmentation
AUTHORS: Linqing Zhao ; Jiwen Lu ; Jie Zhou
CATEGORY: cs.CV [cs.CV, cs.RO]
HIGHLIGHT: In this paper, we propose a similarity-aware fusion network (SAFNet) to adaptively fuse 2D images and 3D point clouds for 3D semantic segmentation.

49, TITLE: Fast and Scalable Optimal Transport for Brain Tractograms
AUTHORS: Jean Feydy ; Pierre Roussillon ; Alain Trouv� ; Pietro Gori
CATEGORY: cs.CV [cs.CV, cs.AI, stat.ML]
HIGHLIGHT: We present a new multiscale algorithm for solving regularized Optimal Transport problems on the GPU, with a linear memory footprint.

50, TITLE: Improving A Neural Network Model By Explanation-guided Training for Glioma Classification Based on MRI Data
AUTHORS: Frantisek Sefcik ; Wanda Benesova
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we proposed a method for explanation-guided training that uses a Layer-wise relevance propagation (LRP) technique to force the model to focus only on the relevant part of the image.

51, TITLE: Gaze Estimation with An Ensemble of Four Architectures
AUTHORS: XIN CAI et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This paper presents a method for gaze estimation according to face images.

52, TITLE: Understanding The Security of Deepfake Detection
AUTHORS: Xiaoyu Cao ; Neil Zhenqiang Gong
CATEGORY: cs.CR [cs.CR, cs.CV, cs.LG]
HIGHLIGHT: In this work, we aim to bridge the gap.

53, TITLE: FINT: Field-aware INTeraction Neural Network For CTR Prediction
AUTHORS: Zhishan Zhao ; Sen Yang ; Guohui Liu ; Dawei Feng ; Kele Xu
CATEGORY: cs.IR [cs.IR, cs.CV]
HIGHLIGHT: In this paper, we proposed a novel prediction method, named FINT, that employs the Field-aware INTeraction layer which captures high-order feature interactions while retaining the low-order field information.

54, TITLE: On The Distribution of Penultimate Activations of Classification Networks
AUTHORS: Minkyo Seo ; Yoonho Lee ; Suha Kwak
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: This paper studies probability distributions ofpenultimate activations of classification networks.We show that, when a classification network istrained with the cross-entropy loss, its final classi-fication layer forms aGenerative-Discriminativepairwith a generative classifier based on a specificdistribution of penultimate activations.

55, TITLE: A Contextual Analysis of Multi-layer Perceptron Models in Classifying Hand-written Digits and Letters: Limited Resources
AUTHORS: Tidor-Vlad Pricope
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: Classifying hand-written digits and letters has taken a big leap with the introduction of ConvNets.

56, TITLE: Split-and-Bridge: Adaptable Class Incremental Learning Within A Single Neural Network
AUTHORS: Jong-Yeong Kim ; Dong-Wan Choi
CATEGORY: cs.LG [cs.LG, cs.AI, cs.CV]
HIGHLIGHT: In this paper, we propose a novel continual learning method, called Split-and-Bridge, which can successfully address the above problem by partially splitting a neural network into two partitions for training the new task separated from the old task and re-connecting them for learning the knowledge across tasks.

57, TITLE: CInC Flow: Characterizable Invertible 3x3 Convolution
AUTHORS: Sandeep Nagar ; Marius Dufraisse ; Girish Varma
CATEGORY: cs.LG [cs.LG, cs.AI, cs.CV]
HIGHLIGHT: We study conditions such that 3$\times$3 CNNs are invertible, allowing them to construct expressive normalizing flows.

58, TITLE: Are Standard Object Segmentation Models Sufficient for Learning Affordance Segmentation?
AUTHORS: Hugo Caselles-Dupr� ; Michael Garcia-Ortiz ; David Filliat
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: We observe that theoretically, these popular object segmentation methods should be sufficient for detecting affordances masks.

59, TITLE: GraspME -- Grasp Manifold Estimator
AUTHORS: Janik Hager ; Ruben Bauer ; Marc Toussaint ; Jim Mainprice
CATEGORY: cs.RO [cs.RO, cs.AI, cs.CV]
HIGHLIGHT: In this paper, we introduce a Grasp Manifold Estimator (GraspME) to detect grasp affordances for objects directly in 2D camera images.

60, TITLE: UCSL : A Machine Learning Expectation-Maximization Framework for Unsupervised Clustering Driven By Supervised Learning
AUTHORS: ROBIN LOUISET et. al.
CATEGORY: stat.ML [stat.ML, cs.AI, cs.CV, cs.LG]
HIGHLIGHT: In this paper, we propose a general Expectation-Maximization ensemble framework entitled UCSL (Unsupervised Clustering driven by Supervised Learning).

61, TITLE: A Study of CNN Capacity Applied to Left Venticle Segmentation in Cardiac MRI
AUTHORS: Marcelo Toledo ; Daniel Lima ; Jos� Krieger ; Marco Gutierrez
CATEGORY: eess.IV [eess.IV, cs.CV, cs.NE, 68T07, 92B20, I.2.6; I.5.1; J.3]
HIGHLIGHT: We propose a framework to answer them, by experimenting with deep and shallow versions of three U-Net families, trained from scratch in six subsets varying from 100 to 10,000 images, different network sizes, learning rates and regularization values.

62, TITLE: Custom Deep Neural Network for 3D Covid Chest CT-scan Classification
AUTHORS: Quoc Huy Trinh ; Minh Van Nguyen
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: In this paper, we propose a method that custom and combine Deep Neural Network to classify the series of 3D CT-scans chest images.

63, TITLE: VinDr-RibCXR: A Benchmark Dataset for Automatic Segmentation and Labeling of Individual Ribs on Chest X-rays
AUTHORS: Hoang C. Nguyen ; Tung T. Le ; Hieu H. Pham ; Ha Q. Nguyen
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: We introduce a new benchmark dataset, namely VinDr-RibCXR, for automatic segmentation and labeling of individual ribs from chest X-ray (CXR) scans.

64, TITLE: CT Image Harmonization for Enhancing Radiomics Studies
AUTHORS: Md Selim ; Jie Zhang ; Baowei Fei ; Guo-Qiang Zhang ; Jin Chen
CATEGORY: eess.IV [eess.IV, cs.CV, cs.LG]
HIGHLIGHT: A novel training approach, called Dynamic Window-based Training, has been developed to smoothly transform the pre-trained model to the medical imaging domain.

65, TITLE: EAR-NET: Error Attention Refining Network For Retinal Vessel Segmentation
AUTHORS: Jun Wang ; Xiaohan Yu ; Yongsheng Gao
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: To that end, we propose a novel error attention refining network (ERA-Net) that is capable of learning and predicting the potential false predictions in a two-stage manner for effective retinal vessel segmentation.

66, TITLE: WisdomNet: Prognosis of COVID-19 with Slender Prospect of False Negative Cases and Vaticinating The Probability of Maturation to ARDS Using Posteroanterior Chest X-Rays
AUTHORS: Peeyush Kumar ; Ayushe Gangal ; Sunita Kumari
CATEGORY: eess.IV [eess.IV, cs.CV, cs.LG, 68T07 (Primary), 68T10 (Secondary)]
HIGHLIGHT: In this paper, a novel neural network called WisdomNet has been proposed, for the diagnosis of COVID-19 using chest X-rays.

67, TITLE: Controllable Cardiac Synthesis Via Disentangled Anatomy Arithmetic
AUTHORS: Spyridon Thermos ; Xiao Liu ; Alison O'Neil ; Sotirios A. Tsaftaris
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: Motivated by the ability to disentangle images into spatial anatomy (tensor) factors and accompanying imaging (vector) representations, we propose a framework termed "disentangled anatomy arithmetic", in which a generative model learns to combine anatomical factors of different input images such that when they are re-entangled with the desired imaging modality (e.g. MRI), plausible new cardiac images are created with the target characteristics.

68, TITLE: COVID-Rate: An Automated Framework for Segmentation of COVID-19 Lesions from Chest CT Scans
AUTHORS: NASTARAN ENSHAEI et. al.
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: During pandemic era, however, visual assessment and quantification of COVID-19 lung lesions by expert radiologists become expensive and prone to error, which raises an urgent quest to develop practical autonomous solutions. In this context, first, the paper introduces an open access COVID-19 CT segmentation dataset containing 433 CT images from 82 patients that have been annotated by an expert radiologist.

69, TITLE: COVID-VIT: Classification of COVID-19 from CT Chest Images Based on Vision Transformer Models
AUTHORS: Xiaohong Gao ; Yu Qian ; Alice Gao
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: Two deep learning methods are studied, which are vision transformer (ViT) based on attention models and DenseNet that is built upon conventional convolutional neural network (CNN).

70, TITLE: Pulmonary Vessel Segmentation Based on Orthogonal Fused U-Net++ of Chest CT Images
AUTHORS: Hejie Cui ; Xinglong Liu ; Ning Huang
CATEGORY: eess.IV [eess.IV, cs.CV, cs.LG, 68T45, 68T07, I.2.10; J.3]
HIGHLIGHT: In this work, we present an effective framework and refinement process of pulmonary vessel segmentation from chest computed tomographic (CT) images.