计算机视觉论文-2021-07-22

本专栏是计算机视觉方向论文收集积累，时间：2021年7月22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: TumorCP: A Simple But Effective Object-Level Data Augmentation for Tumor Segmentation
AUTHORS: JIAWEI YANG et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Motivated by the recently revived "Copy-Paste" augmentation, we propose TumorCP, a simple but effective object-level data augmentation method tailored for tumor segmentation.

2, TITLE: Evidential Deep Learning for Open Set Action Recognition
AUTHORS: Wentao Bao ; Qi Yu ; Yu Kong
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a Deep Evidential Action Recognition (DEAR) method to recognize actions in an open testing set.

3, TITLE: DRIVE: Deep Reinforced Accident Anticipation with Visual Explanation
AUTHORS: Wentao Bao ; Qi Yu ; Yu Kong
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose Deep ReInforced accident anticipation with Visual Explanation, named DRIVE.

4, TITLE: Unsupervised Domain Adaptation in LiDAR Semantic Segmentation with Self-Supervision and Gated Adapters
AUTHORS: Mrigank Rochan ; Shubhra Aich ; Eduardo R. Corral-Soto ; Amir Nabatchian ; Bingbing Liu
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we focus on a less explored, but more realistic and complex problem of domain adaptation in LiDAR semantic segmentation.

5, TITLE: From Single to Multiple: Leveraging Multi-level Prediction Spaces for Video Forecasting
AUTHORS: MENGCHENG LAN et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Despite video forecasting has been a widely explored topic in recent years, the mainstream of the existing work still limits their models with a single prediction space but completely neglects the way to leverage their model with multi-prediction spaces.

6, TITLE: Few Shots Is All You Need: A Progressive Few Shot Learning Approach for Low Resource Handwriting Recognition
AUTHORS: Mohamed Ali Souibgui ; Alicia Forn�s ; Yousri Kessentini ; Be�ta Megyesi
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Thus, we propose a few-shot learning-based handwriting recognition approach that significantly reduces the human labor annotation process, requiring only few images of each alphabet symbol.

7, TITLE: Superpixel-guided Iterative Learning from Noisy Labels for Medical Image Segmentation
AUTHORS: Shuailin Li ; Zhitong Gao ; Xuming He
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To address this, we adopt a superpixel representation and develop a robust iterative learning strategy that combines noise-aware training of segmentation network and noisy label refinement, both guided by the superpixels.

8, TITLE: Characterization Multimodal Connectivity of Brain Network By Hypergraph GAN for Alzheimer's Disease Analysis
AUTHORS: JUNREN PAN et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To overcome this problem, a novel Hypergraph Generative Adversarial Networks(HGGAN) is proposed in this paper, which utilizes Interactive Hyperedge Neurons module (IHEN) and Optimal Hypergraph Homomorphism algorithm(OHGH) to generate multimodal connectivity of Brain Network from rs-fMRI combination with DTI.

9, TITLE: Registration of 3D Point Sets Using Correntropy Similarity Matrix
AUTHORS: Ashutosh Singandhupe ; Hung La ; Trung Dung Ngo ; Van Ho
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we propose a variant of the Standard ICP algorithm, where we introduce a Correntropy Relationship Matrix in the computation of rotation and translation component which attempts to solve the large rotation and translation problem between \textit{Source} and \textit{Target} point sets.

10, TITLE: Fabrication-Aware Reverse Engineering for Carpentry
AUTHORS: James Noeckel ; Haisen Zhao ; Brian Curless ; Adriana Schulz
CATEGORY: cs.CV [cs.CV, cs.GR]
HIGHLIGHT: We propose a novel method to generate fabrication blueprints from images of carpentered items.

11, TITLE: CycleMLP: A MLP-like Architecture for Dense Prediction
AUTHORS: Shoufa Chen ; Enze Xie ; Chongjian Ge ; Ding Liang ; Ping Luo
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This paper presents a simple MLP-like architecture, CycleMLP, which is a versatile backbone for visual recognition and dense predictions, unlike modern MLP architectures, e.g., MLP-Mixer, ResMLP, and gMLP, whose architectures are correlated to image size and thus are infeasible in object detection and segmentation.

12, TITLE: S4T: Source-free Domain Adaptation for Semantic Segmentation Via Self-supervised Selective Self-training
AUTHORS: Viraj Prabhu ; Shivam Khare ; Deeksha Kartik ; Judy Hoffman
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: We propose Self-Supervised Selective Self-Training (S4T), a source-free adaptation algorithm that first uses the model's pixel-level predictive consistency across diverse views of each target image along with model confidence to classify pixel predictions as either reliable or unreliable.

13, TITLE: Weighted Intersection Over Union (wIoU): A New Evaluation Metric for Image Segmentation
AUTHORS: Yeong-Jun Cho
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a novel evaluation metric for performance evaluation of semantic segmentation.

14, TITLE: Window Detection In Facade Imagery: A Deep Learning Approach Using Mask R-CNN
AUTHORS: Nils Nordmark ; Mola Ayenew
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: This article investigates the usage of the mask R-CNN framework to be used for window detection of facade imagery input.

15, TITLE: CogME: A Novel Evaluation Metric for Video Understanding Intelligence
AUTHORS: MINJUNG SHIN et. al.
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: To examine the suitability of a VideoQA dataset for validating video understanding intelligence, we evaluated the baseline model of the DramaQA dataset by applying CogME.

16, TITLE: Deep Iterative 2D/3D Registration
AUTHORS: Srikrishna Jaganathan ; Jian Wang ; Anja Borsdorf ; Karthik Shetty ; Andreas Maier
CATEGORY: cs.CV [cs.CV, cs.LG, eess.IV]
HIGHLIGHT: In this work, we propose a novel Deep Learning driven 2D/3D registration framework that can be used end-to-end for iterative registration tasks without relying on any further refinement step.

17, TITLE: Anomaly Detection Via Self-organizing Map
AUTHORS: NING LI et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a novel unsupervised anomaly detection approach based on Self-organizing Map (SOM).

18, TITLE: DRDF: Determining The Importance of Different Multimodal Information with Dual-Router Dynamic Framework
AUTHORS: HAIWEN HONG et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In multimodal tasks, we find that the importance of text and image modal information is different for different input cases, and for this motivation, we propose a high-performance and highly general Dual-Router Dynamic Framework (DRDF), consisting of Dual-Router, MWF-Layer, experts and expert fusion unit.

19, TITLE: An Overview of Mixing Augmentation Methods and Augmentation Strategies
AUTHORS: Dominik Lewy ; Jacek Ma?dziuk
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This review mainly covers the methods published in the materials of top-tier conferences and in leading journals in the years 2017-2021.

20, TITLE: Multimodal Representations Learning and Adversarial Hypergraph Fusion for Early Alzheimer's Disease Prediction
AUTHORS: QIANKUN ZUO et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To solve these problems, we proposed a novel multimodal representation learning and adversarial hypergraph fusion (MRL-AHF) framework for Alzheimer's disease diagnosis using complete trimodal images.

21, TITLE: Structure-Aware Long Short-Term Memory Network for 3D Cephalometric Landmark Detection
AUTHORS: RUNNAN CHEN et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we propose a novel Structure-Aware Long Short-Term Memory framework (SA-LSTM) for efficient and accurate 3D landmark detection.

22, TITLE: You Better Look Twice: A New Perspective for Designing Accurate Detectors with Reduced Computations
AUTHORS: ALEXANDRA DANA et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work we introduce BLT-net, a new low-computation two-stage object detection architecture designed to process images with a significant amount of background and objects of variate scales.

23, TITLE: CGANs with Auxiliary Discriminative Classifier
AUTHORS: Liang Hou ; Qi Cao ; Huawei Shen ; Xueqi Cheng
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: Conditional generative models aim to learn the underlying joint distribution of data and labels, and thus realize conditional generation.

24, TITLE: Memorization in Deep Neural Networks: Does The Loss Function Matter?
AUTHORS: Deep Patel ; P. S. Sastry
CATEGORY: cs.LG [cs.LG, cs.CV, stat.ML]
HIGHLIGHT: We investigate whether the choice of the loss function can affect this memorization.

25, TITLE: Objective Video Quality Metrics Application to Video Codecs Comparisons: Choosing The Best for Subjective Quality Estimation
AUTHORS: ANASTASIA ANTSIFEROVA et. al.
CATEGORY: cs.MM [cs.MM, cs.CV]
HIGHLIGHT: In this paper, a fundamental comparison of various versions of generally accepted metrics is carried out to find the most relevant and recommended versions of video quality metrics to be used in codecs comparisons.

26, TITLE: Modality-aware Mutual Learning for Multi-modal Medical Image Segmentation
AUTHORS: YAO ZHANG et. al.
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: In this paper, we focus on improving automated liver tumor segmentation by integrating multi-modal CT images.

27, TITLE: 3D Fluorescence Microscopy Data Synthesis for Segmentation and Benchmarking
AUTHORS: Dennis Eschweiler ; Malte Rethwisch ; Mareike Jarchow ; Simon Koppers ; Johannes Stegmaier
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: In this work, we propose how conditional generative adversarial networks can be utilized to generate realistic image data for 3D fluorescence microscopy from annotation masks of 3D cellular structures.

28, TITLE: HistoCartography: A Toolkit for Graph Analytics in Digital Pathology
AUTHORS: Guillaume Jaume ; Pushpak Pati ; Valentin Anklin ; Antonio Foncubierta ; Maria Gabrani
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: In this work, we aim to alleviate these issues by developing HistoCartography, a standardized python API with necessary preprocessing, machine learning and explainability tools to facilitate graph-analytics in computational pathology.

29, TITLE: High-Resolution Pelvic MRI Reconstruction Using A Generative Adversarial Network with Attention and Cyclic Loss
AUTHORS: Guangyuan Li ; Jun Lv ; Xiangrong Tong ; Chengyan Wang ; Guang Yang
CATEGORY: eess.IV [eess.IV, cs.CV, cs.LG]
HIGHLIGHT: Therefore, we proposed a novel super-resolution method that uses a generative adversarial network (GAN) with cyclic loss and attention mechanism to generate high-resolution MR images from low-resolution MR images by a factor of 2.

30, TITLE: 3D-StyleGAN: A Style-Based Generative Adversarial Network for Generative Modeling of Three-Dimensional Medical Images
AUTHORS: SUNGMIN HONG et. al.
CATEGORY: eess.IV [eess.IV, cs.CV, cs.LG, 68T07 (Primary) 68T01 (Secondary), I.2; I.4]
HIGHLIGHT: In this paper, we extend the state-of-the-art StyleGAN2 model, which natively works with two-dimensional images, to enable 3D image synthesis.

31, TITLE: A Point Cloud Generative Model Via Tree-Structured Graph Convolutions for 3D Brain Shape Reconstruction
AUTHORS: Bowen Hu ; Baiying Lei ; Yanyan Shen ; Yong Liu ; Shuqiang Wang
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: In this paper, a general generative adversarial network (GAN) architecture based on graph convolutional networks is proposed to reconstruct the 3D point clouds (PCs) of brains by using one single 2D image, thus relieving the limitation of acquiring 3D shape data during surgery.

32, TITLE: Towards Lower-Dose PET Using Physics-Based Uncertainty-Aware Multimodal Learning with Robustness to Out-of-Distribution Data
AUTHORS: Viswanath P. Sudarshan ; Uddeshya Upadhyay ; Gary F. Egan ; Zhaolin Chen ; Suyash P. Awate
CATEGORY: eess.IV [eess.IV, cs.CE, cs.CV, cs.LG]
HIGHLIGHT: Radiation exposure in positron emission tomography (PET) imaging limits its usage in the studies of radiation-sensitive populations, e.g., pregnant women, children, and adults that require longitudinal imaging.