计算机视觉论文-2021-06-03

本专栏是计算机视觉方向论文收集积累，时间：2021年6月3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: Digital Homotopy Relations and Digital Homology Theories
AUTHORS: P. Christopher Staecker
CATEGORY: math.AT [math.AT, cs.CV, math.GN, 55P10, 68R10]
HIGHLIGHT: In this paper we prove results relating to two homotopy relations and four homology theories developed in the topology of digital images.

2, TITLE: Refining The Bounding Volumes for Lossless Compression of Voxelized Point Clouds Geometry
AUTHORS: Emre Can Kaya ; Sebastian Schwarz ; Ioan Tabus
CATEGORY: cs.CV [cs.CV, cs.MM]
HIGHLIGHT: This paper describes a novel lossless compression method for point cloud geometry, building on a recent lossy compression method that aimed at reconstructing only the bounding volume of a point cloud.

3, TITLE: Cleaning and Structuring The Label Space of The IMet Collection 2020
AUTHORS: Vivien Nguyen ; Sunnie S. Y. Kim
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We propose an approach to cleaning and structuring the iMet 2020 labels, and discuss the implications and value of doing so.

4, TITLE: NnDetection: A Self-configuring Method for Medical Object Detection
AUTHORS: Michael Baumgartner ; Paul F. Jaeger ; Fabian Isensee ; Klaus H. Maier-Hein
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Following nnU-Net's agenda, in this work we systematize and automate the configuration process for medical object detection.

5, TITLE: Benchmarking CNN on 3D Anatomical Brain MRI: Architectures, Data Augmentation and Deep Ensemble Learning
AUTHORS: BENOIT DUFUMIER et. al.
CATEGORY: cs.CV [cs.CV, cs.LG, eess.IV]
HIGHLIGHT: We propose an extensive benchmark of recent state-of-the-art (SOTA) 3D CNN, evaluating also the benefits of data augmentation and deep ensemble learning, on both Voxel-Based Morphometry (VBM) pre-processing and quasi-raw images.

6, TITLE: The Semi-Supervised INaturalist Challenge at The FGVC8 Workshop
AUTHORS: Jong-Chyi Su ; Subhransu Maji
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: This document describes baseline results and the details of the dataset which is available here: \url{https://github.com/cvl-umass/semi-inat-2021}.

7, TITLE: Towards Robust Classification Model By Counterfactual and Invariant Data Generation
AUTHORS: Chun-Hao Chang ; George Alexandru Adam ; Anna Goldenberg
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: In this work, we focus on image classification and propose two data generation processes to reduce spuriousness.

8, TITLE: Online and Real-Time Tracking in A Surveillance Scenario
AUTHORS: OLIVER URBANN et. al.
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: This paper presents an approach for tracking in a surveillance scenario.

9, TITLE: ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection
AUTHORS: Danila Rukhovich ; Anna Vorontsova ; Anton Konushin
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we introduce the task of multi-view RGB-based 3D object detection as an end-to-end optimization problem.

10, TITLE: Rethinking Cross-modal Interaction from A Top-down Perspective for Referring Video Object Segmentation
AUTHORS: CHEN LIANG et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we instead put forward a two-stage, top-down RVOS solution.

11, TITLE: Rotation Equivariant Feature Image Pyramid Network for Object Detection in Optical Remote Sensing Imagery
AUTHORS: Pourya Shamsolmoali ; Masoumeh Zareapoor ; Jocelyn Chanussot ; Huiyu Zhou ; Jie Yang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To address these problems, we propose the rotation equivariant feature image pyramid network (REFIPN), an image pyramid network based on rotation equivariance convolution.

12, TITLE: TransMIL: Transformer Based Correlated Multiple Instance Learning for Whole Slide Image Classication
AUTHORS: ZHUCHEN SHAO et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To address this problem, we proposed a new framework, called correlated MIL, and provided a proof for convergence.

13, TITLE: A Novel Edge Detection Operator for Identifying Buildings in Augmented Reality Applications
AUTHORS: Ciprian Orhei ; Silviu Vert ; Radu Vasiu
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a novel filter operator for edge detection that aims to extract building contours or facade features better.

14, TITLE: Data Augmentation and Pre-trained Networks for Extremely Low Data Regimes Unsupervised Visual Inspection
AUTHORS: Pierre Gutierrez ; Antoine Cordier ; Tha�s Caldeira ; Th�ophile Sautory
CATEGORY: cs.CV [cs.CV, cs.AI, cs.LG, stat.ML, I.2.10; I.4.6; I.4.8; I.4.9; I.5]
HIGHLIGHT: In this work, we aim to compare three approaches based on deep pre-trained features when varying the quantity of available data in MVTec AD: KNN, Mahalanobis, and PaDiM.

15, TITLE: Towards Unified Surgical Skill Assessment
AUTHORS: DAOCHANG LIU et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, a unified multi-path framework for automatic surgical skill assessment is proposed, which takes care of multiple composing aspects of surgical skills, including surgical tool usage, intraoperative event pattern, and other skill proxies.

16, TITLE: TSI: Temporal Saliency Integration for Video Action Recognition
AUTHORS: HAISHENG SU et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a Temporal Saliency Integration (TSI) block, which mainly contains a Salient Motion Excitation (SME) module and a Cross-scale Temporal Integration (CTI) module.

17, TITLE: DFGC 2021: A DeepFake Game Competition
AUTHORS: BO PENG et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This paper presents a summary of the DFGC 2021 competition. We also release the DFGC-21 testing dataset collected from our participants to further benefit the research community.

18, TITLE: End-to-End Information Extraction By Character-Level Embedding and Multi-Stage Attentional U-Net
AUTHORS: Tuan-Anh Nguyen Dang ; Dat-Thanh Nguyen
CATEGORY: cs.CV [cs.CV, cs.LG, eess.IV]
HIGHLIGHT: In this paper, we propose a novel deep learning architecture for end-to-end information extraction on the 2D character-grid embedding of the document, namely the \textit{Multi-Stage Attentional U-Net}.

19, TITLE: Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision
AUTHORS: Xiaokang Chen ; Yuhui Yuan ; Gang Zeng ; Jingdong Wang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we study the semi-supervised semantic segmentation problem via exploring both labeled data and extra unlabeled data.

20, TITLE: Feedback Network for Mutually Boosted Stereo Image Super-Resolution and Disparity Estimation
AUTHORS: Qinyan Dai ; Juncheng Li ; Qiaosi Yi ; Faming Fang ; Guixu Zhang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: According to this motivation, we propose a Stereo Super-Resolution and Disparity Estimation Feedback Network (SSRDE-FNet), which simultaneously handles the stereo image super-resolution and disparity estimation in a unified framework and interact them with each other to further improve their performance.

21, TITLE: ICDAR 2021 Competition on On-Line Signature Verification
AUTHORS: RUBEN TOLOSANA et. al.
CATEGORY: cs.CV [cs.CV, cs.HC]
HIGHLIGHT: This paper describes the experimental framework and results of the ICDAR 2021 Competition on On-Line Signature Verification (SVC 2021).

22, TITLE: Multi-task Fully Convolutional Network for Tree Species Mapping in Dense Forests Using Small Training Hyperspectral Data
AUTHORS: LAURA ELENA CU� LA ROSA et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This work proposes a multi-task fully convolutional architecture for tree species mapping in dense forests from sparse and scarce polygon-level annotations using hyperspectral UAV-borne data.

23, TITLE: Consumer Image Quality Prediction Using Recurrent Neural Networks for Spatial Pooling
AUTHORS: Jari Korhonen ; Yicheng Su ; Junyong You
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this study, we propose an image quality model that attempts to mimic the attention mechanism of human visual system (HVS) by using a recurrent neural network (RNN) for spatial pooling of the features extracted from different spatial areas (patches) by a deep CNN-based feature extractor.

24, TITLE: Translational Symmetry-Aware Facade Parsing for 3D Building Reconstruction
AUTHORS: Hantang Liu ; Wentong Li ; Jianke Zhu
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we present a novel translational symmetry-based approach to improving the deep neural networks.

25, TITLE: Online Coreset Selection for Rehearsal-based Continual Learning
AUTHORS: Jaehong Yoon ; Divyam Madaan ; Eunho Yang ; Sung Ju Hwang
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: To tackle this problem, we propose Online Coreset Selection (OCS), a simple yet effective method that selects the most representative and informative coreset at each iteration and trains them in an online manner.

26, TITLE: Evaluating Recipes Generated from Functional Object-Oriented Network
AUTHORS: Md Sadman Sakib ; Hailey Baez ; David Paulius ; Yu Sun
CATEGORY: cs.RO [cs.RO, cs.CV]
HIGHLIGHT: Our preliminary study finds no significant difference between the recipes in Recipe1M+ and the recipes generated from FOON task trees in terms of correctness, completeness, and clarity.

27, TITLE: Deep Learning Based Full-reference and No-reference Quality Assessment Models for Compressed UGC Videos
AUTHORS: Wei Sun ; Tao Wang ; Xiongkuo Min ; Fuwang Yi ; Guangtao Zhai
CATEGORY: eess.IV [eess.IV, cs.CV, cs.MM]
HIGHLIGHT: In this paper, we propose a deep learning based video quality assessment (VQA) framework to evaluate the quality of the compressed user's generated content (UGC) videos.

28, TITLE: Prediction of The Position of External Markers Using A Recurrent Neural Network Trained With Unbiased Online Recurrent Optimization for Safe Lung Cancer Radiotherapy
AUTHORS: Michel Pohl ; Mitsuru Uesaka ; Hiroyuki Takahashi ; Kazuyuki Demachi ; Ritu Bhusal Chhatkuli
CATEGORY: eess.IV [eess.IV, cs.CV, cs.LG, cs.NE]
HIGHLIGHT: In this research, we use nine observation records of the three-dimensional position of three external markers on the chest and abdomen of healthy individuals breathing during intervals from 73s to 222s.

29, TITLE: Tips and Tricks to Improve CNN-based Chest X-ray Diagnosis: A Survey
AUTHORS: CHANGHEE HAN et. al.
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: Therefore, based on our development experience and related work, this paper thoroughly introduces tricks to improve generalization in the CXR diagnosis: how to (i) leverage additional data, (ii) augment/distillate data, (iii) regularize training, and (iv) conduct efficient segmentation.

30, TITLE: Fourier Space Losses for Efficient Perceptual Image Super-Resolution
AUTHORS: Dario Fuoli ; Luc Van Gool ; Radu Timofte
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: As large models are often not practical in real-world applications, we investigate and propose novel loss functions, to enable SR with high perceptual quality from much more efficient models.

31, TITLE: Self-supervised Lesion Change Detection and Localisation in Longitudinal Multiple Sclerosis Brain Imaging
AUTHORS: Minh-Son To ; Ian G Sarno ; Chee Chong ; Mark Jenkinson ; Gustavo Carneiro
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: Hence, we introduce a new unsupervised anomaly detection and localisation method trained exclusively with serial images that do not contain any lesion changes.