计算机视觉论文-2021-05-31

本专栏是计算机视觉方向论文收集积累，时间：2021年5月31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: Type III Solar Radio Burst Detection and Classification: A Deep Learning Approach
AUTHORS: Jeremiah Scully ; Ronan Flynn ; Eoin Carley ; Peter Gallagher ; Mark Daly
CATEGORY: astro-ph.SR [astro-ph.SR, astro-ph.IM, cs.CV]
HIGHLIGHT: In this research, we are introducing a methodology named You Only Look Once v2 (YOLOv2) for solar radio burst classification.

2, TITLE: On Hamilton-Jacobi PDEs and Image Denoising Models with Certain Non-additive Noise
AUTHORS: J�r�me Darbon ; Tingwei Meng ; Elena Resmerita
CATEGORY: math.OC [math.OC, cs.CV]
HIGHLIGHT: In this work, we address certain non-additive noise models and show that they are also related to Hamilton-Jacobi PDEs.

3, TITLE: Learning Relation Alignment for Calibrated Cross-modal Retrieval
AUTHORS: SHUHUAI REN et. al.
CATEGORY: cs.CL [cs.CL, cs.CV]
HIGHLIGHT: In response, we present Inter-modal Alignment on Intra-modal Self-attentions (IAIS), a regularized training method to optimize the ISD and calibrate intra-modal self-attentions from the two modalities mutually via inter-modal alignment.

4, TITLE: AutoSampling: Search for Effective Data Sampling Schedules
AUTHORS: MING SUN et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose an AutoSampling method to automatically learn sampling schedules for model training, which consists of the multi-exploitation step aiming for optimal local sampling schedules and the exploration step for the ideal sampling distribution.

5, TITLE: Learning Dynamic Graph Representation of Brain Connectome with Spatio-Temporal Attention
AUTHORS: Byung-Hoon Kim ; Jong Chul Ye ; Jae-Jin Kim
CATEGORY: cs.CV [cs.CV, cs.LG, q-bio.NC]
HIGHLIGHT: Here, we propose STAGIN, a method for learning dynamic graph representation of the brain connectome with spatio-temporal attention.

6, TITLE: The Wits Intelligent Teaching System: Detecting Student Engagement During Lectures Using Convolutional Neural Networks
AUTHORS: Richard Klein ; Turgay Celik
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: The deep learning approach provides satisfactory results on a challenging, real-world dataset with significant occlusion, lighting and resolution constraints.

7, TITLE: Empirical Study of Multi-Task Hourglass Model for Semantic Segmentation Task
AUTHORS: Darwin Saire ; Ad�n Ram�rez Rivera
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we propose to use a multi-task approach by complementing the semantic segmentation task with edge detection, semantic contour, and distance transform tasks.

8, TITLE: Inertial Sensor Data To Image Encoding For Human Action Recognition
AUTHORS: Zeeshan Ahmad ; Naimul Khan
CATEGORY: cs.CV [cs.CV, cs.HC, cs.LG, eess.SP]
HIGHLIGHT: To get the maximum advantage of CNN model for Human Action Recognition (HAR) using inertial sensor data, in this paper, we use 4 types of spatial domain methods for transforming inertial sensor data to activity images, which are then utilized in a novel fusion framework.

9, TITLE: Unsupervised Domain Adaption of Object Detectors: A Survey
AUTHORS: Poojan Oza ; Vishwanath A. Sindagi ; Vibashan VS ; Vishal M. Patel
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: In this paper, we provide a brief introduction to the domain adaptation problem for object detection and present an overview of various methods proposed to date for addressing this problem.

10, TITLE: Learning to Stylize Novel Views
AUTHORS: Hsin-Ping Huang ; Hung-Yu Tseng ; Saurabh Saini ; Maneesh Singh ; Ming-Hsuan Yang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We propose a point cloud-based method for consistent 3D scene stylization.

11, TITLE: Boosting Monocular Depth Estimation Models to High-Resolution Via Content-Adaptive Multi-Resolution Merging
AUTHORS: S. Mahdi H. Miangoleh ; Sebastian Dille ; Long Mai ; Sylvain Paris ; Ya??z Aksoy
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We present a double estimation method that improves the whole-image depth estimation and a patch selection method that adds local details to the final result.

12, TITLE: Chromatic and Spatial Analysis of One-pixel Attacks Against An Image Classifier
AUTHORS: Janne Alatalo ; Joni Korpihalkola ; Tuomo Sipola ; Tero Kokkonen
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: In this research, the successful and unsuccessful attacks are studied in more detail to illustrate the working mechanisms of a one-pixel attack.

13, TITLE: FastRIFE: Optimization of Real-Time Intermediate Flow Estimation for Video Frame Interpolation
AUTHORS: Malwina Kubas ; Grzegorz Sarwas
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This paper proposes the FastRIFE algorithm, which is some speed improvement of the RIFE (Real-Time Intermediate Flow Estimation) model.

14, TITLE: DeepTag: A General Framework for Fiducial Marker Design and Detection
AUTHORS: Zhuming Zhang ; Yongtao Hu ; Guoxing Yu ; Jingwen Dai
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: To improve the flexibility and robustness in various applications, we propose a general deep learning based framework, DeepTag, for fiducial marker design and detection. To validate DeepTag and existing methods, beside existing datasets, we further collect a new large and challenging dataset where markers are placed in different view distances and angles.

15, TITLE: Demotivate Adversarial Defense in Remote Sensing
AUTHORS: Adrien Chan-Hon-Tong ; Gaston Lenczner ; Aurelien Plyer
CATEGORY: cs.CV [cs.CV, eess.IV]
HIGHLIGHT: In this work, we study both adversarial retraining and adversarial regularization as adversarial defenses to this purpose.

16, TITLE: Training of SSD(Single Shot Detector) for Facial Detection Using Nvidia Jetson Nano
AUTHORS: Saif Ur Rehman ; Muhammad Rashid Razzaq ; Muhammad Hadi Hussian
CATEGORY: cs.CV [cs.CV, cs.AI, cs.DC, eess.IV]
HIGHLIGHT: In this project, we have used the computer vision algorithm SSD (Single Shot detector) computer vision algorithm and trained this algorithm from the dataset which consists of 139 Pictures.

17, TITLE: What Is Considered Complete for Visual Recognition?
AUTHORS: Lingxi Xie ; Xiaopeng Zhang ; Longhui Wei ; Jianlong Chang ; Qi Tian
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Based on the observation, we advocate for a new type of pre-training task named learning-by-compression.

18, TITLE: EDEN: Deep Feature Distribution Pooling for Saimaa Ringed Seals Pattern Matching
AUTHORS: Ilja Chelak ; Ekaterina Nepovinnykh ; Tuomas Eerola ; Heikki Kalviainen ; Igor Belykh
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, pelage pattern matching is considered to solve the individual re-identification of the Saimaa ringed seals.

19, TITLE: NViSII: A Scriptable Tool for Photorealistic Image Generation
AUTHORS: NATHAN MORRICAL et. al.
CATEGORY: cs.CV [cs.CV, cs.RO]
HIGHLIGHT: In this work, we discuss design goals, architecture, and performance.

20, TITLE: Revitalizing Optimization for 3D Human Pose and Shape Estimation: A Sparse Constrained Formulation
AUTHORS: TAOSHA FAN et. al.
CATEGORY: cs.CV [cs.CV, cs.RO]
HIGHLIGHT: Based on our optimization method, we present a real-time motion capture framework that estimates 3D human poses and shapes from a single image at over 30 FPS.

21, TITLE: Learning Uncertainty For Safety-Oriented Semantic Segmentation In Autonomous Driving
AUTHORS: Victor Besnier ; David Picard ; Alexandre Briot
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we show how uncertainty estimation can be leveraged to enable safety critical image segmentation in autonomous driving, by triggering a fallback behavior if a target accuracy cannot be guaranteed.

22, TITLE: Semi-supervised Anatomical Landmark Detection Via Shape-regulated Self-training
AUTHORS: RUNNAN CHEN et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a model-agnostic shape-regulated self-training framework for semi-supervised landmark detection by fully considering the global shape constraint.

23, TITLE: 2nd Place Solution for IJCAI-PRICAI 2020 3D AI Challenge: 3D Object Reconstruction from A Single Image
AUTHORS: Yichen Cao ; Yufei Wei ; Shichao Liu ; Lin Xu
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: In this paper, we present our solution for the {\it IJCAI--PRICAI--20 3D AI Challenge: 3D Object Reconstruction from A Single Image}.

24, TITLE: MODISSA: A Multipurpose Platform for The Prototypical Realization of Vehicle-related Applications Using Optical Sensors
AUTHORS: BJ�RN BORGMANN et. al.
CATEGORY: cs.CV [cs.CV, cs.SY, eess.IV, eess.SY]
HIGHLIGHT: We present the current state of development of the sensor-equipped car MODISSA, with which Fraunhofer IOSB realizes a configurable experimental platform for hardware evaluation and software development in the context of mobile mapping and vehicle-related safety and protection.

25, TITLE: ResT: An Efficient Transformer for Visual Recognition
AUTHORS: Qinglong Zhang ; Yubin Yang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This paper presents an efficient multi-scale vision Transformer, called ResT, that capably served as a general-purpose backbone for image recognition.

26, TITLE: Improving Facial Attribute Recognition By Group and Graph Learning
AUTHORS: Zhenghao Chen ; Shuhang Gu ; Feng Zhu ; Jing Xu ; Rui Zhao
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we are concerned with two types of correlations that are spatial and non-spatial relationships.

27, TITLE: Focus on Local: Detecting Lane Marker from Bottom Up Via Key Point
AUTHORS: Zhan Qu ; Huan Jin ; Yang Zhou ; Zhen Yang ; Wei Zhang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We propose a novel lane marker detection solution, FOLOLane, that focuses on modeling local patterns and achieving prediction of global structures in a bottom-up manner.

28, TITLE: Using Convolutional Neural Networks for Relative Pose Estimation of A Non-Cooperative Spacecraft with Thermal Infrared Imagery
AUTHORS: Maxwell Hogan ; Duarte Rondao ; Nabil Aouf ; Olivier Dubois-Matra
CATEGORY: cs.CV [cs.CV, cs.AI, cs.LG, I.2.10]
HIGHLIGHT: Often, thermal information on the target is not available a priori; this paper therefore proposes using visible images to train networks.

29, TITLE: Iris Liveness Detection Using A Cascade of Dedicated Deep Learning Networks
AUTHORS: Juan Tapia ; Sebastian Gonzalez ; Christoph Busch
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This paper proposes a serial architecture based on a MobileNetV2 modification, trained from scratch to classify bona fide iris images versus presentation attack images.

30, TITLE: The Herbarium 2021 Half-Earth Challenge Dataset
AUTHORS: Riccardo de Lutio ; Damon Little ; Barbara Ambrose ; Serge Belongie
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We present the Herbarium Half-Earth dataset, the largest and most diverse dataset of herbarium specimens to date for automatic taxon recognition.

31, TITLE: Linguistic Structures As Weak Supervision for Visual Scene Graph Generation
AUTHORS: Keren Ye ; Adriana Kovashka
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we explore how linguistic structures in captions can benefit scene graph generation.

32, TITLE: GuideMe: A Mobile Application Based on Global Positioning System and Object Recognition Towards A Smart Tourist Guide
AUTHORS: Wadii Boulila ; Anmar Abuhamdah ; Maha Driss ; Slim Kammoun ; Jawad Ahmad
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a mobile application that helps the user find the appropriate doaas for a given holy place in an easy and intuitive manner.

33, TITLE: New Image Captioning Encoder Via Semantic Visual Feature Matching for Heavy Rain Images
AUTHORS: Chang-Hwan Son ; Pung-Hwi Ye
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To address practical issues, this study introduces a new encoder for captioning heavy rain images.

34, TITLE: Recent Advances and Clinical Applications of Deep Learning in Medical Image Analysis
AUTHORS: XUXIN CHEN et. al.
CATEGORY: cs.CV [cs.CV, eess.IV]
HIGHLIGHT: In this paper, we reviewed and summarized more than 200 recently published papers to provide a comprehensive overview of applying deep learning methods in various medical image analysis tasks.

35, TITLE: Recursive Contour Saliency Blending Network for Accurate Salient Object Detection
AUTHORS: Yi Ke Yun ; Chun Wei Tan ; Takahiro Tsubono
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we designed a network for better edge quality in salient object detection.

36, TITLE: Deception Detection in Videos Using The Facial Action Coding System
AUTHORS: Hammad Ud Din Ahmed ; Usama Ijaz Bajwa ; Fan Zhang ; Muhammad Waqas Anwar
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In our approach, we extract facial action units using the facial action coding system which we use as parameters for training a deep learning model.

37, TITLE: FReTAL: Generalizing Deepfake Detection Using Knowledge Distillation and Representation Learning
AUTHORS: Minha Kim ; Shahroz Tariq ; Simon S. Woo
CATEGORY: cs.CV [cs.CV, I.4.9; I.5.4]
HIGHLIGHT: In this work, we employ the Representation Learning (ReL) and Knowledge Distillation (KD) paradigms to introduce a transfer learning-based Feature Representation Transfer Adaptation Learning (FReTAL) method.

38, TITLE: Training With Data Dependent Dynamic Learning Rates
AUTHORS: Shreyas Saxena ; Nidhi Vyas ; Dennis DeCoste
CATEGORY: cs.LG [cs.LG, cs.AI, cs.CV]
HIGHLIGHT: In this work, we relax this assumption and propose an optimization framework which accounts for difference in loss function characteristics across instances.

39, TITLE: Self-supervised Detransformation Autoencoder for Representation Learning in Open Set Recognition
AUTHORS: Jingyun Jia ; Philip K. Chan
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: In this paper, we propose a self-supervision method, Detransformation Autoencoder (DTAE), for the OSR problem.

40, TITLE: One-shot Learning with Absolute Generalization
AUTHORS: Hao Su
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: In this paper, we propose a set of definitions to explain what kind of datasets can support one-shot learning and propose the concept "absolute generalization".

41, TITLE: Geometric Deep Learning and Equivariant Neural Networks
AUTHORS: JAN E. GERKEN et. al.
CATEGORY: cs.LG [cs.LG, cs.CV, hep-th]
HIGHLIGHT: We survey the mathematical foundations of geometric deep learning, focusing on group equivariant and gauge equivariant neural networks.

42, TITLE: Classification and Uncertainty Quantification of Corrupted Data Using Semi-Supervised Autoencoders
AUTHORS: Philipp Joppich ; Sebastian Dorn ; Oliver De Candido ; Wolfgang Utschick ; Jakob Knollm�ller
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: We present a probabilistic approach to classify strongly corrupted data and quantify uncertainty, despite the model only having been trained with uncorrupted data.

43, TITLE: A Systematic Review of Transfer Learning Based Approaches for Diabetic Retinopathy Detection
AUTHORS: Burcu Oltu ; B�?ra K�bra Karaca ; Hamit Erdem ; Atilla �zg�r
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: Accordingly, the present study as a review focuses on DNN and Transfer Learning based applications of DR detection considering 38 publications between 2015 and 2020.

44, TITLE: PTNet: A High-Resolution Infant MRI Synthesizer Based on Transformer
AUTHORS: XUZHE ZHANG et. al.
CATEGORY: eess.IV [eess.IV, cs.CV, cs.LG]
HIGHLIGHT: In this study, we introduced a novel MRI synthesis framework - Pyramid Transformer Net (PTNet).

45, TITLE: ECG Heart-beat Classification Using Multimodal Image Fusion
AUTHORS: Zeeshan Ahmad ; Anika Tabassum ; Naimul Khan ; Ling Guan
CATEGORY: eess.SP [eess.SP, cs.CV, cs.LG]
HIGHLIGHT: In this paper, we present a novel Image Fusion Model (IFM) for ECG heart-beat classification to overcome the weaknesses of existing machine learning techniques that rely either on manual feature extraction or direct utilization of 1D raw ECG signal.