本专栏是计算机视觉方向论文收集积累，时间：2021年7月19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: Optical Inspection of The Silicon Micro-strip Sensors for The CBM Experiment Employing Artificial Intelligence
AUTHORS: E. Lavrik ; M. Shiroya ; H. R. Schmidt ; A. Toia ; J. M. Heuser
CATEGORY: physics.ins-det [physics.ins-det, cs.CV, hep-ex]
HIGHLIGHT: In this manuscript, we present the analysis of various sensor surface defects.
2, TITLE: Progressive Deep Video Dehazing Without Explicit Alignment Estimation
AUTHORS: Runde Li
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a progressive alignment and restoration method for video dehazing.
3, TITLE: Contrastive Predictive Coding for Anomaly Detection
AUTHORS: Puck de Haan ; Sindy L�we
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: In this paper, we close this gap by making use of the Contrastive Predictive Coding model (arXiv:1807.03748).
4, TITLE: A Theoretical Analysis of Granulometry-based Roughness Measures on Cartosat DEMs
AUTHORS: Nagajothi Kannan ; Sravan Danda ; Aditya Challa ; Daya Sagar B S
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this article, we revisit the roughness measure on DEM data adapted from multiscale granulometries in mathematical morphology, namely multiscale directional granulometric index (MDGI).
5, TITLE: Efficient Automated U-Net Based Tree Crown Delineation Using UAV Multi-spectral Imagery on Embedded Devices
AUTHORS: Kostas Blekos ; Stavros Nousias ; Aris S Lalos
CATEGORY: cs.CV [cs.CV, eess.IV]
HIGHLIGHT: In this work, we propose a U-Net based tree delineation method, which is effectively trained using multi-spectral imagery but can then delineate single-spectrum images.
6, TITLE: Conditional Directed Graph Convolution for 3D Human Pose Estimation
AUTHORS: Wenbo Hu ; Changgong Zhang ; Fangneng Zhan ; Lei Zhang ; Tien-Tsin Wong
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose to represent the human skeleton as a directed graph with the joints as nodes and bones as edges that are directed from parent joints to child joints.
7, TITLE: Real-Time Violence Detection Using CNN-LSTM
AUTHORS: Mann Patel
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: To address the butterfly effects impact in our setting, I made a unique model and a theorized system to handle the issue utilizing deep learning.
8, TITLE: Real-Time Face Recognition System for Remote Employee Tracking
AUTHORS: Mohammad Sabik Irbaz ; MD Abdullah Al Nasim ; Refat E Ferdous
CATEGORY: cs.CV [cs.CV, cs.LG, eess.IV]
HIGHLIGHT: In this paper, we discuss in brief the system we have been experimenting with and the pros and cons of the system.
9, TITLE: Multi-Level Contrastive Learning for Few-Shot Problems
AUTHORS: Qing Chen ; Jian Zhang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Most current applications of contrastive learning benefit only a single representation from the last layer of an encoder.In this paper, we propose a multi-level contrasitive learning approach which applies contrastive losses at different layers of an encoder to learn multiple representations from the encoder.
10, TITLE: Controlled AutoEncoders to Generate Faces from Voices
AUTHORS: Hao Liang ; Lulan Yu ; Guikang Xu ; Bhiksha Raj ; Rita Singh
CATEGORY: cs.CV [cs.CV, cs.LG, cs.SD, eess.AS, eess.IV]
HIGHLIGHT: With this in perspective, we propose a framework to morph a target face in response to a given voice in a way that facial features are implicitly guided by learned voice-face correlation in this paper.
11, TITLE: Rectifying The Shortcut Learning of Background: Shared Object Concentration for Few-Shot Image Recognition
AUTHORS: XU LUO et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we observe that image background serves as a source of domain-specific knowledge, which is a shortcut for models to learn in the source dataset, but is harmful when adapting to brand-new classes.
12, TITLE: Deep Learning to Ternary Hash Codes By Continuation
AUTHORS: Mingrui Chen ; Weiyu Li ; Weizhi Lu
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To obtain better ternary codes, we for the first time propose to jointly learn the features with the codes by appending a smoothed function to the networks.
13, TITLE: A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets
AUTHORS: Muhammed Muzammul ; Xi Li
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This survey paper specially analyzed computer vision-based object detection challenges and solutions by different techniques.
14, TITLE: All The Attention You Need: Global-local, Spatial-channel Attention for Image Retrieval
AUTHORS: Chull Hwan Song ; Hye Joo Han ; Yannis Avrithis
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We present global-local attention module (GLAM), which is attached at the end of a backbone network and incorporates all four forms of attention: local and global, spatial and channel.
15, TITLE: An Energy-Efficient Edge Computing Paradigm for Convolution-based Image Upsampling
AUTHORS: Ian Colbert ; Ken Kreutz-Delgado ; Srinjoy Das
CATEGORY: cs.CV [cs.CV, cs.AR, cs.DC, cs.LG]
HIGHLIGHT: These kernel transformations, intended as a one-time cost when shifting from training to inference, enable a systems designer to use each algorithm in their optimal context by preserving the image fidelity learned when training in the cloud while minimizing data transfer penalties during inference at the edge.
16, TITLE: Is Attention to Bounding Boxes All You Need for Pedestrian Action Prediction?
AUTHORS: Lina Achaji ; Julien Moreau ; Thibault Fouqueray ; Francois Aioun ; Francois Charpillet
CATEGORY: cs.CV [cs.CV, cs.LG, cs.RO]
HIGHLIGHT: In this paper, we present a framework based on multiple variations of the Transformer models to reason attentively about the dynamic evolution of the pedestrians' past trajectory and predict its future actions of crossing or not crossing the street. In addition, we introduced a large-size simulated dataset (CP2A) using CARLA for action prediction.
17, TITLE: Pose Normalization of Indoor Mapping Datasets Partially Compliant to The Manhattan World Assumption
AUTHORS: Patrick H�bner ; Martin Weinmann ; Sven Wursthorn ; Stefan Hinz
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we present a novel pose normalization method for indoor mapping point clouds and triangle meshes that is robust against large fractions of the indoor mapping geometries deviating from an ideal Manhattan World structure.
18, TITLE: Unsupervised 3D Human Mesh Recovery from Noisy Point Clouds
AUTHORS: Xinxin Zuo ; Sen Wang ; Minglun Gong ; Li Cheng
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This paper presents a novel unsupervised approach to reconstruct human shape and pose from noisy point cloud.
19, TITLE: Representation Consolidation for Training Expert Students
AUTHORS: ZHIZHONG LI et. al.
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: Traditionally, distillation has been used to train a student model to emulate the input/output functionality of a teacher.
20, TITLE: CCVS: Context-aware Controllable Video Synthesis
AUTHORS: Guillaume Le Moing ; Jean Ponce ; Cordelia Schmid
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This presentation introduces a self-supervised learning approach to the synthesis of new video clips from old ones, with several new key elements for improved spatial resolution and realism: It conditions the synthesis process on contextual information for temporal continuity and ancillary information for fine control.
21, TITLE: Painting Style-Aware Manga Colorization Based on Generative Adversarial Networks
AUTHORS: YUGO SHIMIZU et. al.
CATEGORY: cs.CV [cs.CV, eess.IV]
HIGHLIGHT: To realize consistent colorization, we propose here a semi-automatic colorization method based on generative adversarial networks (GAN); the method learns the painting style of a specific comic from small amount of training data.
22, TITLE: DANCE: DAta-Network Co-optimization for Efficient Segmentation Model Training and Inference
AUTHORS: CHAOJIAN LI et. al.
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: To this end, we propose DANCE, general automated DAta-Network Co-optimization for Efficient segmentation model training and inference.
23, TITLE: Align Before Fuse: Vision and Language Representation Learning with Momentum Distillation
AUTHORS: JUNNAN LI et. al.
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: In this paper, we introduce a contrastive loss to ALign the image and text representations BEfore Fusing (ALBEF) them through cross-modal attention, which enables more grounded vision and language representation learning.
24, TITLE: CutDepth:Edge-aware Data Augmentation in Depth Estimation
AUTHORS: Yasunori Ishii ; Takayoshi Yamashita
CATEGORY: cs.CV [cs.CV, cs.AI, cs.LG]
HIGHLIGHT: In this paper, we propose a data augmentation method, called CutDepth.
25, TITLE: Multiple Instance Learning with Auxiliary Task Weighting for Multiple Myeloma Classification
AUTHORS: TALHA QAISER et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To aid radiological reading, we propose an auxiliary task-based multiple instance learning approach (ATMIL) for MM classification with the ability to localize sites of disease.
26, TITLE: Semi-supervised 3D Hand-Object Pose Estimation Via Pose Dictionary Learning
AUTHORS: Zida Cheng ; Siheng Chen ; Ya Zhang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To tackle the problem of data collection, we propose a semi-supervised 3D hand-object pose estimation method with two key techniques: pose dictionary learning and an object-oriented coordinate system.
27, TITLE: A Comparison of Deep Learning Classification Methods on Small-scale Image Data Set: from Converlutional Neural Networks to Visual Transformers
AUTHORS: PENG ZHAO et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Through the comparison of experimental results, the recommended deep learning model is given according to the model application environment.
28, TITLE: OdoViz: A 3D Odometry Visualization and Processing Tool
AUTHORS: Saravanabalagi Ramachandran ; John McDonald
CATEGORY: cs.CV [cs.CV, cs.RO]
HIGHLIGHT: This significantly reduces the effort required in creating subsets of data from existing datasets for machine learning tasks.
29, TITLE: Self-Supervised Learning Framework for Remote Heart Rate Estimation Using Spatiotemporal Augmentation
AUTHORS: Hao Wang ; Euijoon Ahn ; Jinman Kim
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To solve this problem, we present a novel 3D self-supervised spatiotemporal learning framework for remote HR estimation on facial videos.
30, TITLE: Attention-based Vehicle Self-Localization with HD Feature Maps
AUTHORS: Nico Engel ; Vasileios Belagiannis ; Klaus Dietmayer
CATEGORY: cs.CV [cs.CV, cs.RO]
HIGHLIGHT: We present a vehicle self-localization method using point-based deep neural networks.
31, TITLE: A Survey on Bias in Visual Datasets
AUTHORS: Simone Fabbrizzi ; Symeon Papadopoulos ; Eirini Ntoutsi ; Ioannis Kompatsiaris
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To this end, we propose a checklist that can be used to spot different types of bias during visual dataset collection.
32, TITLE: Unsupervised Discovery of Object Radiance Fields
AUTHORS: Hong-Xing Yu ; Leonidas J. Guibas ; Jiajun Wu
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: In this paper, we propose unsupervised discovery of Object Radiance Fields (uORF), integrating recent progresses in neural 3D scene representations and rendering with deep inference networks for unsupervised 3D scene decomposition.
33, TITLE: Panoptic Segmentation of Satellite Image Time Series with Convolutional Temporal Attention Networks
AUTHORS: Vivien Sainte Fare Garnot ; Loic Landrieu
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we present the first end-to-end, single-stage method for panoptic segmentation of Satellite Image Time Series (SITS).
34, TITLE: Wasserstein Distances, Geodesics and Barycenters of Merge Trees
AUTHORS: Mathieu Pont ; Jules Vidal ; Julie Delon ; Julien Tierny
CATEGORY: cs.GR [cs.GR, cs.CG, cs.CV, eess.IV]
HIGHLIGHT: This paper presents a unified computational framework for the estimation of distances, geodesics and barycenters of merge trees.
35, TITLE: In-Bed Person Monitoring Using Thermal Infrared Sensors
AUTHORS: Elias Josse ; Amanda Nerborg ; Kevin Hernandez-Diaz ; Fernando Alonso-Fernandez
CATEGORY: cs.HC [cs.HC, cs.CV, eess.SP]
HIGHLIGHT: Technological solutions involving cameras can contribute to safety, comfort and efficient emergency responses, but they are invasive of privacy.
36, TITLE: DoReMi: First Glance at A Universal OMR Dataset
AUTHORS: Elona Shatri ; Gy�rgy Fazekas
CATEGORY: cs.IR [cs.IR, cs.CV, cs.MM]
HIGHLIGHT: This paper provides a first look at DoReMi, an OMR dataset that addresses these challenges, and a baseline object detection model to assess its utility.
37, TITLE: Graph Representation Learning for Road Type Classification
AUTHORS: Zahra Gharaee ; Shreyas Kowshik ; Oliver Stromann ; Michael Felsberg
CATEGORY: cs.LG [cs.LG, cs.AI, cs.CV]
HIGHLIGHT: We present a novel learning-based approach to graph representations of road networks employing state-of-the-art graph convolutional neural networks.
38, TITLE: Measuring and Explaining The Inter-Cluster Reliability of Multidimensional Projections
AUTHORS: Hyeon Jeon ; Hyung-Kwon Ko ; Jaemin Jo ; Youngtaek Kim ; Jinwook Seo
CATEGORY: cs.LG [cs.LG, cs.CV, cs.HC]
HIGHLIGHT: We propose Steadiness and Cohesiveness, two novel metrics to measure the inter-cluster reliability of multidimensional projection (MDP), specifically how well the inter-cluster structures are preserved between the original high-dimensional space and the low-dimensional projection space.
39, TITLE: Probabilistic Appearance-Invariant Topometric Localization with New Place Awareness
AUTHORS: Ming Xu ; Tobias Fischer ; Niko S�nderhauf ; Michael Milford
CATEGORY: cs.RO [cs.RO, cs.CV]
HIGHLIGHT: To address these shortcomings, we present a new probabilistic topometric localization system which incorporates full 3-dof odometry into the motion model and furthermore, adds an "off-map" state within the state-estimation framework, allowing query traverses which feature significant route detours from the reference map to be successfully localized.
40, TITLE: Exploiting Generative Self-supervised Learning for The Assessment of Biological Images with Lack of Annotations: A COVID-19 Case-study
AUTHORS: Alessio Mascolini ; Dario Cardamone ; Francesco Ponzio ; Santa Di Cataldo ; Elisa Ficarra
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: In this paper we present GAN-DL, a Discriminator Learner based on the StyleGAN2 architecture, which we employ for self-supervised image representation learning in the case of fluorescent biological images.
41, TITLE: Unpaired Cross-modality Educed Distillation (CMEDL) Applied to CT Lung Tumor Segmentation
AUTHORS: Jue Jiang ; Andreas Rimner ; Joseph O. Deasy ; Harini Veeraraghavan
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: Our contribution eliminates two requirements of distillation methods: (i) paired image sets by using an image to image (I2I) translation and (ii) pre-training of the teacher network with a large training set by using concurrent training of all networks.
42, TITLE: Depth Estimation from Monocular Images and Sparse Radar Using Deep Ordinal Regression Network
AUTHORS: Chen-Chou Lo ; Patrick Vandewalle
CATEGORY: eess.IV [eess.IV, cs.AI, cs.CV, eess.SP]
HIGHLIGHT: We integrate sparse radar data into a monocular depth estimation model and introduce a novel preprocessing method for reducing the sparseness and limited field of view provided by radar.
43, TITLE: NeXtQSM -- A Complete Deep Learning Pipeline for Data-consistent Quantitative Susceptibility Mapping Trained with Hybrid Data
AUTHORS: FRANCESCO COGNOLATO et. al.
CATEGORY: eess.IV [eess.IV, cs.CV, cs.LG]
HIGHLIGHT: Here we aim to overcome these limitations and developed a framework to solve the QSM processing steps jointly.
44, TITLE: Joint Semi-supervised 3D Super-Resolution and Segmentation with Mixed Adversarial Gaussian Domain Adaptation
AUTHORS: NICOLO SAVIOLI et. al.
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: Here we propose a semi-supervised multi-task generative adversarial network (Gemini-GAN) that performs joint super-resolution of the images and their labels using a ground truth of high resolution 3D cines and segmentations, while an unsupervised variational adversarial mixture autoencoder (V-AMA) is used for continuous domain adaptation.
45, TITLE: Lightness Modulated Deep Inverse Tone Mapping
AUTHORS: Kanglin Liu ; Gaofeng Cao ; Jiang Duan ; Guoping Qiu
CATEGORY: eess.IV [eess.IV, cs.CV, cs.MM]
HIGHLIGHT: In this paper, we present a deep learning based iTM method that takes advantage of the feature extraction and mapping power of deep convolutional neural networks (CNNs) and uses a lightness prior to modulate the CNN to better exploit observations in the surrounding areas of the over-exposed regions to enhance the quality of HDR image reconstruction.
