All kinds of original system download: download Windows, MacOS, Linux original system mirror in MSDN

2023-01-05   ES  

This column is the collection and accumulation of computer visual direction papers. Time: June 30, 2021, Source: Paper Digest

Welcome to follow the original public account[Computer Visual Alliance], Reply[Watermelon book hand push notes]to get my machine learning pure hand push notes!

straight note address:Machine learning hand push notes(github address)

1, TITLE: Cosmic-CoNN: A Cosmic Ray Detection Deep-Learning Framework, Dataset, and Toolkit
AUTHORS: Chengyuan Xu ; Curtis McCully ; Boning Dong ; D. Andrew Howell ; Pradeep Sen
CATEGORY: astro-ph.IM [astro-ph.IM, cs.CV]
HIGHLIGHT: In this work, we present Cosmic-CoNN, a deep-learning framework designed to produce generic CR-detection models. We build a large, diverse ground-based CR dataset leveraging thousands of images from the Las Cumbres Observatory global telescope network to produce a generic CR-detection model which achieves a 99.91% true-positive detection rate and maintains over 96.40% true-positive rates on unseen data from Gemini GMOS-N/S, with a false-positive rate of 0.01%.

2, TITLE: Hate Speech Detection Using Static BERT Embeddings
AUTHORS: Gaurav Rajput ; Narinder Singh punn ; Sanjay Kumar Sonbhadra ; Sonali Agarwal
CATEGORY: cs.CL [cs.CL, cs.CV]
HIGHLIGHT: In this paper, we use ETHOS hate speech detection dataset and analyze the performance of hate speech detection classifier by replacing or integrating the word embeddings (fastText (FT), GloVe (GV) or FT + GV) with static BERT embeddings (BE).

3, TITLE: SRF-Net: Selective Receptive Field Network for Anchor-Free Temporal Action Detection
AUTHORS: Ranyu Ning ; Can Zhang ; Yuexian Zou
HIGHLIGHT: In this study, we explore to remove the requirement of pre-defined anchors for TAD methods.

4, TITLE: Inconspicuous Adversarial Patches for Fooling Image Recognition Systems on Mobile Devices
AUTHORS: Tao Bai ; Jinqi Luo ; Jun Zhao
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: To tackle these challenges, we propose an approach to generate inconspicuous adversarial patches with one single image.

5, TITLE: Detecting Cattle and Elk in The Wild from Space
AUTHORS: Caleb Robinson ; Anthony Ortiz ; Lacey Hughey ; Jared A. Stabach ; Juan M. Lavista Ferres
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: We extend this line of work by proposing a baseline method, CowNet, that simultaneously estimates the number of animals in an image (counts), as well as predicts their location at a pixel level (localizes).

6, TITLE: Domain-Class Correlation Decomposition for Generalizable Person Re-Identification
AUTHORS: Kaiwen Yang ; Xinmei Tian
HIGHLIGHT: Inspired by casual inference, we propose to perform interventions to the domain factor $d$, aiming to decompose the domain-class correlation.

7, TITLE: A Systematic Evaluation of Domain Adaptation in Facial Expression Recognition
AUTHORS: Yan San Kong ; Varsha Suresh ; Jonathan Soh ; Desmond C. Ong
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: In this paper, we provide a systematic evaluation of domain adaptation in facial expression recognition.

8, TITLE: O2O-Afford: Annotation-Free Large-Scale Object-Object Affordance Learning
AUTHORS: Kaichun Mo ; Yuzhe Qin ; Fanbo Xiang ; Hao Su ; Leonidas Guibas
CATEGORY: cs.CV [cs.CV, cs.RO]
HIGHLIGHT: In this paper, we propose a unified affordance learning framework to learn object-object interaction for various tasks.

9, TITLE: Cells Are Actors: Social Network Analysis with Classical ML for SOTA Histology Image Classification
AUTHORS: Neda Zamanitajeddin ; Mostafa Jahanifar ; Nasir Rajpoot
CATEGORY: cs.CV [cs.CV, cs.SI]
HIGHLIGHT: To tackle these challenges, we propose to use a statistical network analysis method to describe the complex structure of the tissue micro-environment by modelling nuclei and their connections as a network.

10, TITLE: Improving Transferability of Adversarial Patches on Face Recognition with Generative Models
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: In this paper, we evaluate the robustness of face recognition models using adversarial patches based on transferability, where the attacker has limited accessibility to the target models.

11, TITLE: Multiple Graph Learning for Scalable Multi-view Clustering
AUTHORS: Tianyu Jiang ; Quanxue Gao
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: To well exploit complementary information and tackle the scalability issue plaguing graph-based multi-view clustering, we propose an efficient multiple graph learning model via a small number of anchor points and tensor Schatten p-norm minimization.

12, TITLE: Open-Set Representation Learning Through Combinatorial Embedding
AUTHORS: Geeho Kim ; Bohyung Han
CATEGORY: cs.CV [cs.CV, cs.AI, cs.LG]
HIGHLIGHT: To address this challenging task, we propose a combinatorial learning approach, which naturally clusters the examples in unseen classes using the compositional knowledge given by multiple supervised meta-classifiers on heterogeneous label spaces.

13, TITLE: GuidedMix-Net: Learning to Improve Pseudo Masks Using Labeled Images As Reference
AUTHORS: Peng Tu ; Yawen Huang ; Rongrong Ji ; Feng Zheng ; Ling Shao
HIGHLIGHT: In this paper, we propose a novel method for semi-supervised semantic segmentation named GuidedMix-Net, by leveraging labeled information to guide the learning of unlabeled instances.

14, TITLE: Towards Understanding The Effectiveness of Attention Mechanism
AUTHORS: Xiang Ye ; Zihang He ; Heng Wang ; Yong Li
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: In this paper, we find that there is only a weak consistency between the attention weights of features and their importance.

15, TITLE: An End-to-End Autofocus Camera for Iris on The Move
AUTHORS: Leyuan Wang ; Kunbo Zhang ; Yunlong Wang ; Zhenan Sun
HIGHLIGHT: In this paper, we introduced a novel rapid autofocus camera for active refocusing ofthe iris area ofthe moving objects using a focus-tunable lens.

16, TITLE: Segmentation with Multiple Acceptable Annotations: A Case Study of Myocardial Segmentation in Contrast Echocardiography
HIGHLIGHT: In this paper, we address the first problem by proposing a new extended Dice to effectively evaluate the segmentation performance when multiple accepted ground truth is available.

17, TITLE: An Efficient Cervical Whole Slide Image Analysis Framework Based on Multi-scale Semantic and Spatial Features Using Deep Learning
AUTHORS: Ziquan Wei ; Shenghua Cheng ; Xiuli Liu ; Shaoqun Zeng
HIGHLIGHT: This study designs a novel inline connection network (InCNet) by enriching the multi-scale connectivity to build the lightweight model named You Only Look Cytopathology Once (YOLCO) with the additional supervision of spatial information.

18, TITLE: Tackling Catastrophic Forgetting and Background Shift in Continual Semantic Segmentation
AUTHORS: Arthur Douillard ; Yifu Chen ; Arnaud Dapogny ; Matthieu Cord
HIGHLIGHT: In this paper, we propose Local POD, a multi-scale pooling distillation scheme that preserves long- and short-range spatial relationships at feature level.

19, TITLE: EVPropNet: Detecting Drones By Finding Propellers For Mid-Air Landing And Following
CATEGORY: cs.CV [cs.CV, cs.AI, cs.RO]
HIGHLIGHT: In this paper, we model the geometry of a propeller and use it to generate simulated events which are used to train a deep neural network called EVPropNet to detect propellers from the data of an event camera.

20, TITLE: MFR 2021: Masked Face Recognition Competition
HIGHLIGHT: This paper presents a summary of the Masked Face Recognition Competitions (MFR) held within the 2021 International Joint Conference on Biometrics (IJCB 2021).

21, TITLE: SDL: New Data Generation Tools for Full-level Annotated Document Layout
AUTHORS: Son Nguyen Truong
HIGHLIGHT: We present a novel data generation tool for document processing.

22, TITLE: On-board Volcanic Eruption Detection Through CNNs and Satellite Multispectral Imagery
AUTHORS: Maria Pia Del Rosso ; Alessandro Sebastianelli ; Dario Spiller ; Pierre Philippe Mathieu ; Silvia Liberata Ullo
CATEGORY: cs.CV [cs.CV, cs.LG, eess.IV]
HIGHLIGHT: In this context, the authors of this work aim to propose a first prototype and a study of feasibility for an AI model to be ‘loaded’ on board.

23, TITLE: Multimodal Trajectory Prediction Conditioned on Lane-Graph Traversals
AUTHORS: Nachiket Deo ; Eric M. Wolff ; Oscar Beijbom
CATEGORY: cs.CV [cs.CV, cs.RO]
HIGHLIGHT: We present a novel method that combines learned discrete policy rollouts with a focused decoder on subsets of the lane graph.

24, TITLE: Quantifying Urban Streetscapes with Deep Learning: Focus on Aesthetic Evaluation
AUTHORS: Yusuke Kumakoshi ; Shigeaki Onoda ; Tetsuya Takahashi ; Yuji Yoshimura
CATEGORY: cs.CV [cs.CV, cs.CY]
HIGHLIGHT: To fill the gap, this paper reports the performance of our deep learning model on a unique data set prepared in Tokyo to recognize the areas covered by facades and billboards in streetscapes, respectively.

25, TITLE: Face Sketch Synthesis Via Semantic-Driven Generative Adversarial Network
HIGHLIGHT: To tackle these challenges, we propose a novel Semantic-Driven Generative Adversarial Network (SDGAN) which embeds global structure-level style injection and local class-level knowledge re-weighting.

26, TITLE: Fast and Accurate Road Crack Detection Based on Adaptive Cost-Sensitive Loss Function
AUTHORS: Kai Li ; Bo Wang ; Yingjie Tian ; Zhiquan Qi
HIGHLIGHT: In this paper, we propose a pixel-based adaptive weighted cross-entropy loss in conjunction with Jaccard distance to facilitate high-quality pixel-level road crack detection.

27, TITLE: An Uncertainty Estimation Framework for Probabilistic Object Detection
AUTHORS: Zongyao Lyu ; Nolan B. Gutierrez ; William J. Beksi
HIGHLIGHT: In this paper, we introduce a new technique that combines two popular methods to estimate uncertainty in object detection.

28, TITLE: Understanding Cognitive Fatigue from FMRI Scans with Self-supervised Learning
AUTHORS: Ashish Jaiswal ; Ashwin Ramesh Babu ; Mohammad Zaki Zadeh ; Fillia Makedon ; Glenn Wylie
HIGHLIGHT: This paper proposes tackling this issue as a multi-class classification problem by dividing the state of cognitive fatigue into six different levels, ranging from no-fatigue to extreme fatigue conditions.

29, TITLE: AutoNovel: Automatically Discovering and Learning Novel Visual Categories
AUTHORS: Kai Han ; Sylvestre-Alvise Rebuffi ; S�bastien Ehrhardt ; Andrea Vedaldi ; Andrew Zisserman
HIGHLIGHT: We present a new approach called AutoNovel to address this problem by combining three ideas: (1) we suggest that the common approach of bootstrapping an image representation using the labelled data only introduces an unwanted bias, and that this can be avoided by using self-supervised learning to train the representation from scratch on the union of labelled and unlabelled data; (2) we use ranking statistics to transfer the model’s knowledge of the labelled classes to the problem of clustering the unlabelled images; and, (3) we train the data representation by optimizing a joint objective function on the labelled and unlabelled subsets of the data, improving both the supervised classification of the labelled data, and the clustering of the unlabelled data.

30, TITLE: Using Robust Regression to Find Font Usage Trends
AUTHORS: Kaigen Tsuji ; Daichi Haraguchi ; Seiichi Uchida ; Brian Kenji Iwana
HIGHLIGHT: In this paper, we attempt to specifically find the trends in font usage using robust regression on a large collection of text images.

31, TITLE: Are Conditional GANs Explicitly Conditional?
AUTHORS: Houssem-eddine Boulahbal ; Adrian Voicila ; Andrew Comport
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: This paper proposes two important contributions for conditional Generative Adversarial Networks (cGANs) to improve the wide variety of applications that exploit this architecture.

32, TITLE: How Does Heterogeneous Label Noise Impact Generalization in Neural Nets?
AUTHORS: Bidur Khanal ; Christopher Kanan
HIGHLIGHT: We hypothesized that heterogeneous label noise would only affect the classes that had label noise unless there was transfer from those classes to the classes without label noise.

33, TITLE: Object Detection Based Handwriting Localization
AUTHORS: Yuli Wu ; Yucheng Hu ; Suting Miao
HIGHLIGHT: We present an object detection based approach to localize handwritten regions from documents, which initially aims to enhance the anonymization during the data transmission.

34, TITLE: Unified Questioner Transformer for Descriptive Question Generation in Goal-Oriented Visual Dialogue
HIGHLIGHT: In this paper, we propose a novel Questioner architecture, called Unified Questioner Transformer (UniQer), for descriptive question generation with referring expressions.

35, TITLE: An Image Is Worth More Than A Thousand Words: Towards Disentanglement in The Wild
AUTHORS: Aviv Gabbay ; Niv Cohen ; Yedid Hoshen
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: To this end, we propose a method for disentangling a set of factors which are only partially labeled, as well as separating the complementary set of residual factors that are never explicitly specified.

36, TITLE: Contrastive Semantic Similarity Learning for Image Captioning Evaluation with Intrinsic Auto-encoder
AUTHORS: Chao Zeng ; Tiesong Zhao ; Sam Kwong
HIGHLIGHT: Motivated by the auto-encoder mechanism and contrastive representation learning advances, we propose a learning-based metric for image captioning, which we call Intrinsic Image Captioning Evaluation($I^2CE$).

37, TITLE: Uncertainty-Guided Progressive GANs for Medical Image Translation
AUTHORS: Uddeshya Upadhyay ; Yanbei Chen ; Tobias Hepp ; Sergios Gatidis ; Zeynep Akata
CATEGORY: cs.CV [cs.CV, cs.LG, eess.IV]
HIGHLIGHT: In this work, we propose an uncertainty-guided progressive learning scheme for image-to-image translation.

38, TITLE: TUCaN: Progressively Teaching Colourisation to Capsules
AUTHORS: Rita Pucci ; Niki Martinel
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: We introduce a novel downsampling upsampling architecture named TUCaN (Tiny UCapsNet) that exploits the collaboration of convolutional layers and capsule layers to obtain a neat colourisation of entities present in every single image. We pose the problem as a per pixel colour classification task that identifies colours as a bin in a quantized space.

39, TITLE: Wrong Colored Vermeer: Color-Symmetric Image Distortion
AUTHORS: Hendrik Richter
CATEGORY: cs.CV [cs.CV, cs.GR]
HIGHLIGHT: I use this concept for generative art and apply symmetry-consistent color distortions to images of paintings by Johannes Vermeer.

40, TITLE: Spatio-Temporal Context for Action Detection
AUTHORS: Manuel Sarmiento Calder� ; David Varas ; Elisenda Bou-Balust
HIGHLIGHT: This is done by adding an attention based method that leverages spatio-temporal interactions between elements in the scene along the clip.The main contribution of this work is the introduction of two cross attention blocks to effectively model the spatial relations and capture short range temporal interactions.Experiments on the AVA dataset show the advantages of the proposed approach that models spatio-temporal relations between relevant elements in the scene, outperforming other methods that model actor interactions with their context by +0.31 mAP.

41, TITLE: Multi-Exit Vision Transformer for Dynamic Inference
AUTHORS: Arian Bakhtiarnia ; Qi Zhang ; Alexandros Iosifidis
HIGHLIGHT: In this work, we propose seven different architectures for early exit branches that can be used for dynamic inference in Vision Transformer backbones.

42, TITLE: IMENet: Joint 3D Semantic Scene Completion and 2D Semantic Segmentation Through Iterative Mutual Enhancement
AUTHORS: Jie Li ; Laiyan Ding ; Rui Huang
HIGHLIGHT: We argue that this sequential scheme does not ensure these two tasks fully benefit each other, and present an Iterative Mutual Enhancement Network (IMENet) to solve them jointly, which interactively refines the two tasks at the late prediction stage.

43, TITLE: Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition
AUTHORS: Yi-Fan Song ; Zhang Zhang ; Caifeng Shan ; Liang Wang
HIGHLIGHT: Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition

44, TITLE: Text Prior Guided Scene Text Image Super-resolution
AUTHORS: Jianqi Ma ; Shi Guo ; Lei Zhang
HIGHLIGHT: In this paper, we make an inspiring attempt to embed categorical text prior into STISR model training.

45, TITLE: Deep Learning for Face Anti-Spoofing: A Survey
HIGHLIGHT: In this paper, to stimulate future research, we present the first comprehensive review of recent advances in deep learning based FAS.

46, TITLE: Fast Training of Neural Lumigraph Representations Using Meta Learning
AUTHORS: Alexander W. Bergman ; Petr Kellnhofer ; Gordon Wetzstein
CATEGORY: cs.CV [cs.CV, cs.GR, cs.LG]
HIGHLIGHT: Inspired by neural variants of image-based rendering, we develop a new neural rendering approach with the goal of quickly learning a high-quality representation which can also be rendered in real-time.

47, TITLE: Achieving Real-Time Object Detection on MobileDevices with Neural Pruning Search
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: To facilitate this, we propose a compiler-aware neural pruning search framework to achieve high-speed inference on autonomous vehicles for 2D and 3D object detection.

48, TITLE: Striking The Right Balance: Recall Loss for Semantic Segmentation
AUTHORS: Junjiao Tian ; Niluthpol Mithun ; Zach Seymour ; Han-Pang Chiu ; Zsolt Kira
HIGHLIGHT: Many works have proposed to weight the standard cross entropy loss function with pre-computed weights based on class statistics, such as the number of samples and class margins.

49, TITLE: Do Not Deceive Your Employer with A Virtual Background: A Video Conferencing Manipulation-Detection System
AUTHORS: Mauro Conti ; Simone Milani ; Ehsan Nowroozi ; Gabriele Orazi
CATEGORY: cs.CR [cs.CR, cs.AI, cs.CV, cs.LG, cs.MM]
HIGHLIGHT: In this paper, we study the feasibility of an efficient tool to detect whether a videoconferencing user background is real.

50, TITLE: Framework for An Intelligent Affect Aware Smart Home Environment for Elderly People
AUTHORS: Nirmalya Thakur ; Chia Y. Han
CATEGORY: cs.HC [cs.HC, cs.AI, cs.CV, cs.ET, cs.LG, H.5; I.2; I.5; E.0; D.0]
HIGHLIGHT: This work therefore proposes the framework for an Intelligent Affect Aware environment for elderly people that can not only analyze the affective components of their interactions but also predict their likely user experience even before they start engaging in any activity in the given smart home environment.

51, TITLE: Evaluation of Automated Image Descriptions for Visually Impaired Students
AUTHORS: Anett Hoppe ; David Morris ; Ralph Ewerth
CATEGORY: cs.HC [cs.HC, cs.CV, cs.CY, H.5.2; I.4; K.3.1]
HIGHLIGHT: In this paper, we report on a study for the assessment of automated image descriptions.

52, TITLE: ElephantBook: A Semi-Automated Human-in-the-Loop System for Elephant Re-Identification
AUTHORS: Peter Kulits ; Jake Wall ; Anka Bedetti ; Michelle Henley ; Sara Beery
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: We have built and deployed a web-based platform and database for human-in-the-loop re-identification of elephants combining manual attribute labeling and state-of-the-art computer vision algorithms, known as ElephantBook.

53, TITLE: Convolutional Sparse Coding Fast Approximation with Application to Seismic Reflectivity Estimation
AUTHORS: Deborah Pereg ; Israel Cohen ; Anthony A. Vassiliou
CATEGORY: cs.LG [cs.LG, cs.CE, cs.CV]
HIGHLIGHT: We propose a speed-up upgraded version of the classic iterative thresholding algorithm, that produces a good approximation of the convolutional sparse code within 2-5 iterations.

54, TITLE: Adaptive Sample Selection for Robust Learning Under Label Noise
AUTHORS: Deep Patel ; P. S. Sastry
CATEGORY: cs.LG [cs.LG, cs.AI, cs.CV]
HIGHLIGHT: In this paper, we propose a data-dependent, adaptive sample selection strategy that relies only on batch statistics of a given mini-batch to provide robustness against label noise.

55, TITLE: Spiking-GAN: A Spiking Generative Adversarial Network Using Time-To-First-Spike Coding
AUTHORS: Vineet Kotariya ; Udayan Ganguly
CATEGORY: cs.NE [cs.NE, cs.CV, q-bio.NC]
HIGHLIGHT: In this paper, we propose Spiking-GAN, the first spike-based Generative Adversarial Network (GAN).

56, TITLE: Unified Framework for Spectral Dimensionality Reduction, Maximum Variance Unfolding, and Kernel Learning By Semidefinite Programming: Tutorial and Survey
AUTHORS: Benyamin Ghojogh ; Ali Ghodsi ; Fakhri Karray ; Mark Crowley
CATEGORY: stat.ML [stat.ML, cs.CV, cs.LG]
HIGHLIGHT: Unified Framework for Spectral Dimensionality Reduction, Maximum Variance Unfolding, and Kernel Learning By Semidefinite Programming: Tutorial and Survey

57, TITLE: IREM: High-Resolution Magnetic Resonance (MR) Image Reconstruction Via Implicit Neural Representation
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: In this work, we suppose the desired HR image as an implicit continuous function of the 3D image spatial coordinate and the thick-slice LR images as several sparse discrete samplings of this function.

58, TITLE: A Mixed-Supervision Multilevel GAN Framework for Image Quality Enhancement
AUTHORS: Uddeshya Upadhyay ; Suyash Awate
CATEGORY: eess.IV [eess.IV, cs.CV, cs.LG]
HIGHLIGHT: Thus, we propose a novel generative adversarial network (GAN) that can leverage training data at multiple levels of quality (e.g., high and medium quality) to improve performance while limiting costs of data curation.

59, TITLE: Two-Stage Self-Supervised Cycle-Consistency Network for Reconstruction of Thin-Slice MR Images
AUTHORS: Zhiyang Lu ; Zheng Li ; Jun Wang ; Jun shi ; Dinggang Shen
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: Deep learning (DL) has shown great potential to re-construct the high-resolution (HR) thin-slice MR images from those low-resolution (LR) cases, which we refer to as the slice interpolation task in this work.

60, TITLE: Data Augmentation for Deep Learning Based Accelerated MRI Reconstruction with Limited Data
AUTHORS: Zalan Fabian ; Reinhard Heckel ; Mahdi Soltanolkotabi
CATEGORY: eess.IV [eess.IV, cs.CV, cs.LG, I.2; I.4; J.3]
HIGHLIGHT: Inspired by the success of Data Augmentation (DA) for classification problems, in this paper, we propose a pipeline for data augmentation for accelerated MRI reconstruction and study its effectiveness at reducing the required training data in a variety of settings.


Related Posts

Maven actual combat (4) — Multi-module project — JBOSS deployment issues

About ELEMENT-UI Table Rolling Style El-Scrollbar’s problem use Jack

Female programmer: I am responsible for making money and supporting her family, my husband is responsible for being beautiful!

[Large screen project] SpringBoot + Vue implemented visualized drag editor

All kinds of original system download: download Windows, MacOS, Linux original system mirror in MSDN

Random Posts

vs2005 + DDK6001 environment matching and compilation of the whole process ZEALOT

nr CSI (3) CQI

jQuery.extend function detailed explanation

Based on HAL library, transplant RT-Thread on the MDK V5

Enhanced for loop