计算机视觉论文-2021-07-01

本专栏是计算机视觉方向论文收集积累，时间：2021年7月1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: Automated Onychomycosis Detection Using Deep Neural Networks
AUTHORS: ABDURRAHIM YILMAZ et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This study presents a deep neural network structure that enables the rapid solutions for these problems and can perform automatic fungi detection in grayscale images without colorants.

2, TITLE: Dense Graph Convolutional Neural Networks on 3D Meshes for 3D Object Segmentation and Classification
AUTHORS: Wenming Tang Guoping Qiu
CATEGORY: cs.CV [cs.CV, cs.GR]
HIGHLIGHT: This paper presents new designs of graph convolutional neural networks (GCNs) on 3D meshes for 3D object segmentation and classification.

3, TITLE: Small In-distribution Changes in 3D Perspective and Lighting Fool Both CNNs and Transformers
AUTHORS: Spandan Madan ; Tomotake Sasaki ; Tzu-Mao Li ; Xavier Boix ; Hanspeter Pfister
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: To find these in-distribution errors, we introduce an evolution strategies (ES) based approach, which we call CMA-Search.

4, TITLE: Attention Aware Wavelet-based Detection of Morphed Face Images
AUTHORS: Poorya Aghdaie ; Baaria Chaudhary ; Sobhan Soleymani ; Jeremy Dawson ; Nasser M. Nasrabadi
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To overcome the risks incurred due to morphed presentations, we propose a wavelet-based morph detection methodology which adopts an end-to-end trainable soft attention mechanism .

5, TITLE: Positive-unlabeled Learning for Cell Detection in Histopathology Images with Incomplete Annotations
AUTHORS: Zipei Zhao ; Fengqian Pang ; Zhiwen Liu ; Chuyang Ye
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, to address the problem of incomplete annotations, we formulate the training of detection networks as a positive-unlabeled learning problem.

6, TITLE: Domain Adaptation for Person Re-identification on New Unlabeled Data Using AlignedReID++
AUTHORS: Tiago de C. G. Pereira ; Teofilo E. de Campos
CATEGORY: cs.CV [cs.CV, 68T45 (Primary) 68T10, 68T07 (Secondary), I.4.9; I.5.4; I.2.10]
HIGHLIGHT: In this work we propose a domain adaptation workflow to allow CNNs that were trained in one domain to be applied to another domain without the need for new annotation of the target data.

7, TITLE: Word-level Sign Language Recognition with Multi-stream Neural Networks Focusing on Local Regions
AUTHORS: MIZUKI MARUYAMA et. al.
CATEGORY: cs.CV [cs.CV, cs.MM]
HIGHLIGHT: Thus in this work, we utilized local region images of both hands and face, along with skeletal information to capture local information and the positions of both hands relative to the body, respectively.

8, TITLE: SOLO: A Simple Framework for Instance Segmentation
AUTHORS: Xinlong Wang ; Rufeng Zhang ; Chunhua Shen ; Tao Kong ; Lei Li
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we view the task of instance segmentation from a completely new perspective by introducing the notion of "instance categories", which assigns categories to each pixel within an instance according to the instance's location.

9, TITLE: Cyclist Trajectory Forecasts By Incorporation of Multi-View Video Information
AUTHORS: Stefan Zernetsch ; Oliver Trupp ; Viktor Kress ; Konrad Doll ; Bernhard Sick
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: This article presents a novel approach to incorporate visual cues from video-data from a wide-angle stereo camera system mounted at an urban intersection into the forecast of cyclist trajectories.

10, TITLE: Augmented Shortcuts for Vision Transformers
AUTHORS: YEHUI TANG et. al.
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: In this paper, we theoretically analyze the feature collapse phenomenon and study the relationship between shortcuts and feature diversity in these transformer models.

11, TITLE: Affective Image Content Analysis: Two Decades Review and New Perspectives
AUTHORS: SICHENG ZHAO et. al.
CATEGORY: cs.CV [cs.CV, cs.AI, cs.MM]
HIGHLIGHT: In this survey, we will comprehensively review the development of AICA in the recent two decades, especially focusing on the state-of-the-art methods with respect to three main challenges -- the affective gap, perception subjectivity, and label noise and absence.

12, TITLE: Recognizing Facial Expressions in The Wild Using Multi-Architectural Representations Based Ensemble Learning with Distillation
AUTHORS: Rauf Momin ; Ali Shan Momin ; Khalid Rasheed
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We proposed two models, EmoXNet which is an ensemble learning technique for learning convoluted facial representations, and EmoXNetLite which is a distillation technique that is useful for transferring the knowledge from our ensemble model to an efficient deep neural network using label-smoothen soft labels for able to effectively detect expressions in real-time.

13, TITLE: Looking Outside The Window: Wider-Context Transformer for The Semantic Segmentation of High-Resolution Remote Sensing Images
AUTHORS: LEI DING et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To break this limitation, we propose a Wider-Context Network (WiCNet) for the semantic segmentation of HR RSIs.

14, TITLE: Recurrently Estimating Reflective Symmetry Planes from Partial Pointclouds
AUTHORS: Mihaela C?t?lina Stoian ; Tommaso Cavallari
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper we present an alternative novel encoding that instead slices the data along the height dimension and passes it sequentially to a 2D convolutional recurrent regression scheme.

15, TITLE: Dual Reweighting Domain Generalization for Face Presentation Attack Detection
AUTHORS: SHUBAO LIU et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To settle the issue, we propose a novel Dual Reweighting Domain Generalization (DRDG) framework which iteratively reweights the relative importance between samples to further improve the generalization.

16, TITLE: Single-Step Adversarial Training for Semantic Segmentation
AUTHORS: Daniel Wiens ; Barbara Hammer
CATEGORY: cs.CV [cs.CV, cs.LG, eess.IV]
HIGHLIGHT: In this work we address the computationally particularly demanding task of semantic segmentation and propose a new step size control algorithm that increases the robustness of single-step adversarial training.

17, TITLE: Weakly Supervised Temporal Adjacent Network for Language Grounding
AUTHORS: Yuechen Wang ; Jiajun Deng ; Wengang Zhou ; Houqiang Li
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we are dedicated to weakly supervised TLG, where multiple description sentences are given to an untrimmed video without temporal boundary labels.

18, TITLE: Multi-Source Domain Adaptation Via Supervised Contrastive Learning and Confident Consistency Regularization
AUTHORS: Marin Scalbert ; Maria Vakalopoulou ; Florent Couzini�-Devy
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we propose a new framework called Contrastive Multi-Source Domain Adaptation (CMSDA) for multi-source UDA that addresses this limitation.

19, TITLE: Synthetic Data Are As Good As The Real for Association Knowledge Learning in Multi-object Tracking
AUTHORS: Yuchi Liu ; Zhongdao Wang ; Xiangxin Zhou ; Liang Zheng
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we study whether 3D synthetic data can replace real-world videos for association training.

20, TITLE: RICE: Refining Instance Masks in Cluttered Environments with Graph Neural Networks
AUTHORS: Christopher Xie ; Arsalan Mousavian ; Yu Xiang ; Dieter Fox
CATEGORY: cs.CV [cs.CV, cs.RO]
HIGHLIGHT: Thus, in this work, we propose a novel framework that refines the output of such methods by utilizing a graph-based representation of instance masks.

21, TITLE: Zero-shot Learning with Class Description Regularization
AUTHORS: Shayan Kousha ; Marcus A. Brubaker
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We introduce a novel form of regularization that encourages generative ZSL models to pay more attention to the description of each category.

22, TITLE: When Video Classification Meets Incremental Classes
AUTHORS: Hanbin Zhao ; Xin Qin ; Shihao Su ; Zibo Lin ; Xi Li
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we summarize this task as \textit{Class-Incremental Video Classification (CIVC)} and propose a novel framework to address it.

23, TITLE: Semantic Segmentation of Periocular Near-Infra-Red Eye Images Under Alcohol Effects
AUTHORS: JUAN TAPIA et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This paper proposes a new framework to detect, segment, and estimate the localization of the eyes from a periocular Near-Infra-Red iris image under alcohol consumption.

24, TITLE: S2C2 - An Orthogonal Method for Semi-Supervised Learning on Fuzzy Labels
AUTHORS: LARS SCHMARJE et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We propose Semi-Supervised Classification & Clustering (S2C2) which can extend many deep SSL algorithms.

25, TITLE: Shape Completion Via IMLE
AUTHORS: Himanshu Arora ; Saurabh Mishra ; Shichong Peng ; Ke Li ; Ali Mahdavi-Amiri
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We propose a novel multimodal shape completion technique that is effectively able to learn a one-to-many mapping and generates diverse complete shapes.

26, TITLE: Learning More for Free - A Multi Task Learning Approach for Improved Pathology Classification in Capsule Endoscopy
AUTHORS: Anuja Vats ; Marius Pedersen ; Ahmed Mohammed ; �istein Hovde
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we explore how to learn more for free, from limited data through solving a WCE multicentric, multi-pathology classification problem.

27, TITLE: Mutual-GAN: Towards Unsupervised Cross-Weather Adaptation with Mutual Information Constraint
AUTHORS: Jiawei Chen ; Yuexiang Li ; Kai Ma ; Yefeng Zheng
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: In this paper, we propose a novel generative adversarial network (namely Mutual-GAN) to alleviate the accuracy decline when daytime-trained neural network is applied to videos captured under adverse weather conditions.

28, TITLE: Long-Short Temporal Modeling for Efficient Action Recognition
AUTHORS: Liyu Wu ; Yuexian Zou ; Can Zhang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a new two-stream action recognition network, termed as MENet, consisting of a Motion Enhancement (ME) module and a Video-level Aggregation (VLA) module to achieve long-short temporal modeling.

29, TITLE: Align Yourself: Self-supervised Pre-training for Fine-grained Recognition Via Saliency Alignment
AUTHORS: DI WU et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we first point out that current contrastive methods are prone to memorizing background/foreground texture and therefore have a limitation in localizing the foreground object.

30, TITLE: Multi-Source Domain Adaptation for Object Detection
AUTHORS: Xingxu Yao ; Sicheng Zhao ; Pengfei Xu ; Jufeng Yang
CATEGORY: cs.CV [cs.CV, cs.AI, cs.LG]
HIGHLIGHT: For the more challenging task, we propose a unified Faster R-CNN based framework, termed Divide-and-Merge Spindle Network (DMSN), which can simultaneously enhance domain invariance and preserve discriminative power.

31, TITLE: Monocular 3D Object Detection: An Extrinsic Parameter Free Approach
AUTHORS: YUNSONG ZHOU et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To this end, we propose a novel method to capture camera pose to formulate the detector free from extrinsic perturbation.

32, TITLE: Content-Aware Convolutional Neural Networks
AUTHORS: YONG GUO et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To this end, we propose a Content-aware Convolution (CAC) that automatically detects the smooth windows and applies a 1x1 convolutional kernel to replace the original large kernel.

33, TITLE: MissFormer: (In-)attention-based Handling of Missing Observations for Trajectory Filtering and Prediction
AUTHORS: Stefan Becker ; Ronny Hug ; Wolfgang H�bner ; Michael Arens ; Brendan T. Morris
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Towards this end, this paper introduces a transformer-based approach for handling missing observations in variable input length trajectory data.

34, TITLE: A Survey on Adversarial Image Synthesis
AUTHORS: William Roy ; Glen Kelly ; Robert Leer ; Frederick Ricardo
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we provide a taxonomy of methods used in image synthesis, review different models for text-to-image synthesis and image-to-image translation, and discuss some evaluation metrics as well as possible future research directions in image synthesis with GAN.

35, TITLE: SIMPL: Generating Synthetic Overhead Imagery to Address Zero-shot and Few-Shot Detection Problems
AUTHORS: Yang Xu ; Bohao Huang ; Xiong Luo ; Kyle Bradbury ; Jordan M. Malof
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work we present a simple approach - termed Synthetic object IMPLantation (SIMPL) - to easily and rapidly generate large quantities of synthetic overhead training data for custom target objects.

36, TITLE: Efficient Spatio-Temporal Recurrent Neural Network for Video Deblurring
AUTHORS: Zhihang Zhong ; Ye Gao ; Yinqiang Zheng ; Bo Zheng ; Imari Sato
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Thus, we contribute a novel dataset (BSD) to the community, by collecting paired blurry/sharp video clips using a co-axis beam splitter acquisition system.

37, TITLE: A Structured Analysis of The Video Degradation Effects on The Performance of A Machine Learning-enabled Pedestrian Detector
AUTHORS: Christian Berger
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, a structured analysis has been conducted to explore video degradation effects on the performance of an ML-enabled pedestrian detector.

38, TITLE: Learning to Map for Active Semantic Goal Navigation
AUTHORS: Georgios Georgakis ; Bernadette Bucher ; Karl Schmeckpeper ; Siddharth Singh ; Kostas Daniilidis
CATEGORY: cs.CV [cs.CV, cs.RO]
HIGHLIGHT: In this work, we propose a novel framework that actively learns to generate semantic maps outside the field of view of the agent and leverages the uncertainty over the semantic classes in the unobserved areas to decide on long term goals.

39, TITLE: Diff2Dist: Learning Spectrally Distinct Edge Functions, with Applications to Cell Morphology Analysis
AUTHORS: CORY BRAKER SCOTT et. al.
CATEGORY: cs.LG [cs.LG, cs.CV, math.MG]
HIGHLIGHT: We present a method for learning "spectrally descriptive" edge weights for graphs.

40, TITLE: Interventional Assays for The Latent Space of Autoencoders
AUTHORS: Felix Leeb ; Stefan Bauer ; Bernhard Sch�lkopf
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: We propose a framework, called latent responses, for probing the learned data manifold using interventions in the latent space.

41, TITLE: Leveraging Hidden Structure in Self-Supervised Learning
AUTHORS: Emanuele Sansone
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: We propose a principled framework based on a mutual information objective, which integrates self-supervised and structure learning.

42, TITLE: The Evolution of Out-of-Distribution Robustness Throughout Fine-Tuning
AUTHORS: Anders Andreassen ; Yasaman Bahri ; Behnam Neyshabur ; Rebecca Roelofs
CATEGORY: cs.LG [cs.LG, cs.AI, cs.CV]
HIGHLIGHT: Identifying such models, and understanding their properties, is key to improving out-of-distribution performance.

43, TITLE: How to Train Your MAML to Excel in Few-Shot Classification
AUTHORS: Han-Jia Ye ; Wei-Lun Chao
CATEGORY: cs.LG [cs.LG, cs.AI, cs.CV]
HIGHLIGHT: In this paper, we point out several key facets of how to train MAML to excel in few-shot classification.

44, TITLE: Improving The Efficiency of Transformers for Resource-Constrained Devices
AUTHORS: Hamid Tabani ; Ajay Balasubramaniam ; Shabbir Marzban ; Elahe Arani ; Bahram Zonooz
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: In this paper, we present a performance analysis of state-of-the-art vision transformers on several devices.

45, TITLE: SimNet: Enabling Robust Unknown Object Manipulation from Pure Synthetic Data Via Stereo
AUTHORS: Thomas Kollar ; Michael Laskey ; Kevin Stone ; Brijen Thananjeyan ; Mark Tjersland
CATEGORY: cs.RO [cs.RO, cs.CV, cs.LG]
HIGHLIGHT: To address these challenges we propose an approach to performing sim-to-real transfer of robotic perception.

46, TITLE: Hierarchical Phenotyping and Graph Modeling of Spatial Architecture in Lymphoid Neoplasms
AUTHORS: Pingjun Chen ; Muhammad Aminu ; Siba El Hussein ; Joseph Khoury ; Jia Wu
CATEGORY: q-bio.QM [q-bio.QM, cs.CV, cs.LG, eess.IV]
HIGHLIGHT: In the end, we built global graphs to abstract spatial interaction patterns and extract features for disease diagnosis.

47, TITLE: 10-mega Pixel Snapshot Compressive Imaging with A Hybrid Coded Aperture
AUTHORS: ZHIHONG ZHANG et. al.
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: In this paper, we build a novel hybrid coded aperture snapshot compressive imaging (HCA-SCI) system by incorporating a dynamic liquid crystal on silicon and a high-resolution lithography mask.

48, TITLE: RCNN-SliceNet: A Slice and Cluster Approach for Nuclei Centroid Detection in Three-Dimensional Fluorescence Microscopy Images
AUTHORS: LIMING WU et. al.
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: To address these issues, we present a scalable approach for nuclei centroid detection of 3D microscopy volumes.

49, TITLE: Learnable Reconstruction Methods from RGB Images to Hyperspectral Imaging: A Survey
AUTHORS: Jingang Zhang ; Runmu Su ; Wenqi Ren ; Qiang Fu ; Yunfeng Nie
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: Therefore, many alternative spectral imaging methods have been proposed by directly reconstructing the hyperspectral information from lower-cost, more available RGB images.

50, TITLE: BLNet: A Fast Deep Learning Framework for Low-Light Image Enhancement with Noise Removal and Color Restoration
AUTHORS: XINXU WEI et. al.
CATEGORY: eess.IV [eess.IV, cs.CV, I.2; I.4]
HIGHLIGHT: In this paper, we propose a very fast deep learning framework called Bringing the Lightness (denoted as BLNet) that consists of two U-Nets with a series of well-designed loss functions to tackle all of the above degradations.

51, TITLE: Fast Whole-slide Cartography in Colon Cancer Histology Using Superpixels and CNN Classification
AUTHORS: FRAUKE WILM et. al.
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: We propose to subdivide the image into coherent regions prior to classification by grouping visually similar adjacent image pixels into larger segments, i.e. superpixels.

52, TITLE: ResViT: Residual Vision Transformers for Multi-modal Medical Image Synthesis
AUTHORS: Onat Dalmaz ; Mahmut Yurt ; Tolga �ukur
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: Here, we propose a novel generative adversarial approach for medical image synthesis, ResViT, to combine local precision of convolution operators with contextual sensitivity of vision transformers.