计算机视觉论文-2021-05-10

本专栏是计算机视觉方向论文收集积累，时间：2021年5月10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: Towards Real-World Category-level Articulation Pose Estimation
AUTHORS: Liu Liu ; Han Xue ; Wenqiang Xu ; Haoyuan Fu ; Cewu Lu
CATEGORY: cs.CV [cs.CV, cs.RO]
HIGHLIGHT: To support this task, we build an articulated model repository ReArt-48 and present an efficient dataset generation pipeline, which contains Fast Articulated Object Modeling (FAOM) and Semi-Authentic MixEd Reality Technique (SAMERT).

2, TITLE: ResMLP: Feedforward Networks for Image Classification with Data-efficient Training
AUTHORS: HUGO TOUVRON et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We present ResMLP, an architecture built entirely upon multi-layer perceptrons for image classification.

3, TITLE: Toward Interactive Modulation for Photo-Realistic Image Restoration
AUTHORS: Haoming Cai ; Jingwen He ; Qiao Yu ; Chao Dong
CATEGORY: cs.CV [cs.CV, eess.IV]
HIGHLIGHT: This paper presents a Controllable Unet Generative Adversarial Network (CUGAN) to generate high-frequency textures in the modulation tasks.

4, TITLE: Human Object Interaction Detection Using Two-Direction Spatial Enhancement and Exclusive Object Prior
AUTHORS: Lu Liu ; Robby T. Tan
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To address the mis-grouping problem, we propose a spatial enhancement approach to enforce fine-level spatial constraints in two directions from human body parts to the object center, and from object parts to the human center.

5, TITLE: Salient Objects in Clutter
AUTHORS: Deng-Ping Fan ; Jing Zhang ; Gang Xu ; Ming-Ming Cheng ; Ling Shao
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Based on our analyses, we propose a new high-quality dataset and update the previous saliency benchmark. We also provide a comprehensive benchmark for SOD, which can be found in our repository: http://dpfan.net/SOCBenchmark.

6, TITLE: Adaptive Focus for Efficient Video Recognition
AUTHORS: YULIN WANG et. al.
CATEGORY: cs.CV [cs.CV, cs.LG, eess.IV]
HIGHLIGHT: In this paper, we explore the spatial redundancy in video recognition with the aim to improve the computational efficiency.

7, TITLE: Few-Shot Learning for Image Classification of Common Flora
AUTHORS: Joshua Ball
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper we will showcase our experimental results from testing various state-of-the-art transfer learning weights and architectures versus similar state-of-the-art works in the meta-learning field for image classification utilizing Model-Agnostic Meta Learning (MAML).

8, TITLE: An Intelligent Passive Food Intake Assessment System with Egocentric Cameras
AUTHORS: FRANK PO WEN LO et. al.
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: To demonstrate the efficacy, experienced dietitians are involved in this research to perform the visual portion size estimation, and their predictions are compared to our proposed method.

9, TITLE: Faster and Simpler Siamese Network for Single Object Tracking
AUTHORS: Shaokui Jiang ; Baile Xu ; Jian Zhao ; Furao Shen
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we compare the proposed method with some state-of-the-art trackers and analysis their performances.

10, TITLE: Probabilistic Ranking-Aware Ensembles for Enhanced Object Detections
AUTHORS: MINGYUAN MAO et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To address this issue, we propose a novel ensemble called the Probabilistic Ranking Aware Ensemble (PRAE) that refines the confidence of bounding boxes from detectors.

11, TITLE: Self-paced Resistance Learning Against Overfitting on Noisy Labels
AUTHORS: Xiaoshuang Shi ; Zhenhua Guo ; Fuyong Xing ; Yun Liang ; Xiaofeng Zhu
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To address this issue, inspired by an observation, deep neural networks might first memorize the probably correct-label data and then corrupt-label samples, we propose a novel yet simple self-paced resistance framework to resist corrupted labels, without using any clean validation data.

12, TITLE: Interpretable Social Anchors for Human Trajectory Forecasting in Crowds
AUTHORS: Parth Kothari ; Brian Sifringer ; Alexandre Alahi
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To overcome this limitation, we leverage the power of discrete choice models to learn interpretable rule-based intents, and subsequently utilise the expressibility of neural networks to model scene-specific residual.

13, TITLE: Neural 3D Scene Compression Via Model Compression
AUTHORS: Berivan Isik
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: In this work, we take a different approach and compress a functional representation of 3D scenes.

14, TITLE: Efficient Masked Face Recognition Method During The COVID-19 Pandemic
AUTHORS: Walid Hariri
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a reliable method based on occlusion removal and deep learning-based features in order to address the problem of the masked face recognition process.

15, TITLE: Contrastive Learning for Unsupervised Image-to-Image Translation
AUTHORS: Hanbit Lee ; Jinseok Seol ; Sang-goo Lee
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To this end, we propose an unsupervised image-to-image translation method based on contrastive learning.

16, TITLE: Adaptive Domain-Specific Normalization for Generalizable Person Re-Identification
AUTHORS: JIAWEI LIU et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we propose a novel adaptive domain-specific normalization approach (AdsNorm) for generalizable person Re-ID.

17, TITLE: A^2-FPN: Attention Aggregation Based Feature Pyramid Network for Instance Segmentation
AUTHORS: Miao Hu ; Yali Li ; Lu Fang ; Shengjin Wang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we propose Attention Aggregation based Feature Pyramid Network (A^2-FPN), to improve multi-scale feature learning through attention-guided feature aggregation.

18, TITLE: Probabilistic Visual Place Recognition for Hierarchical Localization
AUTHORS: Ming Xu ; Niko S�nderhauf ; Michael Milford
CATEGORY: cs.CV [cs.CV, cs.RO]
HIGHLIGHT: In this letter, we propose two methods which adapt image retrieval techniques used for visual place recognition to the Bayesian state estimation formulation for localization.

19, TITLE: BasisNet: Two-stage Model Synthesis for Efficient Inference
AUTHORS: MINGDA ZHANG et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we present BasisNet which combines recent advancements in efficient neural network architectures, conditional computation, and early termination in a simple new form.

20, TITLE: SkyCam: A Dataset of Sky Images and Their Irradiance Values
AUTHORS: Evangelos Ntavelis ; Jan Remund ; Philipp Schmid
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Motivated by this success, the SkyCam Dataset aims to enable image-based Deep Learning solutions for short-term, precise prediction of solar radiation on a local level.

21, TITLE: Foreground-guided Facial Inpainting with Fidelity Preservation
AUTHORS: Jireh Jam ; Connah Kendrick ; Vincent Drouard ; Kevin Walker ; Moi Hoon Yap
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Specifically, we propose a new loss function with semantic capability reasoning of facial expressions, natural and unnatural features (make-up).

22, TITLE: Exploring Instance Relations for Unsupervised Feature Embedding
AUTHORS: Yifei Zhang ; Yu Zhou ; Weiping Wang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we explore instance relations including intra-instance multi-view relation and inter-instance interpolation relation for unsupervised feature embedding.

23, TITLE: MOTR: End-to-End Multiple-Object Tracking with TRansformer
AUTHORS: FANGAO ZENG et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we present MOTR, the first fully end-to-end multiple-object tracking framework.

24, TITLE: LASR: Learning Articulated Shape Reconstruction from A Monocular Video
AUTHORS: GENGSHAN YANG et. al.
CATEGORY: cs.CV [cs.CV, cs.GR]
HIGHLIGHT: In this work, we introduce a template-free approach to learn 3D shapes from a single video.

25, TITLE: More Separable and Easier to Segment: A Cluster Alignment Method for Cross-Domain Semantic Segmentation
AUTHORS: SHUANG WANG et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a new UDA semantic segmentation approach based on domain closeness assumption to alleviate the above problems.

26, TITLE: A State-of-the-art Survey of Object Detection Techniques in Microorganism Image Analysis: from Traditional Image Processing and Classical Machine Learning to Current Deep Convolutional Neural Networks and Potential Visual Transformers
AUTHORS: CHEN LI et. al.
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: In general, we have summarized 137 related technical papers from 1985 to the present.

27, TITLE: Autoencoder Based Inter-Vehicle Generalization for In-Cabin Occupant Classification
AUTHORS: Steve Dias Da Cruz ; Bertram Taetz ; Oliver Wasenm�ller ; Thomas Stifter ; Didier Stricker
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We performed an investigation on the SVIRO dataset for occupant classification on the rear bench and propose an autoencoder based approach to improve the transferability.

28, TITLE: Adv-Makeup: A New Imperceptible and Transferable Attack on Face Recognition
AUTHORS: BANGJIE YIN et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a unified adversarial face generation method - Adv-Makeup, which can realize imperceptible and transferable attack under black-box setting.

29, TITLE: Energy-Based Anomaly Detection and Localization
AUTHORS: Ergin Utku Genc ; Nilesh Ahuja ; Ibrahima J Ndiour ; Omesh Tickoo
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: We employ the density estimates from the energy-based model (EBM) as normalcy scores that can be used to discriminate normal images from anomalous ones.

30, TITLE: Understanding Catastrophic Overfitting in Adversarial Training
AUTHORS: Peilin Kang ; Seyed-Mohsen Moosavi-Dezfooli
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: In this paper, we find CO is not only limited to FGSM, but also happens in $\mbox{DF}^{\infty}$-1 adversarial training.

31, TITLE: Structured Dataset Documentation: A Datasheet for CheXpert
AUTHORS: Christian Garbin ; Pranav Rajpurkar ; Jeremy Irvin ; Matthew P. Lungren ; Oge Marques
CATEGORY: eess.IV [eess.IV, cs.CV, cs.LG]
HIGHLIGHT: Another objective of this paper is to put forward this dataset datasheet as an example to the community of how to create detailed and structured descriptions of datasets.

32, TITLE: NTIRE 2021 Challenge on Perceptual Image Quality Assessment
AUTHORS: JINJIN GU et. al.
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: This paper reports on the NTIRE 2021 challenge on perceptual image quality assessment (IQA), held in conjunction with the New Trends in Image Restoration and Enhancement workshop (NTIRE) workshop at CVPR 2021.

33, TITLE: Self-Adaptive Transfer Learning for Multicenter Glaucoma Classification in Fundus Retina Images
AUTHORS: YIMING BAO et. al.
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: In this paper, we propose a self-adaptive transfer learning (SATL) strategy to fill the domain gap between multicenter datasets.

34, TITLE: LINN: Lifting Inspired Invertible Neural Network for Image Denoising
AUTHORS: Jun-Jie Huang ; Pier Luigi Dragotti
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: In this paper, we propose an invertible neural network for image denoising (DnINN) inspired by the transform-based denoising framework.