2021.3.15 Vision papers

03-09-2021	NeX: Real-time View Synthesis with Neural Basis Expansion by Suttisak Wizadwongsa et al
03-10-2021	Involution: Inverting the Inherence of Convolution for Visual Recognition by Duo Li et al
03-11-2021	SMPLicit: Topology-aware Generative Model for Clothed People by Enric Corona et al
03-10-2021	Holistic 3D Scene Understanding from a Single Image with Implicit Representation by Cheng Zhang et al
03-11-2021	Fast and Accurate Model Scaling by Piotr Dollár et al
03-11-2021	HumanGAN: A Generative Model of Humans Images by Kripasindhu Sarkar et al
03-11-2021	WenLan: Bridging Vision and Language by Large-Scale Multi-Modal Pre-Training by Yuqi Huo et al
03-10-2021	3D Head-Position Prediction in First-Person View by Considering Head Pose for Human-Robot Eye Contact by Yuki Tamaru et al
03-10-2021	What is Multimodality? by Letitia Parcalabescu et al
03-10-2021	Full Page Handwriting Recognition via Image to Sequence Extraction by Sumeet S. Singh et al
03-09-2021	ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysis by Yinan He et al
03-10-2021	VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examples by Tian Pan et al
03-09-2021	SMIL: Multimodal Learning with Severely Missing Modality by Mengmeng Ma et al
03-10-2021	Spatially Consistent Representation Learning by Byungseok Roh et al
03-10-2021	Dynamical Pose Estimation by Heng Yang et al
03-10-2021	Where is your place, Visual Place Recognition? by Sourav Garg et al
03-11-2021	CoMoGAN: continuous model-guided image-to-image translation by Fabio Pizzati et al
03-11-2021	Diverse Semantic Image Synthesis via Probability Distribution Modeling by Zhentao Tan et al
03-11-2021	Emerging Paradigms of Neural Network Pruning by Huan Wang et al
03-09-2021	SimTriplet: Simple Triplet Representation Learning with a Single GPU by Quan Liu et al
03-09-2021	Deep Learning based 3D Segmentation: A Survey by Yong He et al
03-11-2021	Instance Segmentation GNNs for One-Shot Conformal Tracking at the LHC by Savannah Thais et al
03-09-2021	Pixel-wise Anomaly Detection in Complex Driving Scenes by Giancarlo Di Biase et al
03-11-2021	DAFAR: Detecting Adversaries by Feedback-Autoencoder Reconstruction by Haowen Liu et al
03-10-2021	A Vision Based Deep Reinforcement Learning Algorithm for UAV Obstacle Avoidance by Jeremy Roghair et al
03-11-2021	Integrated Age Estimation Mechanism by Fan Li et al
03-11-2021	Affect2MM: Affective Analysis of Multimedia Content Using Emotion Causality by Trisha Mittal et al
03-11-2021	MagFace: A Universal Representation for Face Recognition and Quality Assessment by Qiang Meng et al
03-11-2021	Generalized Contrastive Optimization of Siamese Networks for Place Recognition by María Leyva-Vallina et al
03-10-2021	Oversampling errors in multimodal medical imaging are due to the Gibbs effect by Davide Poggiali et al
03-09-2021	Super-Resolving Beyond Satellite Hardware Using Realistically Degraded Images by Jack White et al
03-11-2021	3D Human Pose, Shape and Texture from Low-Resolution Images and Videos by Xiangyu Xu et al
03-11-2021	An unsupervised deep learning framework for medical image denoising by Swati Rai et al
03-10-2021	FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding by Bo Sun et al
03-11-2021	Preprint: Norm Loss: An efficient yet effective regularization method for deep neural networks by Theodoros Georgiou et al
03-11-2021	Privacy-preserving Object Detection by Peiyang He et al
03-11-2021	Triple-cooperative Video Shadow Detection by Zhihao Chen et al
03-12-2021	Probabilistic two-stage detection by Xingyi Zhou et al
03-10-2021	A Study of Face Obfuscation in ImageNet by Kaiyu Yang et al
03-11-2021	Unknown Object Segmentation from Stereo Images by Maximilian Durner et al
03-11-2021	Automatic Social Distance Estimation From Images: Performance Evaluation, Test Benchmark, and Algorithm by Mert Seker et al
03-11-2021	Pavement Distress Detection and Segmentation using YOLOv4 and DeepLabv3 on Pavements in the Philippines by James-Andrew Sarmiento
03-09-2021	Select, Substitute, Search: A New Benchmark for Knowledge-Augmented Visual Question Answering by Aman Jain et al
03-10-2021	Symmetry meets AI by Gabriela Barenboim et al
03-11-2021	Deep Graph Matching under Quadratic Constraint by Quankai Gao et al
03-10-2021	Learning a Domain-Agnostic Visual Representation for Autonomous Driving via Contrastive Loss by Dongseok Shim et al
03-11-2021	Intraclass clustering: an implicit learning ability that regularizes DNNs by Carbonnelle Simon et al
03-09-2021	QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information by Masato Tamura et al
03-10-2021	A Computed Tomography Vertebral Segmentation Dataset with Anatomical Variations and Multi-Vendor Scanner Data by Hans Liebl et al
03-10-2021	Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representations by Umberto Michieli et al
03-11-2021	PointFlow: Flowing Semantics Through Points for Aerial Image Segmentation by Xiangtai Li et al
03-10-2021	Towards Learning an Unbiased Classifier from Biased Data via Conditional Adversarial Debiasing by Christian Reimers et al
03-10-2021	Enhancing VMAF through New Feature Integration and Model Combination by Fan Zhang et al
03-11-2021	Fast Hyperspectral Image Denoising and Inpainting Based on Low-Rank and Sparse Representations by Lina Zhuang et al
03-10-2021	Robust 2D/3D Vehicle Parsing in CVIS by Hui Miao et al
03-11-2021	Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition by Shancheng Fang et al
03-11-2021	Coming Down to Earth: Satellite-to-Street View Synthesis for Geo-Localization by Aysim Toker et al
03-09-2021	Open-book Video Captioning with Retrieve-Copy-Generate Network by Ziqi Zhang et al
03-11-2021	Real-Time Surface Fitting to RGBD Sensor Data by John Papadakis et al
03-09-2021	unzipFPGA: Enhancing FPGA-based CNN Engines with On-the-Fly Weights Generation by Stylianos I. Venieris et al
03-11-2021	Large Batch Simulation for Deep Reinforcement Learning by Brennan Shacklett et al
03-11-2021	Duplex Contextual Relation Network for Polyp Segmentation by Zijin Yin et al
03-11-2021	Level-aware Haze Image Synthesis by Self-Supervised Content-Style Disentanglement by Chi Zhang et al
03-09-2021	Probabilistic Modeling of Semantic Ambiguity for Scene Graph Generation by Gengcong Yang et al
03-09-2021	BASAR:Black-box Attack on Skeletal Action Recognition by Yunfeng Diao et al
03-11-2021	PREPRINT: Comparison of deep learning and hand crafted features for mining simulation data by Theodoros Georgiou et al
03-10-2021	Deep Convolutional Sparse Coding Network for Pansharpening with Guidance of Side Information by Shuang Xu et al
03-09-2021	Fusing Medical Image Features and Clinical Features with Deep Learning for Computer-Aided Diagnosis by Songxiao Yang et al
03-09-2021	Novel tile segmentation scheme for omnidirectional video by Jisheng Li et al
03-10-2021	Quantization-Guided Training for Compact TinyML Models by Sedigh Ghamari et al
03-09-2021	AutoDO: Robust AutoAugment for Biased Data with Label Noise via Scalable Probabilistic Implicit Differentiation by Denis Gudovskiy et al
03-10-2021	TransMed: Transformers Advance Multi-modal Medical Image Classification by Yin Dai et al
03-10-2021	A registration error estimation framework for correlative imaging by Guillaume Potier et al
03-10-2021	MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks by Alexandre Rame et al
03-11-2021	Temporal Action Segmentation from Timestamp Supervision by Zhe Li et al
03-11-2021	Vision Transformer for COVID-19 CXR Diagnosis using Chest X-ray Feature Corpus by Sangjoon Park et al
03-09-2021	ST3D: Self-training for Unsupervised Domain Adaptation on 3D ObjectDetection by Jihan Yang et al
03-11-2021	Calibrated and Partially Calibrated Semi-Generalized Homographies by Snehal Bhayani et al
03-09-2021	Manifold Regularized Dynamic Network Pruning by Yehui Tang et al
03-09-2021	Practical Relative Order Attack in Deep Ranking by Mo Zhou et al
03-11-2021	A learning-based view extrapolation method for axial super-resolution by Zhaolin Xiao et al
03-09-2021	Stabilized Medical Image Attacks by Gege Qi et al
03-09-2021	Reframing Neural Networks: Deep Structure in Overcomplete Representations by Calvin Murdock et al
03-09-2021	Doubly Contrastive Deep Clustering by Zhiyuan Dang et al
03-10-2021	Deep Superpixel Cut for Unsupervised Image Segmentation by Qinghong Lin et al
03-10-2021	U-Net Transformer: Self and Cross Attention for Medical Image Segmentation by Olivier Petit et al
03-12-2021	Multiview Sensing With Unknown Permutations: An Optimal Transport Approach by Yanting Ma et al
03-09-2021	Selective and Features based Adversarial Example Detection by Ahmed Aldahdooh et al
03-09-2021	A Mask R-CNN approach to counting bacterial colony forming units in pharmaceutical development by Tanguy Naets et al
03-11-2021	ChallenCap: Monocular 3D Capture of Challenging Human Performances using Multi-Modal References by Yannan He et al
03-10-2021	Structure-From-Motion and RGBD Depth Fusion by Akash Chandrashekar et al
03-09-2021	Learning Class-Agnostic Pseudo Mask Generation for Box-Supervised Semantic Segmentation by Chaohao Xie et al
03-10-2021	Limitations of Post-Hoc Feature Alignment for Robustness by Collin Burns et al
03-10-2021	An Image-based Approach of Task-driven Driving Scene Categorization by Shaochi Hu et al
03-09-2021	NaroNet: Objective-based learning of the tumor microenvironment from highly multiplexed immunostained images by Daniel Jiménez-Sánchez et al
03-09-2021	Instance and Pair-Aware Dynamic Networks for Re-Identification by Bingliang Jiao et al
03-09-2021	Weather GAN: Multi-Domain Weather Translation Using Generative Adversarial Networks by Xuelong Li et al
03-09-2021	Deep and Statistical Learning in Biomedical Imaging: State of the Art in 3D MRI Brain Tumor Segmentation by K. Ruwani M. Fernando et al
03-09-2021	FAIR1M: A Benchmark Dataset for Fine-grained Object Recognition in High-Resolution Remote Sensing Imagery by Xian Sun et al
03-09-2021	DeepSeagrass Dataset by Scarlett Raine et al
03-09-2021	Bio-Inspired Representation Learning for Visual Attention Prediction by Yuan Yuan et al
03-09-2021	Pluggable Weakly-Supervised Cross-View Learning for Accurate Vehicle Re-Identification by Lu Yang et al
03-09-2021	Thumbnail: A Novel Data Augmentation for Convolutional Neural Network by Tianshu Xie et al
03-12-2021	Searching by Generating: Flexible and Efficient One-Shot NAS with Architecture Generator by Sian-Yao Huang et al
03-10-2021	Deep Sensing of Urban Waterlogging by Shi-Wei Lo
03-10-2021	MapFusion: A General Framework for 3D Object Detection with HDMaps by Jin Fang et al
03-09-2021	Exploiting Edge-Oriented Reasoning for 3D Point-based Scene Graph Analysis by Chaoyi Zhang et al
03-09-2021	TS-Net: OCR Trained to Switch Between Text Transcription Styles by Jan Kohút et al
03-10-2021	Quality-Aware Network for Human Parsing by Lu Yang et al
03-09-2021	Enhancing sensor resolution improves CNN accuracy given the same number of parameters or FLOPS by Ali Borji
03-09-2021	MetaCorrection: Domain-aware Meta Loss Correction for Unsupervised Domain Adaptation in Semantic Segmentation by Xiaoqing Guo et al
03-10-2021	Tuna Nutriment Tracking using Trajectory Mapping in Application to Aquaculture Fish Tank by Hilmil Pradana et al
03-10-2021	Regressive Domain Adaptation for Unsupervised Keypoint Detection by Junguang Jiang et al
03-09-2021	PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency by Xuyang Bai et al
03-10-2021	Weak labels and anatomical knowledge: making deep learning practical for intracranial aneurysm detection in TOF-MRA by Tommaso Di Noto et al
03-09-2021	Learning to Estimate Kernel Scale and Orientation of Defocus Blur with Asymmetric Coded Aperture by Jisheng Li et al

03-10-2021	ES-Net: Erasing Salient Parts to Learn More in Re-Identification by Dong Shen et al
03-09-2021	Quadruple Augmented Pyramid Network for Multi-class COVID-19 Segmentation via CT by Ziyang Wang
03-10-2021	Spatiotemporal Registration for Event-based Visual Odometry by Daqi Liu Alvaro Parra et al
03-10-2021	COLA-Net: Collaborative Attention Network for Image Restoration by Chong Mou et al
03-09-2021	ChangeSim: Towards End-to-End Online Scene Change Detection in Industrial Indoor Environments by Jin-Man Park et al
03-09-2021	MWQ: Multiscale Wavelet Quantized Neural Networks by Qigong Sun et al
03-09-2021	Point-supervised Segmentation of Microscopy Images and Volumes via Objectness Regularization by Shijie Li et al
03-10-2021	Spatial Attention-based Non-reference Perceptual Quality Prediction Network for Omnidirectional Images by Li Yang et al
03-10-2021	Model-inspired Deep Learning for Light-Field Microscopy with Application to Neuron Localization by Pingfan Song et al
03-10-2021	RL-CSDia: Representation Learning of Computer Science Diagrams by Shaowei Wang et al
03-12-2021	VDSM: Unsupervised Video Disentanglement with State-Space Modeling and Deep Mixtures of Experts by Matthew J. Vowels et al
03-09-2021	Understanding the Robustness of Skeleton-based Action Recognition under Adversarial Attack by He Wang et al
03-09-2021	3D-QCNet -- A Pipeline for Automated Artifact Detection in Diffusion MRI images by Adnan Ahmad et al
03-10-2021	DSEC: A Stereo Event Camera Dataset for Driving Scenarios by Mathias Gehrig et al
03-09-2021	Generalizable Limited-Angle CT Reconstruction via Sinogram Extrapolation by Ce Wang et al
03-09-2021	2D histology meets 3D topology: Cytoarchitectonic brain mapping with Graph Neural Networks by Christian Schiffer et al
03-10-2021	Evaluating COPY-BLEND Augmentation for Low Level Vision Tasks by Pranjay Shyam et al
03-09-2021	Self-Supervision by Prediction for Object Discovery in Videos by Beril Besbinar et al
03-10-2021	Reformulating HOI Detection as Adaptive Set Prediction by Mingfei Chen et al
03-10-2021	SAR-U-Net: squeeze-and-excitation block and atrous spatial pyramid pooling based residual U-Net for automatic liver CT segmentation by Jinke Wang et al
03-10-2021	Model-free Vehicle Tracking and State Estimation in Point Cloud Sequences by Ziqi Pang et al
03-10-2021	AttaNet: Attention-Augmented Network for Fast and Accurate Scene Parsing by Qi Song et al
03-09-2021	PcmNet: Position-Sensitive Context Modeling Network for Temporal Action Localization by Xin Qin et al
03-09-2021	Learning to compose 6-DoF omnidirectional videos using multi-sphere images by Jisheng Li et al
03-10-2021	Adversarial Regression Learning for Bone Age Estimation by Youshan Zhang et al
03-10-2021	Beyond Self-Supervision: A Simple Yet Effective Network Distillation Alternative to Improve Backbones by Cheng Cui et al
03-10-2021	Sim2Real 3D Object Classification using Spherical Kernel Point Convolution and a Deep Center Voting Scheme by Jean-Baptiste Weibel et al
03-10-2021	A Relational-learning Perspective to Multi-label Chest X-ray Classification by Anjany Sekuboyina et al
03-09-2021	Uncertainty-aware Incremental Learning for Multi-organ Segmentation by Yuhang Zhou et al
03-10-2021	SDD-FIQA: Unsupervised Face Image Quality Assessment with Similarity Distribution Distance by Fu-Zhao Ou et al
03-10-2021	Time-Ordered Recent Event (TORE) Volumes for Event Cameras by R. Wes Baldwin et al
03-12-2021	Thousand to One: Semantic Prior Modeling for Conceptual Coding by Jianhui Chang et al
03-09-2021	Structural Connectome Atlas Construction in the Space of Riemannian Metrics by Kristen M. Campbell et al
03-10-2021	Automated liver tissues delineation based on machine learning techniques: A survey, current trends and future orientations by Ayman Al-Kababji et al
03-12-2021	Robust and generalizable embryo selection based on artificial intelligence and time-lapse image sequences by Jørgen Berntsen et al
03-10-2021	Principal component-based image segmentation: a new approach to outline in vitro cell colonies by Delmon Arous et al
03-10-2021	Cross-modal Image Retrieval with Deep Mutual Information Maximization by Chunbin Gu et al
03-10-2021	Multi-Pretext Attention Network for Few-shot Learning with Self-supervision by Hainan Li et al
03-10-2021	Wide Aspect Ratio Matching for Robust Face Detection by Shi Luo et al
03-09-2021	Incorporating Orientations into End-to-end Driving Model for Steering Control by Peng Wan et al
03-12-2021	Neural Reprojection Error: Merging Feature Learning and Camera Pose Estimation by Hugo Germain et al
03-09-2021	Pixel-wise Distance Regression for Glacier Calving Front Detection and Segmentation by Amirabbas Davari et al
03-11-2021	Interleaving Learning, with Application to Neural Architecture Search by Hao Ban et al
03-12-2021	Game-theoretic Understanding of Adversarially Learned Features by Jie Ren et al
03-12-2021	Learnable Companding Quantization for Accurate Low-bit Neural Networks by Kohei Yamamoto
03-12-2021	Deep Gaussian Scale Mixture Prior for Spectral Compressive Imaging by Tao Huang et al
03-12-2021	PVStereo: Pyramid Voting Module for End-to-End Self-Supervised Stereo Matching by Hengli Wang et al
03-11-2021	iToF2dToF: A Robust and Flexible Representation for Data-Driven Time-of-Flight Imaging by Felipe Gutierrez-Barragan et al
03-09-2021	Content-Preserving Unpaired Translation from Simulated to Realistic Ultrasound Images by Devavrat Tomar et al
03-11-2021	DP-Image: Differential Privacy for Image Data in Feature Space by Bo Liu et al
03-11-2021	Severity Quantification and Lesion Localization of COVID-19 on CXR using Vision Transformer by Gwanghyun Kim et al
03-09-2021	A Multi-resolution Approach to Expression Recognition in the Wild by Fabio Valerio Massoli et al
03-12-2021	UIEC^2-Net: CNN-based Underwater Image Enhancement Using Two Color Space by Yudong Wang et al
03-09-2021	Capturing Omni-Range Context for Omnidirectional Segmentation by Kailun Yang et al
03-09-2021	Multitask 3D CBCT-to-CT Translation and Organs-at-Risk Segmentation Using Physics-Based Data Augmentation by Navdeep Dahiya et al
03-11-2021	CRFace: Confidence Ranker for Model-Agnostic Face Detection Refinement by Noranart Vesdapunt et al
03-12-2021	In the light of feature distributions: moment matching for Neural Style Transfer by Nikolai Kalischek et al
03-10-2021	Are we using appropriate segmentation metrics? Identifying correlates of human expert perception for CNN training beyond rolling the DICE coefficient by Florian Kofler et al
03-11-2021	The Semi-Supervised iNaturalist-Aves Challenge at FGVC7 Workshop by Jong-Chyi Su et al
03-10-2021	Face Images as Jigsaw Puzzles: Compositional Perception of Human Faces for Machines Using Generative Adversarial Networks by Mahla Abdolahnejad et al
03-12-2021	Siamese Infrared and Visible Light Fusion Network for RGB-T Tracking by Peng Jingchao et al
03-12-2021	Real-time Nonrigid Mosaicking of Laparoscopy Images by Haoyin Zhou et al
03-11-2021	DefakeHop: A Light-Weight High-Performance Deepfake Detector by Hong-Shuo Chen et al
03-12-2021	Information Maximization Clustering via Multi-View Self-Labelling by Foivos Ntelemis et al
03-11-2021	CORSAIR: Convolutional Object Retrieval and Symmetry-AIded Registration by Tianyu Zhao et al
03-11-2021	FS-Net: Fast Shape-based Network for Category-Level 6D Object Pose Estimation with Decoupled Rotation Mechanism by Wei Chen et al
03-12-2021	Hyperspectral Image Denoising and Anomaly Detection Based on Low-rank and Sparse Representations by Lina Zhuang et al
03-11-2021	Dual Attention-in-Attention Model for Joint Rain Streak and Raindrop Removal by Kaihao Zhang et al
03-11-2021	Advanced Multiple Linear Regression Based Dark Channel Prior Applied on Dehazing Image and Generating Synthetic Haze by Binghan Li et al
03-12-2021	Learning Long-Term Style-Preserving Blind Video Temporal Consistency by Hugo Thimonier et al
03-12-2021	Patient-specific virtual spine straightening and vertebra inpainting: An automatic framework for osteoplasty planning by Christina Bukas et al
03-11-2021	Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusion by Shi Qiu et al
03-12-2021	Urban Surface Reconstruction in SAR Tomography by Graph-Cuts by Clément Rambour et al
03-11-2021	DualPoseNet: Category-level 6D Object Pose and Size Estimation using Dual Pose Network with Refined Learning of Pose Consistency by Jiehong Lin et al
03-12-2021	3D Semantic Scene Completion: a Survey by Luis Roldao et al
03-12-2021	Deep Dual Consecutive Network for Human Pose Estimation by Zhenguang Liu et al
03-10-2021	FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Space by Quande Liu et al
03-12-2021	Discriminative Region Suppression for Weakly-Supervised Semantic Segmentation by Beomyoung Kim et al
03-12-2021	Seeking the Shape of Sound: An Adaptive Framework for Learning Voice-Face Association by Peisong Wen et al
03-12-2021	Sequential Random Network for Fine-grained Image Classification by Chaorong Li et al
03-12-2021	Longitudinal Quantitative Assessment of COVID-19 Infection Progression from Chest CTs by Seong Tae Kim et al
03-11-2021	Efficient Pairwise Neuroimage Analysis using the Soft Jaccard Index and 3D Keypoint Sets by Laurent Chauvin et al
03-12-2021	Monocular Quasi-Dense 3D Object Tracking by Hou-Ning Hu et al
03-12-2021	Self-Feature Regularization: Self-Feature Distillation Without Teacher Models by Wenxuan Fan et al
03-11-2021	ACTION-Net: Multipath Excitation for Action Recognition by Zhengwei Wang et al
03-10-2021	PatchNet -- Short-range Template Matching for Efficient Video Processing by Huizi Mao et al
03-11-2021	Continuous 3D Multi-Channel Sign Language Production via Progressive Transformers and Mixture Density Networks by Ben Saunders et al
03-12-2021	PLADE-Net: Towards Pixel-Level Accuracy for Self-Supervised Single-View Depth Estimation with Neural Positional Encoding and Distilled Matting Loss by Juan Luis Gonzalez Bello et al
03-12-2021	Radiomic Deformation and Textural Heterogeneity (R-DepTH) Descriptor to characterize Tumor Field Effect: Application to Survival Prediction in Glioblastoma by Marwa Ismail et al
03-12-2021	Juggling With Representations: On the Information Transfer Between Imagery, Point Clouds, and Meshes for Multi-Modal Semantics by Dominik Laupheimer et al
03-11-2021	The Location of Optimal Object Colors with More Than Two Transitions by Scott A. Burns
03-11-2021	An Efficient Hypergraph Approach to Robust Point Cloud Resampling by Qinwen Deng et al