2021.1.25 Vision papers

01-21-2021	Characterizing signal propagation to close the performance gap in unnormalized ResNets by Andrew Brock et al
01-21-2021	Learn to Dance with AIST++: Music Conditioned 3D Dance Generation by Ruilong Li et al
01-21-2021	Expectation-Maximization Regularized Deep Learning for Weakly Supervised Tumor Segmentation for Glioblastoma by Chao Li et al
01-21-2021	DAF:re: A Challenging, Crowd-Sourced, Large-Scale, Long-Tailed Dataset For Anime Character Recognition by Edwin Arkel Rios et al
01-21-2021	Pre-training without Natural Images by Hirokatsu Kataoka et al
01-21-2021	SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation by Brendan Duke et al
01-20-2021	Aesthetics, Personalization and Recommendation: A survey on Deep Learning in Fashion by Wei Gong et al
01-20-2021	SplitSR: An End-to-End Approach to Super-Resolution on Mobile Devices by Xin Liu et al
01-19-2021	JigsawGAN: Self-supervised Learning for Solving Jigsaw Puzzles with Generative Adversarial Networks by Ru Li et al
01-19-2021	Classification of COVID-19 X-ray Images Using a Combination of Deep and Handcrafted Features by Weihan Zhang et al
01-20-2021	Can stable and accurate neural networks be computed? -- On the barriers of deep learning and Smales 18th problem by Vegard Antun et al
01-20-2021	Generative Zero-shot Network Quantization by Xiangyu He et al
01-19-2021	Quantum Permutation Synchronization by Tolga Birdal et al
01-21-2021	Activity Graph Transformer for Temporal Action Localization by Megha Nawhal et al
01-19-2021	LowKey: Leveraging Adversarial Attacks to Protect Social Media Users from Facial Recognition by Valeriia Cherepanova et al
01-21-2021	Segmenting Transparent Object in the Wild with Transformer by Enze Xie et al
01-21-2021	Copycat CNN: Are Random Non-Labeled Data Enough to Steal Knowledge from Black-box Models? by Jacson Rodrigues Correia-Silva et al
01-20-2021	MoG-QSM: Model-based Generative Adversarial Deep Learning Network for Quantitative Susceptibility Mapping by Ruimin Feng et al
01-20-2021	Analysis of Information Flow Through U-Nets by Suemin Lee et al
01-21-2021	ItNet: iterative neural networks with tiny graphs for accurate and efficient anytime prediction by Thomas Pfeil
01-20-2021	Learning Ultrasound Rendering from Cross-Sectional Model Slices for Simulated Training by Lin Zhang et al
01-21-2021	Image-to-Image Translation: Methods and Applications by Yingxue Pang et al
01-21-2021	Self-Adaptive Training: Bridging the Supervised and Self-Supervised Learning by Lang Huang et al
01-21-2021	Exponential Moving Average Normalization for Self-supervised and Semi-supervised Learning by Zhaowei Cai et al
01-21-2021	Fast and Robust Certifiable Estimation of the Relative Pose Between Two Calibrated Cameras by Mercedes Garcia-Salguero et al
01-20-2021	Nonparametric clustering for image segmentation by Giovanna Menardi
01-21-2021	MPASNET: Motion Prior-Aware Siamese Network for Unsupervised Deep Crowd Segmentation in Video Scenes by Jinhai Yang et al
01-20-2021	Chest X-ray lung and heart segmentation based on minimal training sets by Balázs Maga
01-21-2021	A two-stage data association approach for 3D Multi-object Tracking by Minh-Quan Dao et al
01-20-2021	Rethinking Semantic Segmentation Evaluation for Explainability and Model Selection by Yuxiang Zhang et al
01-21-2021	Progressive Co-Attention Network for Fine-grained Visual Classification by Tian Zhang et al
01-21-2021	Regularization via deep generative models: an analysis point of view by Thomas Oberlin et al
01-21-2021	Fire Threat Detection From Videos with Q-Rough Sets by Debarati B. Chakrabortya et al
01-20-2021	TDA-Net: Fusion of Persistent Homology and Deep Learning Features for COVID-19 Detection in Chest X-Ray Images by Mustafa Hajij et al
01-19-2021	Momentum^2 Teacher: Momentum Teacher with Momentum Statistics for Self-Supervised Learning by Zeming Li et al
01-22-2021	Progressive Image Super-Resolution via Neural Differential Equation by Seobin Park et al
01-20-2021	Video Summarization: Study of various techniques by Ravi Raj et al
01-19-2021	Comparative Evaluation of 3D and 2D Deep Learning Techniques for Semantic Segmentation in CT Scans by Abhishek Shivdeo et al
01-21-2021	Weighted Fuzzy-Based PSNR for Watermarking by Maedeh Jamali et al
01-21-2021	Anti-UAV: A Large Multi-Modal Benchmark for UAV Tracking by Nan Jiang et al
01-20-2021	Finger Vein Recognition by Generating Code by Zhongxia Zhang et al
01-21-2021	Discovering Multi-Label Actor-Action Association in a Weakly Supervised Setting by Sovan Biswas et al
01-21-2021	GhostSR: Learning Ghost Features for Efficient Image Super-Resolution by Ying Nie et al
01-19-2021	Machine-Generated Hierarchical Structure of Human Activities to Reveal How Machines Think by Mahsun Altın et al
01-21-2021	Geometric Moment Invariants to Motion Blur by Hongxiang Hao et al
01-21-2021	An Effective Data Augmentation for Person Re-identification by Yunpeng Gong et al
01-20-2021	Text Line Segmentation for Challenging Handwritten Document Images Using Fully Convolutional Network by Berat Barakat et al
01-21-2021	COLLIDE-PRED: Prediction of On-Road Collision From Surveillance Videos by Deesha Chavan et al
01-21-2021	CM-NAS: Rethinking Cross-Modality Neural Architectures for Visible-Infrared Person Re-Identification by Chaoyou Fu et al
01-22-2021	Towards Enhancing Fine-grained Details for Image Matting by Chang Liu et al
01-21-2021	Hierarchical Graph-RNNs for Action Detection of Multiple Activities by Sovan Biswas et al
01-19-2021	Unsupervised Domain Adaptation from Axial to Short-Axis Multi-Slice Cardiac MR Images by Incorporating Pretrained Task Networks by Sven Koehler et al
01-21-2021	All-Day Object Tracking for Unmanned Aerial Vehicle by Bowen Li et al
01-21-2021	Cain: Automatic Code Generation for Simultaneous Convolutional Kernels on Focal-plane Sensor-processors by Edward Stow et al
01-20-2021	Bridge the Vision Gap from Field to Command: A Deep Learning Network Enhancing Illumination and Details by Zhuqing Jiang et al
01-19-2021	The Devils in the Point Clouds: Studying the Robustness of Point Cloud Convolutions by Xingyi Li et al
01-21-2021	Iterative Optimisation with an Innovation CNN for Pose Refinement by Gerard Kennedy et al
01-21-2021	Generative Replay-based Continual Zero-Shot Learning by Chandan Gautam et al
01-22-2021	DSAL: Deeply Supervised Active Learning from Strong and Weak Labelers for Biomedical Image Segmentation by Ziyuan Zhao et al
01-20-2021	Scalable Deep Compressive Sensing by Zhonghao Zhang et al
01-19-2021	DyLoc: Dynamic Localization for Massive MIMO Using Predictive Recurrent Neural Networks by Farzam Hejazi et al
01-19-2021	IntentNet: Learning to Predict Intention from Raw Sensor Data by Sergio Casas et al
01-19-2021	Salient Object Detection via Integrity Learning by Mingchen Zhuge et al
01-19-2021	Quarter Laplacian Filter for Edge Aware Image Processing by Yuanhao Gong et al
01-22-2021	Expression Recognition Analysis in the Wild by Donato Cafarelli et al
01-20-2021	Component Tree Loss Function: Definition and Optimization by Benjamin Perret et al
01-22-2021	Rethinking Domain Generalization Baselines by Francesco Cappio Borlino et al
01-20-2021	Focal and Efficient IOU Loss for Accurate Bounding Box Regression by Yi-Fan Zhang et al
01-19-2021	The Unreasonable Effectiveness of Patches in Deep Convolutional Kernels Methods by Louis Thiry et al
01-19-2021	Hyperspectral Image Restoration via Multi-mode and Double-weighted Tensor Nuclear Norm Minimization by Sheng Liu et al
01-22-2021	Human Interaction Recognition Framework based on Interacting Body Part Attention by Dong-Gyu Lee et al
01-22-2021	Understanding Visual Saliency in Mobile User Interfaces by Luis A. Leiva et al
01-22-2021	Solving the Same-Different Task with Convolutional Neural Networks by Nicola Messina et al
01-20-2021	Non-Parametric Adaptive Network Pruning by Lin Mingbao et al
01-19-2021	Unsupervised Deep Learning for Handwritten Page Segmentation by Ahmad Droby et al
01-19-2021	A Discrete Scheme for Computing Images Weighted Gaussian Curvature by Yuanhao Gong et al
01-21-2021	A Two-stream Neural Network for Pose-based Hand Gesture Recognition by Chuankun Li et al
01-21-2021	A Spike Learning System for Event-driven Object Recognition by Shibo Zhou et al
01-19-2021	A survey on shape-constraint deep learning for medical image segmentation by Simon Bohlender et al
01-20-2021	Macroscopic Control of Text Generation for Image Captioning by Zhangzi Zhu et al
01-20-2021	Improved Signed Distance Function for 2D Real-time SLAM and Accurate Localization by Xingyin Fu et al
01-20-2021	Few-shot Action Recognition with Prototype-centered Attentive Learning by Xiatian Zhu et al
01-22-2021	A Universal Deep Learning Framework for Real-Time Denoising of Ultrasound Images by Simone Cammarasana et al
01-22-2021	Automatic Cerebral Vessel Extraction in TOF-MRA Using Deep Learning by V. de Vos et al
01-19-2021	Feature Sharing Cooperative Network for Semantic Segmentation by Ryota Ikedo et al
01-19-2021	Multi-Task Network Pruning and Embedded Optimization for Real-time Deployment in ADAS by Flora Dellinger et al
01-22-2021	A Closer Look at Temporal Sentence Grounding in Videos: Datasets and Metrics by Yitian Yuan et al
01-21-2021	Hessian-Aware Pruning and Optimal Neural Implant by Shixing Yu et al
01-22-2021	Hybrid Rotation Averaging: A Globally Guaranteed Fast and Robust Rotation Averaging Approach by Yu Chen et al
01-22-2021	Cross Chest Graph for Disease Diagnosis with Structural Relational Reasoning by Gangming Zhao et al
01-22-2021	Visual Question Answering based on Local-Scene-Aware Referring Expression Generation by Jung-Jun Kim et al
01-20-2021	Semi-supervised Keypoint Localization by Olga Moskvyak et al
01-21-2021	AS-Net: Fast Photoacoustic Reconstruction with Multi-feature Fusion from Sparse Data by Mengjie Guo et al
01-21-2021	Occlusion Handling in Generic Object Detection: A Review by Kaziwa Saleh et al
01-19-2021	Cross-domain few-shot learning with unlabelled data by Fupin Yao
01-21-2021	Snapshot Hyperspectral Imaging Based on Weighted High-order Singular Value Regularization by Niankai Cheng et al
01-19-2021	VML-MOC: Segmenting a multiply oriented and curved handwritten text lines dataset by Berat Kurar Barakat et al
01-20-2021	Variational Autoencoders with a Structural Similarity Loss in Time of Flight MRAs by Kimberley M. Timmins et al
01-19-2021	Beyond Fine-tuning: Classifying High Resolution Mammograms using Function-Preserving Transformations by Tao Wei et al
01-22-2021	Dense outlier detection and open-set recognition based on training with noisy negative images by Petra Bevandić et al
01-19-2021	Class balanced underwater object detection dataset generated by class-wise style augmentation by Long Chen et al
01-19-2021	Using StyleGAN for Visual Interpretability of Deep Learning Models on Medical Images by Kathryn Schutte et al
01-19-2021	A modular vision language navigation and manipulation framework for long horizon compositional tasks in indoor environment by Homagni Saha et al
01-19-2021	Joint Learning of 3D Shape Retrieval and Deformation by Mikaela Angelina Uy et al
01-20-2021	TCLR: Temporal Contrastive Learning for Video Representation by Ishan Dave et al
01-22-2021	Personal Fixations-Based Object Segmentation with Object Localization and Boundary Preservation by Gongyang Li et al
01-19-2021	BANet: Blur-aware Attention Networks for Dynamic Scene Deblurring by Fu-Jen Tsai et al
01-20-2021	FedNS: Improving Federated Learning for collaborative image classification on mobile clients by Yaoxin Zhuo et al
01-19-2021	Intelligent Frame Selection as a Privacy-Friendlier Alternative to Face Recognition by Mattijs Baert et al
01-22-2021	Automatic Volumetric Segmentation of Additive Manufacturing Defects with 3D U-Net by Vivian Wen Hui Wong et al
01-21-2021	Analyzing Epistemic and Aleatoric Uncertainty for Drusen Segmentation in Optical Coherence Tomography Images by Tinu Theckel Joy et al
01-20-2021	Fast deep learning correspondence for neuron tracking and identification in C.elegans using synthetic training by Xinwei Yu et al
01-19-2021	Online Active Proposal Set Generation for Weakly Supervised Object Detection by Ruibing Jin et al
01-21-2021	Bridging the gap between Human Action Recognition and Online Action Detection by Alban Main de Boissiere et al
01-19-2021	Real-Time Limited-View CT Inpainting and Reconstruction with Dual Domain Based on Spatial Information by Ken Deng et al
01-20-2021	1st Place Solution to ECCV-TAO-2020: Detect and Represent Any Object for Tracking by Fei Du et al
01-19-2021	A Lightweight Structure Aimed to Utilize Spatial Correlation for Sparse-View CT Reconstruction by Yitong Liu et al
01-20-2021	Self-supervised pre-training enhances change detection in Sentinel-2 imagery by Marrit Leenstra et al
01-19-2021	Predicting Pneumonia and Region Detection from X-Ray Images using Deep Neural Network by Sheikh Md Hanif Hossain et al
01-19-2021	Meningioma segmentation in T1-weighted MRI leveraging global context and attention mechanisms by David Bouget et al
01-20-2021	Semantic Disentangling Generalized Zero-ShotLearning by Zhi Chen et al
01-20-2021	Cell image segmentation by Feature Random Enhancement Module by Takamasa Ando et al
01-19-2021	Multi-target detection with rotations by Tamir Bendory et al
01-19-2021	Attention-Guided Black-box Adversarial Attacks with Large-Scale Multiobjective Evolutionary Optimization by Jie Wang et al
01-19-2021	Collaboration among Image and Object Level Features for Image Colourisation by Rita Pucci et al
01-22-2021	B-DRRN: A Block Information Constrained Deep Recursive Residual Network for Video Compression Artifacts Reduction by Trinh Man Hoang et al
01-19-2021	PICA: A Pixel Correlation-based Attentional Black-box Adversarial Attack by Jie Wang et al
01-21-2021	Virtual laser scanning with HELIOS++: A novel take on ray tracing-based simulation of topographic 3D laser scanning by Lukas Winiwarter et al
01-20-2021	Video Relation Detection with Trajectory-aware Multi-modal Features by Wentao Xie et al
01-19-2021	AXM-Net: Cross-Modal Context Sharing Attention Network for Person Re-ID by Ammarah Farooq et al
01-20-2021	Fooling thermal infrared pedestrian detectors in real world using small bulbs by Xiaopei Zhu et al
01-19-2021	Hyperspectral Image Super-Resolution with Spectral Mixup and Heterogeneous Datasets by Ke Li et al
01-20-2021	SAR and Optical data fusion based on Anisotropic Diffusion with PCA and Classification using Patch-based with LBP by Achala Shakya et al
01-21-2021	FWB-Net:Front White Balance Network for Color Shift Correction in Single Image Dehazing via Atmospheric Light Estimation by Cong Wang et al
01-19-2021	Human Action Recognition Based on Multi-scale Feature Maps from Depth Video Sequences by Chang Li et al
01-19-2021	Object Tracking by Detection with Visual and Motion Cues by Niels Ole Salscheider
01-19-2021	Deep Learning Models for Calculation of Cardiothoracic Ratio from Chest Radiographs for Assisted Diagnosis of Cardiomegaly by Tanveer Gupte et al
01-19-2021	Deep Feedback Inverse Problem Solver by Wei-Chiu Ma et al
01-19-2021	An Improvement of Object Detection Performance using Multi-step Machine Learnings by Tomoe Kishimoto et al
01-19-2021	Hyperdimensional computing as a framework for systematic aggregation of image descriptors by Peer Neubert et al
01-21-2021	A Person Re-identification Data Augmentation Method with Adversarial Defense Effect by Yunpeng Gong et al
01-19-2021	On The Consistency Training for Open-Set Semi-Supervised Learning by Huixiang Luo et al
01-21-2021	Single Neuron Segmentation using Graph-based Global Reasoning with Auxiliary Skeleton Loss from 3D Optical Microscope Images by Heng Wang et al