2021.11.22 Vision papers

11-18-2021	TransMix: Attend to Mix for Vision Transformers by Jie-Neng Chen et al
11-19-2021	FastDOG: Fast Discrete Optimization on GPU by Ahmed Abbas et al
11-19-2021	Enhanced countering adversarial attacks via input denoising and feature restoring by Yanni Li et al
11-19-2021	Evaluating Self and Semi-Supervised Methods for Remote Sensing Segmentation Tasks by Chaitanya Patel et al
11-19-2021	A 3D 2D convolutional Neural Network Model for Hyperspectral Image Classification by Jiaxin Cao et al
11-19-2021	Probabilistic Regression with Huber Distributions by David Mohlin et al
11-17-2021	Lidar with Velocity: Motion Distortion Correction of Point Clouds from Oscillating Scanning Lidars by Wen Yang et al
11-17-2021	Reference-based Magnetic Resonance Image Reconstruction Using Texture Transforme by Pengfei Guo et al
11-17-2021	Quality Measures in Biometric Systems by Fernando Alonso-Fernandez et al
11-16-2021	Automated Atlas-based Segmentation of Single Coronal Mouse Brain Slices using Linear 2D-2D Registration by Sébastien Piluso et al
11-17-2021	The Multiscenario Multienvironment BioSecure Multimodal Database (BMDB) by Javier Ortega-Garcia et al
11-17-2021	Benchmarking Quality-Dependent and Cost-Sensitive Score-Level Multimodal Biometric Fusion Algorithms by Norman Poh et al
11-16-2021	Exploring dual-attention mechanism with multi-scale feature extraction scheme for skin lesion segmentation by G Jignesh Chowdary et al
11-17-2021	Dynamically pruning segformer for efficient semantic segmentation by Haoli Bai et al
11-17-2021	Low Precision Decentralized Distributed Training with Heterogeneous Data by Sai Aparna Aketi et al
11-17-2021	Learning to Align Sequential Actions in the Wild by Weizhe Liu et al
11-17-2021	Segmentation of Lung Tumor from CT Images using Deep Supervision by Farhanaz Farheen et al
11-16-2021	Fight Detection from Still Images in the Wild by Şeymanur Aktı et al
11-17-2021	DiverGAN: An Efficient and Effective Single-Stage Framework for Diverse Text-to-Image Generation by Zhenxing Zhang et al
11-17-2021	TraSw: Tracklet-Switch Adversarial Attacks against Multi-Object Tracking by Delv Lin et al
11-17-2021	Discriminative Dictionary Learning based on Statistical Methods by G. Madhuri et al
11-16-2021	2.5D Vehicle Odometry Estimation by Ciaran Eising et al
11-19-2021	Deep Domain Adaptation for Pavement Crack Detection by Huijun Liu et al
11-18-2021	Edge-preserving Domain Adaptation for semantic segmentation of Medical Images by Thong Vo et al
11-17-2021	Augmentation of base classifier performance via HMMs on a handwritten character data set by Hélder Campos et al
11-16-2021	GRI: General Reinforced Imitation and its Application to Vision-Based Autonomous Driving by Raphael Chekroun et al
11-16-2021	Tracking Blobs in the Turbulent Edge Plasma of Tokamak Fusion Reactors by Woonghee Han et al
11-17-2021	Towards Open Vocabulary Object Detection without Human-provided Bounding Boxes by Mingfei Gao et al
11-19-2021	Positional Encoder Graph Neural Networks for Geographic Data by Konstantin Klemmer et al
11-16-2021	Online Meta Adaptation for Variable-Rate Learned Image Compression by Wei Jiang et al
11-18-2021	Evaluating Transformers for Lightweight Action Recognition by Raivo Koot et al
11-18-2021	IMFNet: Interpretable Multimodal Fusion for Point Cloud Registration by Xiaoshui Huang et al
11-16-2021	Image-specific Convolutional Kernel Modulation for Single Image Super-resolution by Yuanfei Huang et al
11-16-2021	Two-step adversarial debiasing with partial learning -- medical image case-studies by Ramon Correa et al
11-16-2021	Automatic Semantic Segmentation of the Lumbar Spine. Clinical Applicability in a Multi-parametric and Multi-centre MRI study by Jhon Jairo Saenz-Gamboa et al
11-18-2021	Deep neural networks-based denoising models for CT imaging and their efficacy by Prabhat KC et al
11-17-2021	See Eye to Eye: A Lidar-Agnostic 3D Detection Framework for Unsupervised Multi-Target Domain Adaptation by Darren Tsai et al
11-17-2021	Protection of SVM Model with Secret Key from Unauthorized Access by Ryota Iijima et al
11-17-2021	Using Convolutional Neural Networks to Detect Compression Algorithms by Shubham Bharadwaj
11-19-2021	Meta Adversarial Perturbations by Chia-Hung Yuan et al
11-19-2021	More than Words: In-the-Wild Visually-Driven Prosody for Text-to-Speech by Michael Hassid et al
11-19-2021	Medical Visual Question Answering: A Survey by Zhihong Lin et al
11-16-2021	Choose Settings Carefully: Comparing Action Unit detection at Different Settings Using a Large-Scale Dataset by Mina Bishay et al
11-17-2021	Developing a Machine Learning Algorithm-Based Classification Models for the Detection of High-Energy Gamma Particles by Emmanuel Dadzie et al
11-18-2021	A Trainable Spectral-Spatial Sparse Coding Model for Hyperspectral Image Restoration by Théo Bodrito et al
11-16-2021	Pose Recognition in the Wild: Animal pose estimation using Agglomerative Clustering and Contrastive Learning by Samayan Bhattacharya et al
11-16-2021	SequentialPointNet: A strong parallelized point cloud sequence network for 3D action recognition by Xing Li et al
11-18-2021	Neural Network Kalman filtering for 3D object tracking from linear array ultrasound data by Arttu Arjas et al
11-18-2021	Recurrent Variational Network: A Deep Learning Inverse Problem Solver applied to the task of Accelerated MRI Reconstruction by George Yiasemis et al
11-18-2021	Learning Modified Indicator Functions for Surface Reconstruction by Dong Xiao et al
11-17-2021	Efficient deep learning models for land cover image classification by Ioannis Papoutsis et al
11-16-2021	Deep Neural Networks for Rank-Consistent Ordinal Regression Based On Conditional Probabilities by Xintong Shi et al
11-18-2021	Restormer: Efficient Transformer for High-Resolution Image Restoration by Syed Waqas Zamir et al
11-18-2021	Robust Person Re-identification with Multi-Modal Joint Defence by Yunpeng Gong et al
11-19-2021	Neural Image Beauty Predictor Based on Bradley-Terry Model by Shiyu Li et al
11-18-2021	UFO: A UniFied TransfOrmer for Vision-Language Representation Learning by Jianfeng Wang et al
11-16-2021	Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation by William McNally et al
11-19-2021	DSPoint: Dual-scale Point Cloud Recognition with High-frequency Fusion by Renrui Zhang et al
11-19-2021	Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions by Hongwei Xue et al
11-19-2021	Bi-Mix: Bidirectional Mixing for Domain Adaptive Nighttime Semantic Segmentation by Guanglei Yang et al
11-18-2021	ClipCap: CLIP Prefix for Image Captioning by Ron Mokady et al
11-16-2021	Consistent Semantic Attacks on Optical Flow by Tom Koren et al
11-16-2021	Synthesis-Guided Feature Learning for Cross-Spectral Periocular Recognition by Domenick Poster et al
11-17-2021	RAANet: Range-Aware Attention Network for LiDAR-based 3D Object Detection with Auxiliary Density Level Estimation by Yantao Lu et al
11-16-2021	Keypoint Message Passing for Video-based Person Re-Identification by Di Chen et al
11-16-2021	A Benchmark for Modeling Violation-of-Expectation in Physical Reasoning Across Event Categories by Arijit Dasgupta et al
11-17-2021	Large-scale Building Height Retrieval from Single SAR Imagery based on Bounding Box Regression Networks by Yao Sun et al
11-17-2021	Self-Attending Task Generative Adversarial Network for Realistic Satellite Image Creation by Nathan Toner et al
11-17-2021	Temporally Consistent Online Depth Estimation in Dynamic Scenes by Zhaoshuo Li et al
11-17-2021	Learning to Compose Visual Relations by Nan Liu et al
11-16-2021	HARA: A Hierarchical Approach for Robust Rotation Averaging by Seong Hun Lee et al
11-19-2021	Global and Local Alignment Networks for Unpaired Image-to-Image Translation by Guanglei Yang et al
11-17-2021	Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detection by Nicolae-Catalin Ristea et al
11-18-2021	Meta Clustering Learning for Large-scale Unsupervised Person Re-identification by Xin Jin et al
11-18-2021	DeMFI: Deep Joint Deblurring and Multi-Frame Interpolation with Flow-Guided Attentive Correlation and Recursive Boosting by Jihyong Oh et al
11-19-2021	Toward Compact Parameter Representations for Architecture-Agnostic Neural Network Compression by Yuezhou Sun et al
11-19-2021	Factorisation-based Image Labelling by Yu Yan et al
11-17-2021	Improving Person Re-Identification with Temporal Constraints by Julia Dietlmeier et al
11-18-2021	LOLNeRF: Learn from One Look by Daniel Rebain et al
11-18-2021	Improving Transferability of Representations via Augmentation-Aware Self-Supervision by Hankook Lee et al
11-18-2021	TnT Attacks! Universal Naturalistic Adversarial Patches Against Deep Neural Network Systems by Bao Gia Doan et al
11-17-2021	Motion Detection using CSI from Raspberry Pi 4 by Glenn Forbes et al
11-19-2021	DVCFlow: Modeling Information Flow Towards Human-like Video Captioning by Xu Yan et al
11-17-2021	DeepCurrents: Learning Implicit Representations of Shapes with Boundaries by David Palmer et al
11-17-2021	EMScore: Evaluating Video Captioning via Coarse-Grained and Fine-Grained Embedding Matching by Yaya Shi et al
11-17-2021	Local Texture Estimator for Implicit Representation Function by Jaewon Lee et al
11-17-2021	Long-Tailed Multi-Label Retinal Diseases Recognition Using Hierarchical Information and Hybrid Knowledge Distillation by Lie Ju et al
11-18-2021	FBNetV5: Neural Architecture Search for Multiple Tasks in One Run by Bichen Wu et al
11-18-2021	Perceiving and Modeling Density is All You Need for Image Dehazing by Tian Ye et al
11-18-2021	Swin Transformer V2: Scaling Up Capacity and Resolution by Ze Liu et al
11-18-2021	SimMIM: A Simple Framework for Masked Image Modeling by Zhenda Xie et al
11-18-2021	PyTorchVideo: A Deep Learning Library for Video Understanding by Haoqi Fan et al
11-18-2021	Simple but Effective: CLIP Embeddings for Embodied AI by Apoorv Khandelwal et al
11-16-2021	Learning Intrinsic Images for Clothing by Kuo Jiang et al
11-16-2021	Robustness of Bayesian Neural Networks to White-Box Adversarial Attacks by Adaku Uchendu et al
11-17-2021	IntraQ: Learning Synthetic Images with Intra-Class Heterogeneity for Zero-Shot Network Quantization by Yunshan Zhong et al
11-17-2021	Rethinking Drone-Based Search and Rescue with Aerial Person Detection by Pasi Pyrrö et al
11-17-2021	Fine-Grained Vehicle Classification in Urban Traffic Scenes using Deep Learning by Syeda Aneeba Najeeb et al
11-16-2021	Bengali Handwritten Grapheme Classification: Deep Learning Approach by Tarun Roy et al
11-18-2021	CoCAtt: A Cognitive-Conditioned Driver Attention Dataset by Yuan Shen et al
11-17-2021	STEEX: Steering Counterfactual Explanations with Semantics by Paul Jacob et al
11-19-2021	Instance-Adaptive Video Compression: Improving Neural Codecs by Training on the Test Set by Ties van Rozendaal et al
11-16-2021	Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts by Yan Zeng et al
11-17-2021	Do Not Trust Prediction Scores for Membership Inference Attacks by Dominik Hintersdorf et al
11-17-2021	Facial Information Analysis Technology for Gender and Age Estimation by Gilheum Park et al
11-16-2021	A Latent Encoder Coupled Generative Adversarial Network (LE-GAN) for Efficient Hyperspectral Image Super-resolution by Yue Shi et al
11-16-2021	Advancement of Deep Learning in Pneumonia and Covid-19 Classification and Localization: A Qualitative and Quantitative Analysis by Aakash Shah et al
11-16-2021	CAR -- Cityscapes Attributes Recognition A Multi-category Attributes Dataset for Autonomous Vehicles by Kareem Metwaly et al
11-18-2021	Towards Intelligibility-Oriented Audio-Visual Speech Enhancement by Tassadaq Hussain et al
11-16-2021	Detecting AutoAttack Perturbations in the Frequency Domain by Peter Lorenz et al
11-18-2021	Boosting Supervised Learning Performance with Co-training by Xinnan Du et al
11-18-2021	Unsupervised Online Learning for Robotic Interestingness with Visual Memory by Chen Wang et al
11-18-2021	LiDAR Cluster First and Camera Inference Later: A New Perspective Towards Autonomous Driving by Jiyang Chen et al
11-18-2021	SimpleTrack: Understanding and Rethinking 3D Multi-object Tracking by Ziqi Pang et al
11-16-2021	Data Augmentation using Random Image Cropping for High-resolution Virtual Try-On (VITON-CROP) by Taewon Kang et al
11-18-2021	Rethinking Query, Key, and Value Embedding in Vision Transformer under Tiny Model Constraints by Jaesin Ahn et al
11-16-2021	TorchGeo: deep learning with geospatial data by Adam J. Stewart et al
11-16-2021	SAPNet: Segmentation-Aware Progressive Network for Perceptual Contrastive Deraining by Shen Zheng et al
11-16-2021	Achieving Human Parity on Visual Question Answering by Ming Yan et al
11-16-2021	ARKitScenes -- A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data by Gilad Baruch et al
11-16-2021	DRINet++: Efficient Voxel-as-point Point Cloud Segmentation by Maosheng Ye et al
11-16-2021	Pansharpening by convolutional neural networks in the full resolution framework by Matteo Ciotola et al
11-17-2021	Trustworthy Long-Tailed Classification by Bolian Li et al
11-16-2021	Diversified Multi-prototype Representation for Semi-supervised Segmentation by Jizong Peng et al
11-17-2021	Blind VQA on 360{\deg} Video via Progressively Learning from Pixels, Frames and Video by Li Yang et al
11-16-2021	NENet: Monocular Depth Estimation via Neural Ensembles by Shuwei Shao et al
11-17-2021	SeCGAN: Parallel Conditional Generative Adversarial Networks for Face Editing via Semantic Consistency by Jiaze Sun et al
11-16-2021	Enhanced Correlation Matching based Video Frame Interpolation by Sungho Lee et al
11-18-2021	Rethink Dilated Convolution for Real-time Semantic Segmentation by Roland Gao
11-17-2021	Image Super-Resolution Using T-Tetromino Pixels by Simon Grosche et al
11-17-2021	Two-Face: Adversarial Audit of Commercial Face Recognition Systems by Siddharth D Jaiswal et al
11-19-2021	Semi-Supervised Domain Generalization in Real World:New Benchmark and Strong Baseline by Luojun Lin et al
11-16-2021	DeltaConv: Anisotropic Point Cloud Learning with Exterior Calculus by Ruben Wiersma et al
11-16-2021	UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detection by Andra Acsintoae et al
11-16-2021	CNN Filter Learning from Drawn Markers for the Detection of Suggestive Signs of COVID-19 in CT Images by Azael M. Sousa et al
11-16-2021	Enabling equivariance for arbitrary Lie groups by Lachlan E. MacDonald et al
11-18-2021	COVID-19 Detection on Chest X-Ray Images: A comparison of CNN architectures and ensembles by Fabricio Breve
11-16-2021	Which CNNs and Training Settings to Choose for Action Unit Detection? A Study Based on a Large-Scale Dataset by Mina Bishay et al
11-18-2021	Wiggling Weights to Improve the Robustness of Classifiers by Sadaf Gulshad et al
11-16-2021	Identifying the Factors that Influence Urban Public Transit Demand by Armstrong Aboah et al
11-17-2021	Induce, Edit, Retrieve:Language Grounded Multimodal Schema for Instructional Video Retrieval by Yue Yang et al
11-16-2021	Delta-GAN-Encoder: Encoding Semantic Changes for Explicit Image Editing, using Few Synthetic Samples by Nir Diamant et al
11-16-2021	Improved Robustness of Vision Transformer via PreLayerNorm in Patch Embedding by Bum Jun Kim et al
11-19-2021	Xp-GAN: Unsupervised Multi-object Controllable Video Generation by Bahman Rouhani et al
11-16-2021	TYolov5: A Temporal Yolov5 Detector Based on Quasi-Recurrent Neural Networks for Real-Time Handgun Detection in Video by Mario Alberto Duran-Vega et al
11-16-2021	TRIG: Transformer-Based Text Recognizer with Initial Embedding Guidance by Yue Tao et al
11-16-2021	Grounding Psychological Shape Space in Convolutional Neural Networks by Lucas Bechberger et al
11-18-2021	SUB-Depth: Self-distillation and Uncertainty Boosting Self-supervised Monocular Depth Estimation by Hang Zhou et al
11-17-2021	Tiny Obstacle Discovery by Occlusion-Aware Multilayer Regression by Feng Xue et al
11-17-2021	Cryo-shift: Reducing domain shift in cryo-electron subtomograms with unsupervised domain adaptation and randomization by Hmrishav Bandyopadhyay et al
11-18-2021	One-Shot Generative Domain Adaptation by Ceyuan Yang et al
11-18-2021	M2A: Motion Aware Attention for Accurate Video Action Recognition by Brennan Gebotys et al
11-18-2021	Exploring the Limits of Epistemic Uncertainty Quantification in Low-Shot Settings by Matias Valdenegro-Toro
11-16-2021	Weakly-supervised fire segmentation by visualizing intermediate CNN layers by Milad Niknejad et al
11-19-2021	Ubi-SleepNet: Advanced Multimodal Fusion Techniques for Three-stage Sleep Classification Using Ubiquitous Sensing by Bing Zhai et al
11-16-2021	Language bias in Visual Question Answering: A Survey and Taxonomy by Desen Yuan
11-16-2021	Computer Vision for Supporting Image Search by Alan F. Smeaton
11-16-2021	A Data-Driven Approach for Linear and Nonlinear Damage Detection Using Variational Mode Decomposition and GARCH Model by Vahid Reza Gharehbaghi et al
11-16-2021	INTERN: A New Learning Paradigm Towards General Vision by Jing Shao et al
11-17-2021	MPF6D: Masked Pyramid Fusion 6D Pose Estimation by Nuno Pereira et al
11-19-2021	Learning to Detect Instance-level Salient Objects Using Complementary Image Labels by Xin Tian et al
11-17-2021	Single-pass Object-adaptive Data Undersampling and Reconstruction for MRI by Zhishen Huang et al
11-19-2021	Fooling Adversarial Training with Inducing Noise by Zhirui Wang et al
11-17-2021	Fast and Light-Weight Network for Single Frame Structured Illumination Microscopy Super-Resolution by Xi Cheng et al
11-17-2021	Compositional Transformers for Scene Generation by Drew A. Hudson et al
11-18-2021	Successor Feature Landmarks for Long-Horizon Goal-Conditioned Reinforcement Learning by Christopher Hoang et al
11-16-2021	Code-free development and deployment of deep segmentation models for digital pathology by Henrik Sahlin Pettersen et al
11-16-2021	Robust 3D Scene Segmentation through Hierarchical and Learnable Part-Fusion by Anirud Thyagharajan et al
11-19-2021	An Analysis of the Influence of Transfer Learning When Measuring the Tortuosity of Blood Vessels by Matheus V. da Silva et al
11-19-2021	Panoptic Segmentation: A Review by Omar Elharrouss et al
11-19-2021	Combined Scaling for Zero-shot Transfer Learning by Hieu Pham et al
11-18-2021	Interactive segmentation using U-Net with weight map and dynamic user interactions by Ragavie Pirabaharan et al
11-18-2021	The Way to my Heart is through Contrastive Learning: Remote Photoplethysmography from Unlabelled Video by John Gideon et al
11-16-2021	IKEA Object State Dataset: A 6DoF object pose estimation dataset and benchmark for multi-state assembly objects by Yongzhi Su et al
11-16-2021	Point detection through multi-instance deep heatmap regression for sutures in endoscopy by Lalith Sharan et al
11-18-2021	Adaptive Shrink-Mask for Text Detection by Chuang Yang et al
11-17-2021	End-to-end optimized image compression with competition of prior distributions by Benoit Brummer et al
11-17-2021	Automated Approach for Computer Vision-based Vehicle Movement Classification at Traffic Intersections by Udita Jana et al
11-17-2021	Nonlinear Intensity Sonar Image Matching based on Deep Convolution Features by Xiaoteng Zhou et al
11-16-2021	Self-supervised High-fidelity and Re-renderable 3D Facial Reconstruction from a Single Image by Mingxin Yang et al
11-17-2021	Generating Unrestricted 3D Adversarial Point Clouds by Xuelong Dai et al
11-17-2021	Pedestrian Detection by Exemplar-Guided Contrastive Learning by Zebin Lin et al
11-17-2021	Probabilistic Spatial Distribution Prior Based Attentional Keypoints Matching Network by Xiaoming Zhao et al
11-16-2021	An Overview of Backdoor Attacks Against Deep Neural Networks and Possible Defences by Wei Guo et al
11-19-2021	ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentation by Laurynas Karazija et al
11-18-2021	Correcting Face Distortion in Wide-Angle Videos by Wei-Sheng Lai et al
11-16-2021	Single Image Object Counting and Localizing using Active-Learning by Inbar Huberman-Spiegelglas et al
11-17-2021	3D Lip Event Detection via Interframe Motion Divergence at Multiple Temporal Resolutions by Jie Zhang et al
11-16-2021	Film Trailer Generation via Task Decomposition by Pinelopi Papalampidi et al
11-19-2021	Grounded Situation Recognition with Transformers by Junhyeong Cho et al
11-17-2021	Its About Time: Analog Clock Reading in the Wild by Charig Yang et al
11-16-2021	SEnSeI: A Deep Learning Module for Creating Sensor Independent Cloud Masks by Alistair Francis et al
11-17-2021	Transparent Human Evaluation for Image Captioning by Jungo Kasai et al
11-18-2021	Automatic Neural Network Pruning that Efficiently Preserves the Model Accuracy by Thibault Castells et al
11-16-2021	Learning Scene Dynamics from Point Cloud Sequences by Pan He et al