计算机视觉论文-2021-06-08

本专栏是计算机视觉方向论文收集积累，时间：2021年6月8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: End-to-End Neuro-Symbolic Architecture for Image-to-Image Reasoning Tasks
AUTHORS: Ananye Agarwal ; Pradeep Shenoy ; Mausam
CATEGORY: cs.AI [cs.AI, cs.CV, cs.LG]
HIGHLIGHT: In this paper, we study neural-symbolic-neural models for reasoning tasks that require a conversion from an image input (e.g., a partially filled sudoku) to an image output (e.g., the image of the completed sudoku).

2, TITLE: Multi-Target Domain Adaptation with Collaborative Consistency Learning
AUTHORS: TAKASHI ISOBE et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we propose a collaborative learning framework to achieve unsupervised multi-target domain adaptation.

3, TITLE: Resolution Learning in Deep Convolutional Networks Using Scale-space Theory
AUTHORS: Silvia L. Pintea ; Nergis Tomen ; Stanley F. Goes ; Marco Loog ; Jan C. van Gemert
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We propose to do away with hard-coded resolution hyper-parameters and aim to learn the appropriate resolution from data.

4, TITLE: 3D Convolution Neural Network Based Person Identification Using Gait Cycles
AUTHORS: Ravi Shekhar Tiwari ; Supraja P ; Rijo Jackson Tom
CATEGORY: cs.CV [cs.CV, cs.AI, This paper tells us how human can be identified by their Gait cycle using any simple camera]
HIGHLIGHT: In this work, gait features are used to identify an individual.

5, TITLE: Go with The Flows: Mixtures of Normalizing Flows for Point Cloud Generation and Reconstruction
AUTHORS: Janis Postels ; Mengya Liu ; Riccardo Spezialetti ; Luc Van Gool ; Federico Tombari
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This work enhances their representational power by applying mixtures of NFs to point clouds.

6, TITLE: MOC-GAN: Mixing Objects and Captions to Generate Realistic Images
AUTHORS: Tao Ma ; Yikang Li
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Thus, we introduce a more rational setting, generating a realistic image from the objects and captions.

7, TITLE: Transformed ROIs for Capturing Visual Transformations in Videos
AUTHORS: Abhinav Rai ; Fadime Sener ; Angela Yao
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We present TROI, a plug-and-play module for CNNs to reason between mid-level feature representations that are otherwise separated in space and time.

8, TITLE: Learning Video Models from Text: Zero-Shot Anticipation for Procedural Actions
AUTHORS: Fadime Sener ; Rishabh Saraf ; Angela Yao
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This paper presents a hierarchical model that generalizes instructional knowledge from large-scale text-corpora and transfers the knowledge to video.

9, TITLE: Incremental False Negative Detection for Contrastive Learning
AUTHORS: Tsai-Shien Chen ; Wei-Chih Hung ; Hung-Yu Tseng ; Shao-Yi Chien ; Ming-Hsuan Yang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To address the issue, we introduce a novel incremental false negative detection for self-supervised contrastive learning.

10, TITLE: Technical Report: Temporal Aggregate Representations
AUTHORS: Fadime Sener ; Dibyadip Chatterjee ; Angela Yao
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this report, we conduct further experiments with this framework on different tasks and a new dataset, EPIC-KITCHENS-100.

11, TITLE: Oriented Object Detection with Transformer
AUTHORS: TELI MA et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We provide the first attempt and implement Oriented Object DEtection with TRansformer ($\bf O^2DETR$) based on an end-to-end network.

12, TITLE: Large-scale Unsupervised Semantic Segmentation
AUTHORS: SHANG-HUA GAO et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We propose a new problem of large-scale unsupervised semantic segmentation (LUSS) with a newly created benchmark dataset to track the research progress. Based on the ImageNet dataset, we propose the ImageNet-S dataset with 1.2 million training images and 40k high-quality semantic segmentation annotations for evaluation.

13, TITLE: Deep Learning 3D Dose Prediction for Conventional Lung IMRT Using Consistent/Unbiased Automated Plans
AUTHORS: Navdeep Dahiya ; Gourav Jhanwar ; Anthony Yezzi ; Masoud Zarepisheh ; Saad Nadeem
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we instead use consistent plans generated by our in-house automated planning system (named ``ECHO'') to train the DL model.

14, TITLE: Refiner: Refining Self-attention for Vision Transformers
AUTHORS: DAQUAN ZHOU et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Different from existing works, we introduce a conceptually simple scheme, called refiner, to directly refine the self-attention maps of ViTs.

15, TITLE: An End-to-End Breast Tumour Classification Model Using Context-Based Patch Modelling- A BiLSTM Approach for Image Classification
AUTHORS: Suvidha Tripathi ; Satish Kumar Singh ; Hwee Kuan Lee
CATEGORY: cs.CV [cs.CV, cs.AI, cs.MM]
HIGHLIGHT: For the given task of classification, we have used BiLSTMs to model both forward and backward contextual relationship.

16, TITLE: Combinatorial Optimization for Panoptic Segmentation: An End-to-End Trainable Approach
AUTHORS: Ahmed Abbas ; Paul Swoboda
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We propose an end-to-end trainable architecture for simultaneous semantic and instance segmentation (a.k.a. panoptic segmentation) consisting of a convolutional neural network and an asymmetric multiway cut problem solver.

17, TITLE: Transformer in Convolutional Neural Networks
AUTHORS: YUN LIU et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To this end, we propose the Hierarchical MHSA (H-MHSA), whose representation is computed in a hierarchical manner.

18, TITLE: Region-aware Adaptive Instance Normalization for Image Harmonization
AUTHORS: Jun Ling ; Han Xue ; Li Song ; Rong Xie ; Xiao Gu
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To ensure the visual style consistency between the foreground and the background, in this paper, we treat image harmonization as a style transfer problem.

19, TITLE: Patch Slimming for Efficient Vision Transformers
AUTHORS: YEHUI TANG et. al.
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: Considering that the attention mechanism aggregates different patches layer-by-layer, we present a novel patch slimming approach that discards useless patches in a top-down paradigm.

20, TITLE: Feature-based Style Randomization for Domain Generalization
AUTHORS: Yue Wang ; Lei Qi ; Yinghuan Shi ; Yang Gao
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Unlike image-level augmentation, we in this paper develop a simple yet effective feature-based style randomization module to achieve feature-level augmentation, which can produce random styles via integrating random noise into the original style.

21, TITLE: Convolutional Neural Networks with Gated Recurrent Connections
AUTHORS: Jianfeng Wang ; Xiaolin Hu
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We propose to modulate the RFs of neurons by introducing gates to the recurrent connections.

22, TITLE: Category Contrast for Unsupervised Domain Adaptation in Visual Tasks
AUTHORS: Jiaxing Huang ; Dayan Guan ; Aoran Xiao ; Shijian Lu
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we explore the idea of instance contrastive learning in unsupervised domain adaptation (UDA) and propose a novel Category Contrast technique (CaCo) that introduces semantic priors on top of instance discrimination for visual UDA tasks.

23, TITLE: Unsupervised Action Segmentation for Instructional Videos
AUTHORS: AJ Piergiovanni ; Anelia Angelova ; Michael S. Ryoo ; Irfan Essa
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper we address the problem of automatically discovering atomic actions in unsupervised manner from instructional videos, which are rarely annotated with atomic actions.

24, TITLE: Bias Mitigation of Face Recognition Models Through Calibration
AUTHORS: Tiago Salvador ; Stephanie Cairns ; Vikram Voleti ; Noah Marshall ; Adam Oberman
CATEGORY: cs.CV [cs.CV, cs.LG, stat.ML]
HIGHLIGHT: In this work, we introduce the Bias Mitigation Calibration (BMC) method, which (i) increases model accuracy (improving the state-of-the-art), (ii) produces fairly-calibrated probabilities, (iii) significantly reduces the gap in the false positive rates, and (iv) does not require knowledge of the sensitive attribute.

25, TITLE: Recovery Analysis for Plug-and-Play Priors Using The Restricted Eigenvalue Condition
AUTHORS: Jiaming Liu ; M. Salman Asif ; Brendt Wohlberg ; Ulugbek S. Kamilov
CATEGORY: cs.CV [cs.CV, cs.LG, eess.IV, eess.SP]
HIGHLIGHT: We address this gap by showing how to establish theoretical recovery guarantees for PnP/RED by assuming that the solution of these methods lies near the fixed-points of a deep neural network.

26, TITLE: Open Source Disease Analysis System of Cactus By Artificial Intelligence and Image Processing
AUTHORS: Kanlayanee Kaweesinsakul ; Siranee Nuchitprasitchai ; Joshua M. Pearce
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: To develop an automated model for the analysis of cactus disease and to be able to quickly treat and prevent damage to the cactus.

27, TITLE: HERS Superpixels: Deep Affinity Learning for Hierarchical Entropy Rate Segmentation
AUTHORS: Hankui Peng ; Angelica I. Aviles-Rivero ; Carola-Bibiane Schonlieb
CATEGORY: cs.CV [cs.CV, stat.AP, stat.ML, I.4; I.5]
HIGHLIGHT: In this work, we propose a two-stage graph-based framework for superpixel segmentation.

28, TITLE: Reveal of Vision Transformers Robustness Against Adversarial Attacks
AUTHORS: Ahmed Aldahdooh ; Wassim Hamidouche ; Olivier Deforges
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This work studies the robustness of ViT variants 1) against different $L_p$-based adversarial attacks in comparison with CNNs and 2) under Adversarial Examples (AEs) after applying preprocessing defense methods.

29, TITLE: RDA: Robust Domain Adaptation Via Fourier Adversarial Attacking
AUTHORS: Jiaxing Huang ; Dayan Guan ; Aoran Xiao ; Shijian Lu
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This paper presents RDA, a robust domain adaptation technique that introduces adversarial attacking to mitigate overfitting in UDA.

30, TITLE: Dynamic Resolution Network
AUTHORS: MINGJIAN ZHU et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we observe that the smallest resolution for accurately predicting the given image is different using the same neural network.

31, TITLE: Alpha Matte Generation from Single Input for Portrait Matting
AUTHORS: Dogucan Yaman ; Haz?m Kemal Ekenel ; Alexander Waibel
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we introduce an additional input-free approach to perform portrait matting using Generative Adversarial Nets (GANs).

32, TITLE: Reducing The Feature Divergence of RGB and Near-infrared Images Using Switchable Normalization
AUTHORS: Siwei Yang ; Shaozuo Yu ; Bingchen Zhao ; Yin Wang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we consider the multi-modality nature of agricultural aerial images and show that naively combining different modalities together without taking the feature divergence into account can lead to sub-optimal results.

33, TITLE: Neural Implicit 3D Shapes from Single Images with Spatial Patterns
AUTHORS: Yixin Zhuang ; Yunzhe Liu ; Baoquan Chen
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In contrast to previous methods that learn holistic shape priors, we propose a method to learn spatial pattern priors for inferring the invisible regions of the underlying shape, wherein each 3D sample in the implicit shape representation is associated with a set of points generated by hand-crafted 3D mappings, along with their local image features.

34, TITLE: Referring Transformer: A One-step Approach to Multi-task Visual Grounding
AUTHORS: Muchen Li ; Leonid Sigal
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a simple one-stage multi-task framework for visual grounding tasks.

35, TITLE: Efficient Training of Visual Transformers with Small-Size Datasets
AUTHORS: YAHUI LIU et. al.
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: In this paper, we empirically analyse different VTs, comparing their robustness in a small training-set regime, and we show that, despite having a comparable accuracy when trained on ImageNet, their performance on smaller datasets can be largely different.

36, TITLE: Digital Taxonomist: Identifying Plant Species in Citizen Scientists' Photographs
AUTHORS: RICCARDO DE LUTIO et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We propose a machine learning model that takes into account these additional cues in a unified framework.

37, TITLE: CDN-MEDAL: Two-stage Density and Difference Approximation Framework for Motion Analysis
AUTHORS: Synh Viet-Uyen Ha ; Cuong Tien Nguyen ; Hung Ngoc Phan ; Nhat Minh Chung ; Phuong Hoai Ha
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: In this work, we propose a novel, two-stage method of change detection with two convolutional neural networks.

38, TITLE: Person Re-Identification with A Locally Aware Transformer
AUTHORS: Charu Sharma ; Siddhant R. Kapil ; David Chapman
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We propose a novel Locally Aware Transformer (LA-Transformer) that employs a Parts-based Convolution Baseline (PCB)-inspired strategy for aggregating globally enhanced local classification tokens into an ensemble of $\sqrt{N}$ classifiers, where $N$ is the number of patches.

39, TITLE: Points2Polygons: Context-Based Segmentation from Weak Labels Using Adversarial Networks
AUTHORS: Kuai Yu ; Hakeem Frank ; Daniel Wilson
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We introduce Points2Polygons (P2P), a model which makes use of contextual metric learning techniques that directly addresses this problem.

40, TITLE: Highlighting The Importance of Reducing Research Bias and Carbon Emissions in CNNs
AUTHORS: AHMED BADAR et. al.
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: Here, we perform an extensive and fair empirical study of a number of proposed techniques to gauge the utility of each technique for segmentation and classification.

41, TITLE: T-Net: Deep Stacked Scale-Iteration Network for Image Dehazing
AUTHORS: Lirong Zheng ; Yanshan Li ; Kaihao Zhang ; Wenhan Luo
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we address the problem of image dehazing by proposing a dehazing network named T-Net, which consists of a backbone network based on the U-Net architecture and a dual attention module.

42, TITLE: Multi-Level Graph Encoding with Structural-Collaborative Relation Learning for Skeleton-Based Person Re-Identification
AUTHORS: Haocong Rao ; Shihao Xu ; Xiping Hu ; Jun Cheng ; Bin Hu
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To fully explore body relations, we construct graphs to model human skeletons from different levels, and for the first time propose a Multi-level Graph encoding approach with Structural-Collaborative Relation learning (MG-SCR) to encode discriminative graph features for person Re-ID.

43, TITLE: Hidden Markov Modeling for Maximum Likelihood Neuron Reconstruction
AUTHORS: Thomas L. Athey ; Daniel Tward ; Ulrich Mueller ; Michael I. Miller
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Here we present a method inspired by hidden Markov modeling and appearance modeling of fluorescent neuron images that can automatically trace neuronal processes.

44, TITLE: Deep Matching Prior: Test-Time Optimization for Dense Correspondence
AUTHORS: Sunghwan Hong ; Seungryong Kim
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we show that an image pair-specific prior can be captured by solely optimizing the untrained matching networks on an input pair of images.

45, TITLE: Hierarchical Video Generation for Complex Data
AUTHORS: Lluis Castrejon ; Nicolas Ballas ; Aaron Courville
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Inspired by this we propose a hierarchical model for video generation which follows a coarse to fine approach.

46, TITLE: FINet: Dual Branches Feature Interaction for Partial-to-Partial Point Cloud Registration
AUTHORS: Hao Xu ; Nianjin Ye ; Shuaicheng Liu ; Guanghui Liu ; Bing Zeng
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we propose to solve the partial-to-partial registration from a new perspective, by introducing feature interactions between the source and the reference clouds at the feature extraction stage, such that the registration can be realized without the explicit mask estimation or attentions for the overlapping detection as adopted previously.

47, TITLE: Feature Flow Regularization: Improving Structured Sparsity in Deep Neural Networks
AUTHORS: Yue Wu ; Yuan Lan ; Luchan Zhang ; Yang Xiang
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: In this paper, we propose a simple and effective regularization strategy from a new perspective of evolution of features, which we call feature flow regularization (FFR), for improving structured sparsity and filter pruning in DNNs.

48, TITLE: Predify: Augmenting Deep Neural Networks with Brain-inspired Predictive Coding Dynamics
AUTHORS: BHAVIN CHOKSI et. al.
CATEGORY: cs.CV [cs.CV, q-bio.NC]
HIGHLIGHT: In this work we explore whether this shortcoming may be partly addressed by incorporating brain-inspired recurrent dynamics in deep convolutional networks.

49, TITLE: ZeroWaste Dataset: Towards Automated Waste Recycling
AUTHORS: DINA BASHKIROVA et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We present baselines for fully-, semi- and weakly-supervised segmentation methods. In this paper, we take a step towards computer-aided waste detection and present the first in-the-wild industrial-grade waste detection and segmentation dataset, ZeroWaste.

50, TITLE: SADRNet: Self-Aligned Dual Face Regression Networks for Robust 3D Dense Face Alignment and Reconstruction
AUTHORS: Zeyu Ruan ; Changqing Zou ; Longhai Wu ; Gangshan Wu ; Limin Wang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To this end, we propose an end-to-end framework, termed as Self-aligned Dual face Regression Network (SADRNet), which predicts a pose-dependent face, a pose-independent face.

51, TITLE: ViTAE: Vision Transformer Advanced By Exploring Intrinsic Inductive Bias
AUTHORS: Yufei Xu ; Qiming Zhang ; Jing Zhang ; Dacheng Tao
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a novel Vision Transformer Advanced by Exploring intrinsic IB from convolutions, \ie, ViTAE.

52, TITLE: An Adaptive Framework for Learning Unsupervised Depth Completion
AUTHORS: Alex Wong ; Xiaohan Fei ; Byung-Woo Hong ; Stefano Soatto
CATEGORY: cs.CV [cs.CV, cs.LG, cs.RO]
HIGHLIGHT: We present a method to infer a dense depth map from a color image and associated sparse depth measurements.

53, TITLE: ContourRender: Detecting Arbitrary Contour Shape For Instance Segmentation In One Pass
AUTHORS: Tutian Tang ; Wenqiang Xu ; Ruolin Ye ; Yan-Feng Wang ; Cewu Lu
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we argue that the difficulty in regressing the contour points in one pass is mainly due to the ambiguity when discretizing a smooth contour into a polygon.

54, TITLE: Self-Supervision & Meta-Learning for One-Shot Unsupervised Cross-Domain Detection
AUTHORS: F. CAPPIO BORLINO et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Our work addresses this setting, presenting an object detection algorithm able to perform unsupervised adaptation across domains by using only one target sample, seen at test time.

55, TITLE: Exploiting Emotional Dependencies with Graph Convolutional Networks for Facial Expression Recognition
AUTHORS: Panagiotis Antoniadis ; Panagiotis P. Filntisis ; Petros Maragos
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Inspired by recent work in multi-label classification, this paper proposes a novel multi-task learning (MTL) framework that exploits the dependencies between these two models using a Graph Convolutional Network (GCN) to recognize facial expressions in-the-wild.

56, TITLE: Occlusion-aware Unsupervised Learning of Depth from 4-D Light Fields
AUTHORS: Jing Jin ; Junhui Hou
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: By contrast, we propose an unsupervised learning-based method, which does not require ground-truth depth as supervision during training.

57, TITLE: DINs: Deep Interactive Networks for Neurofibroma Segmentation in Neurofibromatosis Type 1 on Whole-Body MRI
AUTHORS: JIAN-WEI ZHANG et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this study, we propose deep interactive networks (DINs) to address the above limitations.

58, TITLE: Few-Shot Unsupervised Image-to-Image Translation on Complex Scenes
AUTHORS: Luca Barras ; Samuel Chassot ; Daniel Filipe Nunes Silva
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: In this work, we assess how a method that has initially been developed for single object translation performs on more diverse and content-rich images.

59, TITLE: Learning Dynamics Via Graph Neural Networks for Human Pose Estimation and Tracking
AUTHORS: YIDING YANG et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a novel online approach to learning the pose dynamics, which are independent of pose detections in current fame, and hence may serve as a robust estimation even in challenging scenarios including occlusion.

60, TITLE: DoubleField: Bridging The Neural Surface and Radiance Fields for High-fidelity Human Rendering
AUTHORS: RUIZHI SHAO et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We introduce DoubleField, a novel representation combining the merits of both surface field and radiance field for high-fidelity human rendering.

61, TITLE: Exploring to Establish An Appropriate Model for Mage Aesthetic Assessment Via CNN-based RSRL: An Empirical Study
AUTHORS: Ying Dai
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To establish an appropriate model for photo aesthetic assessment, in this paper, a D-measure which reflects the disentanglement degree of the final layer FC nodes of CNN is introduced.

62, TITLE: Few-shot Segmentation of Medical Images Based on Meta-learning with Implicit Gradients
AUTHORS: RABINDRA KHADGA et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To this end, we propose to exploit an optimization-based implicit model agnostic meta-learning {iMAML} algorithm in a few-shot setting for medical image segmentation.

63, TITLE: DISCO: Accurate Discrete Scale Convolutions
AUTHORS: Ivan Sosnovik ; Artem Moskalev ; Arnold Smeulders
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We aim for accurate scale-equivariant convolutional neural networks (SE-CNNs) applicable for problems where high granularity of scale and small filter sizes are required.

64, TITLE: Video Imprint
AUTHORS: ZHANNING GAO et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: A new unified video analytics framework (ER3) is proposed for complex event retrieval, recognition and recounting, based on the proposed video imprint representation, which exploits temporal correlations among image features across video frames.

65, TITLE: Wide-Baseline Relative Camera Pose Estimation with Directional Learning
AUTHORS: Kefan Chen ; Noah Snavely ; Ameesh Makadia
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Analogously, in this paper we explore improving camera pose regression by instead predicting a discrete distribution over camera poses.

66, TITLE: Contextual Guided Segmentation Framework for Semi-supervised Video Instance Segmentation
AUTHORS: Trung-Nghia Le ; Tam V. Nguyen ; Minh-Triet Tran
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose Contextual Guided Segmentation (CGS) framework for video instance segmentation in three passes.

67, TITLE: SelfDoc: Self-Supervised Document Representation Learning
AUTHORS: PEIZHAO LI et. al.
CATEGORY: cs.CV [cs.CV, cs.CL]
HIGHLIGHT: We propose SelfDoc, a task-agnostic pre-training framework for document image understanding.

68, TITLE: A Comprehensive Survey on Image Dehazing Based on Deep Learning
AUTHORS: JIE GUI et. al.
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: In this paper, we conduct a comprehensive survey on the recent proposed dehazing methods.

69, TITLE: Adversarial Attack and Defense in Deep Ranking
AUTHORS: MO ZHOU et. al.
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: In this paper, we propose two attacks against deep ranking systems, i.e., Candidate Attack and Query Attack, that can raise or lower the rank of chosen candidates by adversarial perturbations.

70, TITLE: Making CNNs Interpretable By Building Dynamic Sequential Decision Forests with Top-down Hierarchy Learning
AUTHORS: Yilin Wang ; Shaozuo Yu ; Xiaokang Yang ; Wei Shen
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a generic model transfer scheme to make Convlutional Neural Networks (CNNs) interpretable, while maintaining their high classification accuracy.

71, TITLE: Web Based Disease Prediction and Recommender System
AUTHORS: Harish Rajora ; Narinder Singh Punn ; Sanjay Kumar Sonbhadra ; Sonali Agarwal
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: The proposed web-based disease prediction system utilizes machine learning based classification techniques on a data set acquired from the National Centre of Disease Control (NCDC).

72, TITLE: Video Instance Segmentation Using Inter-Frame Communication Transformers
AUTHORS: Sukjun Hwang ; Miran Heo ; Seoung Wug Oh ; Seon Joo Kim
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We propose a novel end-to-end solution for video instance segmentation (VIS) based on transformers.

73, TITLE: Multi-Camera Vehicle Counting Using Edge-AI
AUTHORS: LUCA CIAMPI et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This paper presents a novel solution to automatically count vehicles in a parking lot using images captured by smart cameras.

74, TITLE: Semi-Supervised Domain Adaptation Via Adaptive and Progressive Feature Alignment
AUTHORS: Jiaxing Huang ; Dayan Guan ; Aoran Xiao ; Shijian Lu
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This paper presents SSDAS, a Semi-Supervised Domain Adaptive image Segmentation network that employs a few labeled target samples as anchors for adaptive and progressive feature alignment between labeled source samples and unlabeled target samples.

75, TITLE: Using GANs to Augment Data for Cloud Image Segmentation Task
AUTHORS: Mayank Jain ; Conor Meegan ; Soumyabrata Dev
CATEGORY: cs.CV [cs.CV, eess.IV]
HIGHLIGHT: In this paper, we demonstrate the effectiveness of using Generative Adversarial Networks (GANs) to generate data to augment the training set in order to increase the prediction accuracy of image segmentation model.

76, TITLE: Rethinking Training from Scratch for Object Detection
AUTHORS: Yang Li ; Hong Zhang ; Yu Zhang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we explore to directly pre-training on target dataset for object detection.

77, TITLE: The Distance Transform and Its Computation
AUTHORS: Tilo Strutz
CATEGORY: cs.CV [cs.CV, cs.CG]
HIGHLIGHT: In this tutorial, different approaches are explained in detail and compared using examples.

78, TITLE: Efficient Iterative Amortized Inference for Learning Symmetric and Disentangled Multi-Object Representations
AUTHORS: Patrick Emami ; Pan He ; Sanjay Ranka ; Anand Rangarajan
CATEGORY: cs.CV [cs.CV, cs.AI, cs.LG]
HIGHLIGHT: In this work, we introduce EfficientMORL, an efficient framework for the unsupervised learning of object-centric representations.

79, TITLE: Efficient Training for Future Video Generation Based on Hierarchical Disentangled Representation of Latent Variables
AUTHORS: Naoya Fushishita ; Antonio Tejero-de-Pablos ; Yusuke Mukuta ; Tatsuya Harada
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a novel method for generating future prediction videos with less memory usage than the conventional methods.

80, TITLE: Self-supervised Depth Estimation Leveraging Global Perception and Geometric Smoothness Using On-board Videos
AUTHORS: Shaocheng Jia ; Xin Pei ; Wei Yao ; S. C. Wong
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we present DLNet for pixel-wise depth estimation, which simultaneously extracts global and local features with the aid of our depth Linformer block.

81, TITLE: Uformer: A General U-Shaped Transformer for Image Restoration
AUTHORS: Zhendong Wang ; Xiaodong Cun ; Jianmin Bao ; Jianzhuang Liu
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we present Uformer, an effective and efficient Transformer-based architecture, in which we build a hierarchical encoder-decoder network using the Transformer block for image restoration.

82, TITLE: Efficient Classification of Very Large Images with Tiny Objects
AUTHORS: Fanjie Kong ; Ricardo Henao
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: We present an end-to-end CNN model termed Zoom-In network that leverages hierarchical attention sampling for classification of large images with tiny objects using a single GPU.

83, TITLE: IPS300+: A Challenging Multimodal Dataset for Intersection Perception System
AUTHORS: HUANAN WANG et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Through an IPS (Intersection Perception System) installed at the diagonal of the intersection, this paper proposes a high-quality multimodal dataset for the intersection perception task.

84, TITLE: GLSD: The Global Large-Scale Ship Database and Baseline Evaluations
AUTHORS: ZHENFENG SHAO et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we introduce a challenging global large-scale ship database (called GLSD), designed specifically for ship detection tasks.

85, TITLE: RegionViT: Regional-to-Local Attention for Vision Transformers
AUTHORS: Chun-Fu Chen ; Rameswar Panda ; Quanfu Fan
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Motivated by this, in this paper, we propose a new architecture that adopts the pyramid structure and employ a novel regional-to-local attention rather than global self-attention in vision transformers.

86, TITLE: Visual Communication of Object Concepts at Different Levels of Abstraction
AUTHORS: Justin Yang ; Judith E. Fan
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We found that label-cued category drawings were the most recognizable at the basic level, whereas photo-cued exemplar drawings were the least recognizable.

87, TITLE: End-to-end Reconstruction Meets Data-driven Regularization for Inverse Problems
AUTHORS: Subhadip Mukherjee ; Marcello Carioni ; Ozan �ktem ; Carola-Bibiane Sch�nlieb
CATEGORY: cs.CV [cs.CV, cs.LG, math.OC]
HIGHLIGHT: We propose an unsupervised approach for learning end-to-end reconstruction operators for ill-posed inverse problems.

88, TITLE: Radar-Camera Pixel Depth Association for Depth Completion
AUTHORS: YUNFEI LONG et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Here we propose a radar-to-pixel association stage which learns a mapping from radar returns to pixels.

89, TITLE: Multi-Exit Semantic Segmentation Networks
AUTHORS: Alexandros Kouris ; Stylianos I. Venieris ; Stefanos Laskaridis ; Nicholas D. Lane
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: To this end, we propose a framework for converting state-of-the-art segmentation models to MESS networks; specially trained CNNs that employ parametrised early exits along their depth to save computation during inference on easier samples.

90, TITLE: Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer
AUTHORS: ZILONG HUANG et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we revisit the spatial shuffle as an efficient way to build connections among windows.

91, TITLE: 3DB: A Framework for Debugging Computer Vision Models
AUTHORS: GUILLAUME LECLERC et. al.
CATEGORY: cs.CV [cs.CV, cs.LG, stat.ML]
HIGHLIGHT: We introduce 3DB: an extendable, unified framework for testing and debugging vision models using photorealistic simulation.

92, TITLE: Visual Search Asymmetry: Deep Nets and Humans Share Similar Inherent Biases
AUTHORS: Shashi Kant Gupta ; Mengmi Zhang ; Chia-Chien Wu ; Jeremy M. Wolfe ; Gabriel Kreiman
CATEGORY: cs.CV [cs.CV, q-bio.NC]
HIGHLIGHT: An intriguing property of some classical search tasks is an asymmetry such that finding a target A among distractors B can be easier than finding B among A. To elucidate the mechanisms responsible for asymmetry in visual search, we propose a computational model that takes a target and a search image as inputs and produces a sequence of eye movements until the target is found.

93, TITLE: Visual Transformer for Task-aware Active Learning
AUTHORS: Razvan Caramalau ; Binod Bhattarai ; Tae-Kyun Kim
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: In this paper, we present a novel pipeline for pool-based Active Learning.

94, TITLE: Self-Damaging Contrastive Learning
AUTHORS: Ziyu Jiang ; Tianlong Chen ; Bobak Mortazavi ; Zhangyang Wang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This paper proposes to explicitly tackle this challenge, via a principled framework called Self-Damaging Contrastive Learning (SDCLR), to automatically balance the representation learning without knowing the classes.

95, TITLE: NTIRE 2021 Challenge on Burst Super-Resolution: Methods and Results
AUTHORS: GOUTAM BHAT et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This paper reviews the NTIRE2021 challenge on burst super-resolution.

96, TITLE: Channel DropBlock: An Improved Regularization Method for Fine-Grained Visual Classification
AUTHORS: YIFENG DING et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we propose a lightweight yet effective regularization method named Channel DropBlock (CDB), in combination with two alternative correlation metrics, to address this problem.

97, TITLE: Unsupervised Learning for Cuboid Shape Abstraction Via Joint Segmentation from Point Clouds
AUTHORS: Kaizhi Yang ; Xuejin Chen
CATEGORY: cs.CV [cs.CV, cs.GR]
HIGHLIGHT: In this paper, we propose an unsupervised shape abstraction method to map a point cloud into a compact cuboid representation.

98, TITLE: Source-Free Open Compound Domain Adaptation in Semantic Segmentation
AUTHORS: Yuyang Zhao ; Zhun Zhong ; Zhiming Luo ; Gim Hee Lee ; Nicu Sebe
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we introduce a new concept, named source-free open compound domain adaptation (SF-OCDA), and study it in semantic segmentation.

99, TITLE: Supervised Adptive Threshold Network for Instance Segmentation
AUTHORS: Kuikun Liu ; Jie Yang ; Cai Sun ; Haoyuan Chi
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose supervised adaptive threshold network for instance segmentation.

100, TITLE: Shape As Points: A Differentiable Poisson Solver
AUTHORS: SONGYOU PENG et. al.
CATEGORY: cs.CV [cs.CV, cs.GR]
HIGHLIGHT: In this paper, we revisit the classic yet ubiquitous point cloud representation and introduce a differentiable point-to-mesh layer using a differentiable formulation of Poisson Surface Reconstruction (PSR) that allows for a GPU-accelerated fast solution of the indicator function given an oriented point cloud.

101, TITLE: SIMONe: View-Invariant, Temporally-Abstracted Object Representations Via Unsupervised Video Decomposition
AUTHORS: RISHABH KABRA et. al.
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: We present an unsupervised variational approach to this problem.

102, TITLE: Learning Topology from Synthetic Data for Unsupervised Depth Completion
AUTHORS: Alex Wong ; Safa Cicek ; Stefano Soatto
CATEGORY: cs.CV [cs.CV, cs.LG, cs.RO]
HIGHLIGHT: We present a method for inferring dense depth maps from images and sparse depth measurements by leveraging synthetic data to learn the association of sparse point clouds with dense natural shapes, and using the image as evidence to validate the predicted depth map.

103, TITLE: Mean-Shifted Contrastive Loss for Anomaly Detection
AUTHORS: Tal Reiss ; Yedid Hoshen
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a new loss function which can overcome failure modes of both center-loss and contrastive-loss methods.

104, TITLE: Spectral Temporal Graph Neural Network for Trajectory Prediction
AUTHORS: Defu Cao ; Jiachen Li ; Hengbo Ma ; Masayoshi Tomizuka
CATEGORY: cs.CV [cs.CV, cs.AI, cs.LG, cs.RO]
HIGHLIGHT: To this end, we propose a Spectral Temporal Graph Neural Network (SpecTGNN), which can capture inter-agent correlations and temporal dependency simultaneously in frequency domain in addition to time domain.

105, TITLE: High Resolution Solar Image Generation Using Generative Adversarial Networks
AUTHORS: Ankan Dash ; Junyi Ye ; Guiling Wang
CATEGORY: cs.CV [cs.CV, cs.LG, eess.IV]
HIGHLIGHT: We applied Deep Learning algorithm known as Generative Adversarial Networks (GANs) to perform solar image-to-image translation.

106, TITLE: Deep Medial Fields
AUTHORS: DANIEL REBAIN et. al.
CATEGORY: cs.GR [cs.GR, cs.CV]
HIGHLIGHT: In this work, we introduce medial fields: a field function derived from the medial axis transform (MAT) that makes available information about the underlying 3D geometry that is immediately useful for a number of downstream tasks.

107, TITLE: Principle Bit Analysis: Autoencoding with Schur-Concave Loss
AUTHORS: Sourbh Bhadane ; Aaron B. Wagner ; Jayadev Acharya
CATEGORY: cs.IT [cs.IT, cs.CV, cs.LG, math.IT]
HIGHLIGHT: As one application, we consider a strictly Schur-concave constraint that estimates the number of bits needed to represent the latent variables under fixed-rate encoding, a setup that we call \emph{Principal Bit Analysis (PBA)}.

108, TITLE: Preservation of The Global Knowledge By Not-True Self Knowledge Distillation in Federated Learning
AUTHORS: Gihun Lee ; Yongjin Shin ; Minchan Jeong ; Se-Young Yun
CATEGORY: cs.LG [cs.LG, cs.AI, cs.CV]
HIGHLIGHT: To this end, we propose a simple yet effective framework Federated Local Self-Distillation (FedLSD), which utilizes the global knowledge on locally available data.

109, TITLE: SketchGen: Generating Constrained CAD Sketches
AUTHORS: WAMIQ REYAZ PARA et. al.
CATEGORY: cs.LG [cs.LG, cs.AI, cs.CV, cs.GR]
HIGHLIGHT: We propose SketchGen as a generative model based on a transformer architecture to address the heterogeneity problem by carefully designing a sequential language for the primitives and constraints that allows distinguishing between different primitive or constraint types and their parameters, while encouraging our model to re-use information across related parameters, encoding shared structure.

110, TITLE: Continual Active Learning for Efficient Adaptation of Machine Learning Models to Changing Image Acquisition
AUTHORS: Matthias Perkonigg ; Johannes Hofmanninger ; Georg Langs
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: Here, we propose a method for continual active learning on a data stream of medical images.

111, TITLE: Commutative Lie Group VAE for Disentanglement Learning
AUTHORS: Xinqi Zhu ; Chang Xu ; Dacheng Tao
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: A simple model named Commutative Lie Group VAE is introduced to realize the group-based disentanglement learning.

112, TITLE: DAMSL: Domain Agnostic Meta Score-based Learning
AUTHORS: John Cai ; Bill Cai ; Shengmei Shen
CATEGORY: cs.LG [cs.LG, cs.AI, cs.CV]
HIGHLIGHT: In this paper, we propose Domain Agnostic Meta Score-based Learning (DAMSL), a novel, versatile and highly effective solution that delivers significant out-performance over state-of-the-art methods for cross-domain few-shot learning.

113, TITLE: Efficient Lottery Ticket Finding: Less Data Is More
AUTHORS: Zhenyu Zhang ; Xuxi Chen ; Tianlong Chen ; Zhangyang Wang
CATEGORY: cs.LG [cs.LG, cs.AI, cs.CV]
HIGHLIGHT: This paper explores a new perspective on finding lottery tickets more efficiently, by doing so only with a specially selected subset of data, called Pruning-Aware Critical set (PrAC set), rather than using the full training set.

114, TITLE: Zero-Shot Knowledge Distillation from A Decision-Based Black-Box Model
AUTHORS: Zi Wang
CATEGORY: cs.LG [cs.LG, cs.AI, cs.CV]
HIGHLIGHT: We propose to generate pseudo samples distinguished by the teacher's decision boundaries to the largest extent and construct soft labels for them, which are used as the transfer set.

115, TITLE: Understand and Improve Contrastive Learning Methods for Visual Representation: A Review
AUTHORS: Ran Liu
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: This literature review aims to provide an up-to-date analysis of the efforts of researchers to understand the key components and the limitations of self-supervised learning.

116, TITLE: Making EfficientNet More Efficient: Exploring Batch-Independent Normalization, Group Convolutions and Reduced Resolution Training
AUTHORS: Dominic Masters ; Antoine Labatie ; Zach Eaton-Rosen ; Carlo Luschi
CATEGORY: cs.LG [cs.LG, cs.CV, stat.ML]
HIGHLIGHT: In this work, we focus on improving the practical efficiency of the state-of-the-art EfficientNet models on a new class of accelerator, the Graphcore IPU.

117, TITLE: Asymmetric Loss Functions for Learning with Noisy Labels
AUTHORS: Xiong Zhou ; Xianming Liu ; Junjun Jiang ; Xin Gao ; Xiangyang Ji
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: In this work, we propose a new class of loss functions, namely \textit{asymmetric loss functions}, which are robust to learning with noisy labels for various types of noise.

118, TITLE: CAPE: Encoding Relative Positions with Continuous Augmented Positional Embeddings
AUTHORS: Tatiana Likhomanenko ; Qiantong Xu ; Ronan Collobert ; Gabriel Synnaeve ; Alex Rogozhnikov
CATEGORY: cs.LG [cs.LG, cs.CL, cs.CV]
HIGHLIGHT: In this paper, we propose an augmentation-based approach (CAPE) for absolute positional embeddings, which keeps the advantages of both absolute (simplicity and speed) and relative position embeddings (better generalization).

119, TITLE: Learnable Fourier Features for Multi-DimensionalSpatial Positional Encoding
AUTHORS: Yang Li ; Si Si ; Gang Li ; Cho-Jui Hsieh ; Samy Bengio
CATEGORY: cs.LG [cs.LG, cs.AI, cs.CV]
HIGHLIGHT: In this paper, we propose a novel positional encoding method based on learnable Fourier features.

120, TITLE: GAN Cocktail: Mixing GANs Without Dataset Access
AUTHORS: Omri Avrahami ; Dani Lischinski ; Ohad Fried
CATEGORY: cs.LG [cs.LG, cs.CV, cs.GR, cs.NE]
HIGHLIGHT: In this work we tackle the problem of model merging, given two constraints that often come up in the real world: (1) no access to the original training data, and (2) without increasing the size of the neural network.

121, TITLE: Local Disentanglement in Variational Auto-Encoders Using Jacobian $L_1$ Regularization
AUTHORS: Travers Rhodes ; Daniel D. Lee
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: Borrowing inspiration from Independent Component Analysis (ICA) and sparse coding, we propose applying an $L_1$ loss to the VAE's generative Jacobian during training to encourage local latent variable alignment with independent factors of variation in the data.

122, TITLE: Towards A Multi-purpose Robotic Nursing Assistant
AUTHORS: Krishna Chaitanya Kodur ; Kaustubh Rajpathak ; Akilesh Rajavenkatanarayanan ; Maria Kyrarini ; Fillia Makedon
CATEGORY: cs.RO [cs.RO, cs.CV, cs.SY, eess.SY]
HIGHLIGHT: To address these requirements, we propose a novel Multi-purpose Intelligent Nurse Aid (MINA) robotic system that is capable of providing walking assistance to the patients and perform teleoperation tasks with an easy-to-use and intuitive Graphical User Interface (GUI).

123, TITLE: Active Speaker Detection As A Multi-Objective Optimization with Uncertainty-based Multimodal Fusion
AUTHORS: Baptiste Pouthier ; Laurent Pilati ; Leela K. Gudupudi ; Charles Bouveyron ; Frederic Precioso
CATEGORY: cs.SD [cs.SD, cs.CL, cs.CV, eess.AS]
HIGHLIGHT: This paper outlines active speaker detection as a multi-objective learning problem to leverage best of each modalities using a novel self-attention, uncertainty-based multimodal fusion scheme.

124, TITLE: Representation Mitosis in Wide Neural Networks
AUTHORS: Diego Doimo ; Aldo Glielmo ; Sebastian Goldt ; Alessandro Laio
CATEGORY: stat.ML [stat.ML, cs.CV, cs.LG]
HIGHLIGHT: We show that a key ingredient to activate mitosis is continuing the training process until the training error is zero.

125, TITLE: A Deep Variational Bayesian Framework for Blind Image Deblurring
AUTHORS: Hui Wang ; Zongsheng Yue ; Qian Zhao ; Deyu Meng
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: In this paper, we present a deep variational Bayesian framework for blind image deblurring.

126, TITLE: Deep Neural Network-based Enhancement for Image and Video Streaming Systems: A Survey and Future Directions
AUTHORS: Royson Lee ; Stylianos I. Venieris ; Nicholas D. Lane
CATEGORY: eess.IV [eess.IV, cs.CV, cs.DC]
HIGHLIGHT: In this paper, we survey state-of-the-art content delivery systems that employ neural enhancement as a key component in achieving both fast response time and high visual quality.

127, TITLE: AOSLO-net: A Deep Learning-based Method for Automatic Segmentation of Retinal Microaneurysms from Adaptive Optics Scanning Laser Ophthalmoscope Images
AUTHORS: QIAN ZHANG et. al.
CATEGORY: eess.IV [eess.IV, cs.CV, cs.LG]
HIGHLIGHT: To address this urgency, we introduce AOSLO-net, a deep neural network framework with customized training policy, including preprocessing, data augmentation and transfer learning, to automatically segment MAs from AOSLO images.

128, TITLE: Real Time Video Based Heart and Respiration Rate Monitoring
AUTHORS: Jafar Pourbemany ; Almabrok Essa ; Ye Zhu
CATEGORY: eess.IV [eess.IV, cs.AI, cs.CV, cs.LG]
HIGHLIGHT: This study aimed to provide a method to extract heart rate and respiration rate using the video of individuals' faces.

129, TITLE: Pointwise Visual Field Estimation from Optical Coherence Tomography in Glaucoma: A Structure-function Analysis Using Deep Learning
AUTHORS: RUBEN HEMELINGS et. al.
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: We developed and validated a deep learning (DL) regression model that estimates pointwise and overall VF loss from unsegmented optical coherence tomography (OCT) scans.

130, TITLE: Brain Age Estimation From MRI Using Cascade Networks with Ranking Loss
AUTHORS: JIAN CHENG et. al.
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: In this paper, a novel 3D convolutional network, called two-stage-age-network (TSAN), is proposed to estimate brain age from T1-weighted MRI data.

131, TITLE: Knowledge-aware Deep Framework for Collaborative Skin Lesion Segmentation and Melanoma Recognition
AUTHORS: Xiaohong Wang ; Xudong Jiang ; Henghui Ding ; Yuqian Zhao ; Jun Liu
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: In this paper, we propose a novel knowledge-aware deep framework that incorporates some clinical knowledge into collaborative learning of two important melanoma diagnosis tasks, i.e., skin lesion segmentation and melanoma recognition.