计算机视觉论文-2021-06-22

本专栏是计算机视觉方向论文收集积累，时间：2021年6月23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: Image Simulation for Space Applications with The SurRender Software
AUTHORS: J�R�MY LEBRETON et. al.
CATEGORY: astro-ph.EP [astro-ph.EP, astro-ph.IM, cs.AI, cs.CV]
HIGHLIGHT: In this paper we explain why traditional rendering engines may present limitations that are potentially critical for space applications.

2, TITLE: BiAdam: Fast Adaptive Bilevel Optimization Methods
AUTHORS: Feihu Huang ; Heng Huang
CATEGORY: math.OC [math.OC, cs.CV, cs.LG]
HIGHLIGHT: Specifically, we propose a fast single-loop BiAdam algorithm based on the basic momentum technique, which achieves a sample complexity of $\tilde{O}(\epsilon^{-4})$ for finding an $\epsilon$-stationary point.

3, TITLE: Unsupervised Embedding Adaptation Via Early-Stage Feature Reconstruction for Few-Shot Classification
AUTHORS: Dong Hoon Lee ; Sae-Young Chung
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We propose unsupervised embedding adaptation for the downstream few-shot classification task.

4, TITLE: Spatial-Temporal Super-Resolution of Satellite Imagery Via Conditional Pixel Synthesis
AUTHORS: YUTONG HE et. al.
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: We propose a new conditional pixel synthesis model that uses abundant, low-cost, low-resolution imagery to generate accurate high-resolution imagery at locations and times in which it is unavailable.

5, TITLE: G-VAE, A Geometric Convolutional VAE for ProteinStructure Generation
AUTHORS: Hao Huang ; Boulbaba Ben Amor ; Xichan Lin ; Fan Zhu ; Yi Fang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we introduce a joint geometric-neural networks approach for comparing, deforming and generating 3D protein structures.

6, TITLE: Towards Reducing Labeling Cost in Deep Object Detection
AUTHORS: Ismail Elezi ; Zhiding Yu ; Anima Anandkumar ; Laura Leal-Taixe ; Jose M. Alvarez
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: In this work, we propose a unified framework for active learning, that considers both the uncertainty and the robustness of the detector, ensuring that the network performs accurately in all classes.

7, TITLE: Photozilla: A Large-Scale Photography Dataset and Visual Embedding for 20 Photography Styles
AUTHORS: Trisha Singhal ; Junhua Liu ; Lucienne T. M. Blessing ; Kwan Hui Lim
CATEGORY: cs.CV [cs.CV, cs.AI, cs.LG]
HIGHLIGHT: With this motivation, we introduce a large-scale dataset termed 'Photozilla', which includes over 990k images belonging to 10 different photographic styles.

8, TITLE: Multi-layered Semantic Representation Network for Multi-label Image Classification
AUTHORS: Xiwen Qu ; Hao Che ; Jun Huang ; Linchuan Xu ; Xiao Zheng
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: On the one hand, besides the local semantics of each label, we propose to further explore global semantics shared by multiple labels.

9, TITLE: FDeblur-GAN: Fingerprint Deblurring Using Generative Adversarial Network
AUTHORS: Amol S. Joshi ; Ali Dabouei ; Jeremy Dawson ; Nasser M. Nasrabadi
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We propose a fingerprint deblurring model FDeblur-GAN, based on the conditional Generative Adversarial Networks (cGANs) and multi-stage framework of the stack GAN.

10, TITLE: BEyond Observation: An Approach for ObjectNav
AUTHORS: Daniel V. Ruiz ; Eduardo Todt
CATEGORY: cs.CV [cs.CV, cs.RO]
HIGHLIGHT: In this work, we present our exploratory research of how sensor data fusion and state-of-the-art machine learning algorithms can perform the Embodied Artificial Intelligence (E-AI) task called Visual Semantic Navigation.

11, TITLE: Creating A New Color Space Utilizing PSO and FCM to Perform Skin Detection By Using Neural Network and ANFIS
AUTHORS: Kobra Nazaria ; Samaneh Mazaheri ; Bahram Sadeghi Bigham
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this study, first a new color space is created using FCM and PSO algorithms.

12, TITLE: Tracking Instances As Queries
AUTHORS: SHUSHENG YANG et. al.
CATEGORY: cs.CV [cs.CV, cs.AI, cs.MM]
HIGHLIGHT: In this paper, we present \textbf{QueryTrack} (i.e., tracking instances as queries), a unified query based VIS framework fully leveraging the intrinsic one-to-one correspondence between instances and queries in QueryInst.

13, TITLE: SSUL: Semantic Segmentation with Unknown Label for Exemplar-based Class-Incremental Learning
AUTHORS: Sungmin Cha. Beomyoung Kim ; Youngjoon Yoo ; Taesup Moon
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: To better address these challenges, we propose a new method, dubbed as SSUL-M (Semantic Segmentation with Unknown Label with Memory), by carefully combining several techniques tailored for semantic segmentation.

14, TITLE: RGB2Hands: Real-Time Tracking of 3D Hand Interactions from Monocular RGB Video
AUTHORS: JIAYI WANG et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In contrast, in this work we present the first real-time method for motion capture of skeletal pose and 3D surface geometry of hands from a single RGB camera that explicitly considers close interactions.

15, TITLE: NuPlan: A Closed-loop ML-based Planning Benchmark for Autonomous Vehicles
AUTHORS: HOLGER CAESAR et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we propose the world's first closed-loop ML-based planning benchmark for autonomous driving. We provide a high-quality dataset with 1500h of human driving data from 4 cities across the US and Asia with widely varying traffic patterns (Boston, Pittsburgh, Las Vegas and Singapore). We will provide a closed-loop simulation framework with reactive agents and provide a large set of both general and scenario-specific planning metrics.

16, TITLE: Universal Domain Adaptation in Ordinal Regression
AUTHORS: Chidlovskii Boris ; Assem Sadek ; Christian Wolf
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: We propose a method that complements the OR classifier with an auxiliary task of order learning, which plays the double role of discriminating between common and private instances, and expanding class labels to the private target images via ranking.

17, TITLE: Winning The CVPR'2021 Kinetics-GEBD Challenge: Contrastive Learning Approach
AUTHORS: Hyolim Kang ; Jinwoo Kim ; Kyungmin Kim ; Taehyun Kim ; Seon Joo Kim
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we introduce a novel contrastive learning based approach to deal with the GEBD.

18, TITLE: PALMAR: Towards Adaptive Multi-inhabitant Activity Recognition in Point-Cloud Technology
AUTHORS: Mohammad Arif Ul Alam ; Md Mahmudur Rahman ; Jared Q Widberg
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: More specifically, we propose (i) a voxelized feature representation-based real-time PCD fine-tuning method, (ii) efficient clustering (DBSCAN and BIRCH), Adaptive Order Hidden Markov Model based multi-person tracking and crossover ambiguity reduction techniques and (iii) novel adaptive deep learning-based domain adaptation technique to improve the accuracy of HAR in presence of data scarcity and diversity (device, location and population diversity).

19, TITLE: A Comparison for Patch-level Classification of Deep Learning Methods on Transparent Images: from Convolutional Neural Networks to Visual Transformers
AUTHORS: HECHEN YANG et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we compare the classification performance of different deep learning for the problem that transparent images are difficult to analyze.

20, TITLE: Enhanced Separable Disentanglement for Unsupervised Domain Adaptation
AUTHORS: Youshan Zhang ; Brian D. Davison
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a novel enhanced separable disentanglement (ESD) model.

21, TITLE: RootPainter3D: Interactive-machine-learning Enables Rapid and Accurate Contouring for Radiotherapy
AUTHORS: ABRAHAM GEORGE SMITH et. al.
CATEGORY: cs.CV [cs.CV, cs.HC, cs.LG]
HIGHLIGHT: We compare the method to the Eclipse contouring software and find strong agreement with manual delineations, with a dice score of 0.95.

22, TITLE: Residual Networks As Flows of Velocity Fields for Diffeomorphic Time Series Alignment
AUTHORS: Hao Huang ; Boulbaba Ben Amor ; Xichan Lin ; Fan Zhu ; Yi Fang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a novel diffeomorphic temporal transformer network for both pairwise and joint time-series alignment.

23, TITLE: Evaluation of A Region Proposal Architecture for Multi-task Document Layout Analysis
AUTHORS: Lorenzo Quir�s ; Enrique Vidal
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: The most common application is to feed downstream applications such as automatic text recognition and keyword spotting; however, the recognition of the layout also helps to establish relationships between elements in the document which allows to enrich the information that can be extracted.

24, TITLE: Gait Analysis with Curvature Maps: A Simulation Study
AUTHORS: Khac Chinh Tran ; Marc Daniel ; Jean Meunier
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper we propose to focus our attention on extracting relevant curvature information from the body surface provided by a depth camera.

25, TITLE: Multimodal Trajectory Forecasting Based on Discrete Heat Map
AUTHORS: Jingni Yuan ; Jianyun Xu ; Yushi Zhu
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We use vectorized lane map and 2 s targets' history trajectories as input.

26, TITLE: MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Images
AUTHORS: Shaofei Wang ; Marko Mihajlovic ; Qianli Ma ; Andreas Geiger ; Siyu Tang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we aim to create generalizable and controllable neural signed distance fields (SDFs) that represent clothed humans from monocular depth observations.

27, TITLE: Hand-Drawn Electrical Circuit Recognition Using Object Detection and Node Recognition
AUTHORS: Rachala Rohith Reddy ; Mahesh Raveendranatha Panicker
CATEGORY: cs.CV [cs.CV, eess.IV]
HIGHLIGHT: This paper proposes a real-time algorithm for the automatic recognition of hand-drawn electrical circuits based on object detection and circuit node recognition.

28, TITLE: Unsupervised Object-Level Representation Learning from Scene Images
AUTHORS: Jiahao Xie ; Xiaohang Zhan ; Ziwei Liu ; Yew Soon Ong ; Chen Change Loy
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To overcome this limitation, we introduce Object-level Representation Learning (ORL), a new self-supervised learning framework towards scene images.

29, TITLE: An Alternative Auxiliary Task for Enhancing Image Classification
AUTHORS: Chen Liu
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we investigate ``estimating the Fourier Transform of the input image" as a potential alternative auxiliary task, in the hope that it may further boost the performances on the primary task or introduce novel constraints not well covered by image reconstruction.

30, TITLE: MODETR: Moving Object Detection with Transformers
AUTHORS: Eslam Mohamed ; Ahmad El-Sallab
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: In this paper, we tackle this problem through multi-head attention mechanisms, both across the spatial and motion streams.

31, TITLE: Normalized Avatar Synthesis Using StyleGAN and Perceptual Refinement
AUTHORS: HUIWEN LUO et. al.
CATEGORY: cs.CV [cs.CV, cs.GR]
HIGHLIGHT: We introduce a highly robust GAN-based framework for digitizing a normalized 3D avatar of a person from a single unconstrained photo. We further introduce a Normalized Face Dataset, which consists of a combination photogrammetry scans, carefully selected photographs, and generated fake people with neutral expressions in diffuse lighting conditions.

32, TITLE: Domain-Smoothing Network for Zero-Shot Sketch-Based Image Retrieval
AUTHORS: Zhipeng Wang ; Hao Wang ; Jiexi Yan ; Aming Wu ; Cheng Deng
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Toward this end, we propose a novel Domain-Smoothing Network (DSN) for ZS-SBIR.

33, TITLE: Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation
AUTHORS: LEI KE et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We propose Prototypical Cross-Attention Network (PCAN), capable of leveraging rich spatio-temporal information for online multiple object tracking and segmentation.

34, TITLE: Wallpaper Texture Generation and Style Transfer Based on Multi-label Semantics
AUTHORS: YING GAO et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Based on these labels and generative adversarial networks, we present a framework for perception driven wallpaper texture generation and style transfer.

35, TITLE: VoxelEmbed: 3D Instance Segmentation and Tracking with Voxel Embedding Based Deep Learning
AUTHORS: MENGYANG ZHAO et. al.
CATEGORY: cs.CV [cs.CV, eess.IV]
HIGHLIGHT: In this work, we propose a novel spatial-temporal voxel-embedding (VoxelEmbed) based learning method to perform simultaneous cell instance segmenting and tracking on 3D volumetric video sequences.

36, TITLE: SeqNetVLAD Vs PointNetVLAD: Image Sequence Vs 3D Point Clouds for Day-Night Place Recognition
AUTHORS: Sourav Garg ; Michael Milford
CATEGORY: cs.CV [cs.CV, cs.AI, cs.IR, cs.LG, cs.RO]
HIGHLIGHT: In this extended abstract, we attempt to compare these two types of methods by considering a similar ``metric span'' to represent places.

37, TITLE: DocFormer: End-to-End Transformer for Document Understanding
AUTHORS: Srikar Appalaraju ; Bhavan Jasani ; Bhargava Urala Kota ; Yusheng Xie ; R. Manmatha
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We present DocFormer -- a multi-modal transformer based architecture for the task of Visual Document Understanding (VDU).

38, TITLE: Deep3DPose: Realtime Reconstruction of Arbitrarily Posed Human Bodies from Single RGB Images
AUTHORS: LIGUO JIANG et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We introduce an approach that accurately reconstructs 3D human poses and detailed 3D full-body geometric models from single images in realtime.

39, TITLE: Part-Aware Measurement for Robust Multi-View Multi-Human 3D Pose Estimation and Tracking
AUTHORS: HAU CHU et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This paper introduces an approach for multi-human 3D pose estimation and tracking based on calibrated multi-view.

40, TITLE: GAIA: A Transfer Learning System of Object Detection That Fits Your Needs
AUTHORS: Xingyuan Bu ; Junran Peng ; Junjie Yan ; Tieniu Tan ; Zhaoxiang Zhang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we focus on the area of object detection and present a transfer learning system named GAIA, which could automatically and efficiently give birth to customized solutions according to heterogeneous downstream needs.

41, TITLE: Self-Supervised Iterative Contextual Smoothing for Efficient Adversarial Defense Against Gray- and Black-Box Attack
AUTHORS: Sungmin Cha ; Naeun Ko ; Youngjoon Yoo ; Taesup Moon
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: We propose a novel and effective input transformation based adversarial defense method against gray- and black-box attack, which is computationally efficient and does not require any adversarial training or retraining of a classification model.

42, TITLE: MEAL: Manifold Embedding-based Active Learning
AUTHORS: Deepthi Sreenivasaiah ; Thomas Wollmann
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: In this work, we propose a new pool-based method for active learning, which proposes promising image regions, in each acquisition step.

43, TITLE: HybVIO: Pushing The Limits of Real-time Visual-inertial Odometry
AUTHORS: OTTO SEISKARI et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We present HybVIO, a novel hybrid approach for combining filtering-based visual-inertial odometry (VIO) with optimization-based SLAM.

44, TITLE: Zero-Shot Chinese Character Recognition with Stroke-Level Decomposition
AUTHORS: Jingye Chen ; Bin Li ; Xiangyang Xue
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: Inspired by the fact that humans can generalize to know how to write characters unseen before if they have learned stroke orders of some characters, we propose a stroke-based method by decomposing each character into a sequence of strokes, which are the most basic units of Chinese characters.

45, TITLE: The Hitchhiker's Guide to Prior-Shift Adaptation
AUTHORS: Tomas Sipka ; Milan Sulc ; Jiri Matas
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: We propose a novel method to address a known issue of prior estimation methods based on confusion matrices, where inconsistent estimates of decision probabilities and confusion matrices lead to negative values in the estimated priors.

46, TITLE: Spatio-Temporal Multi-Task Learning Transformer for Joint Moving Object Detection and Segmentation
AUTHORS: Eslam Mohamed ; Ahmed El-Sallab
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: In this paper, we present a Multi-Task Learning architecture, based on Transformers, to jointly perform both tasks through one network.

47, TITLE: Mapping Slums with Medium Resolution Satellite Imagery: A Comparative Analysis of Multi-Spectral Data and Grey-level Co-occurrence Matrix Techniques
AUTHORS: Agatha C. H. de Mattos ; Gavin McArdle ; Michela Bertolotto
CATEGORY: cs.CV [cs.CV, cs.CY]
HIGHLIGHT: In this paper, we evaluate two techniques (multi-spectral data and grey-level co-occurrence matrix feature extraction) on an open-access dataset consisting of labelled Sentinel-2 images with a spatial resolution of 10 meters.

48, TITLE: Confidence-Aware Learning for Camouflaged Object Detection
AUTHORS: Jiawei Liu ; Jing Zhang ; Nick Barnes
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We present a confidence-aware camouflaged object detection framework using dynamic supervision to produce both accurate camouflage map and meaningful "confidence" representing model awareness about the current prediction.

49, TITLE: Give Me Your Trained Model: Domain Adaptive Semantic Segmentation Without Source Data
AUTHORS: Yuxi Wang ; Jian Liang ; Zhaoxiang Zhang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Benefited from considerable pixel-level annotations collected from a specific situation (source), the trained semantic segmentation model performs quite well, but fails in a new situation (target) due to the large domain shift.

50, TITLE: A Latent Transformer for Disentangled and Identity-Preserving Face Editing
AUTHORS: Xu Yao ; Alasdair Newson ; Yann Gousseau ; Pierre Hellier
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To tackle these limitations, we propose to edit facial attributes via the latent space of a StyleGAN generator, by training a dedicated latent transformation network and incorporating explicit disentanglement and identity preservation terms in the loss function.

51, TITLE: Data Augmentation for Opcode Sequence Based Malware Detection
AUTHORS: Niall McLaughlin ; Jesus Martinez del Rincon
CATEGORY: cs.CR [cs.CR, cs.CV, cs.LG]
HIGHLIGHT: In this paper we study different methods of data augmentation starting with basic methods using fixed transformations and moving to methods that adapt to the data.

52, TITLE: On The Importance of Cross-task Features for Class-incremental Learning
AUTHORS: Albin Soutif--Cormerais ; Marc Masana ; Joost Van de Weijer ; Bart?omiej Twardowski
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: In this paper, we ablate the learning of cross-task features and study its influence on the performance of basic replay strategies used for class-IL.

53, TITLE: Dive Into Deep Learning
AUTHORS: Aston Zhang ; Zachary C. Lipton ; Mu Li ; Alexander J. Smola
CATEGORY: cs.LG [cs.LG, cs.AI, cs.CL, cs.CV]
HIGHLIGHT: Our goal is to offer a resource that could (i) be freely available for everyone; (ii) offer sufficient technical depth to provide a starting point on the path to actually becoming an applied machine learning scientist; (iii) include runnable code, showing readers how to solve problems in practice; (iv) allow for rapid updates, both by us and also by the community at large; (v) be complemented by a forum for interactive discussion of technical details and to answer questions.

54, TITLE: Kernel Clustering with Sigmoid-based Regularization for Efficient Segmentation of Sequential Data
AUTHORS: Tung Doan ; Atsuhiro Takasu
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: In this paper, we take a differentiable approach to alleviate the aforementioned issues.

55, TITLE: Differentiable Architecture Search Without Training Nor Labels: A Pruning Perspective
AUTHORS: MIAO ZHANG et. al.
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: By leveraging recent techniques on the network pruning at initialization, we designed a FreeFlow proxy to score the importance of candidate operations in NAS without any training nor labels, and proposed a novel framework called \textit{training and label free neural architecture search} (\textbf{FreeNAS}) accordingly.

56, TITLE: Recent Deep Semi-supervised Learning Approaches and Related Works
AUTHORS: Gyeongho Kim
CATEGORY: cs.LG [cs.LG, cs.AI, cs.CV]
HIGHLIGHT: Based on the key assumptions of semi-supervised learning, which are the manifold assumption, cluster assumption, and continuity assumption, the work reviews the recent semi-supervised learning approaches.

57, TITLE: F-Domain-Adversarial Learning: Theory and Algorithms
AUTHORS: David Acuna ; Guojun Zhang ; Marc T. Law ; Sanja Fidler
CATEGORY: cs.LG [cs.LG, cs.AI, cs.CV]
HIGHLIGHT: In this paper, we introduce a novel and general domain-adversarial framework.

58, TITLE: Incremental Deep Neural Network Learning Using Classification Confidence Thresholding
AUTHORS: Justin Leo ; Jugal Kalita
CATEGORY: cs.LG [cs.LG, cs.CL, cs.CV]
HIGHLIGHT: To address these problems, this paper proposes the Classification Confidence Threshold approach to prime neural networks for incremental learning to keep accuracies high by limiting forgetting.

59, TITLE: SA-LOAM: Semantic-aided LiDAR SLAM with Loop Closure
AUTHORS: LIN LI et. al.
CATEGORY: cs.RO [cs.RO, cs.AI, cs.CV]
HIGHLIGHT: In this paper, we present a novel semantic-aided LiDAR SLAM with loop closure based on LOAM, named SA-LOAM, which leverages semantics in odometry as well as loop closure detection.

60, TITLE: A Survey on Human-aware Robot Navigation
AUTHORS: Ronja M�ller ; Antonino Furnari ; Sebastiano Battiato ; Aki H�rm� ; Giovanni Maria Farinella
CATEGORY: cs.RO [cs.RO, cs.CV]
HIGHLIGHT: This paper is concerned with the navigation aspect of a socially-compliant robot and provides a survey of existing solutions for the relevant areas of research as well as an outlook on possible future directions.

61, TITLE: MIMIR: Deep Regression for Automated Analysis of UK Biobank Body MRI
AUTHORS: Taro Langner ; Andr�s Mart�nez Mora ; Robin Strand ; H�kan Ahlstr�m ; Joel Kullberg
CATEGORY: eess.IV [eess.IV, cs.CV, cs.LG]
HIGHLIGHT: This work aims to make the proposed system available for free to researchers, who can use it to obtain fast and fully-automated estimates of 72 different measurements immediately upon release of new UK Biobank image data.

62, TITLE: Context-aware PolyUNet for Liver and Lesion Segmentation from Abdominal CT Images
AUTHORS: Liping Zhang ; Simon Chun-Ho Yu
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: To tackle these issues, we propose a novel context-aware PolyUNet for accurate liver and lesion segmentation.

63, TITLE: Learning-Based Practical Light Field Image Compression Using A Disparity-Aware Model
AUTHORS: Mohana Singh ; Renu M. Rameshan
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: We propose a new learning-based, disparity-aided model for compression of 4D light field images capable of parallel decoding.

64, TITLE: Encoder-Decoder Architectures for Clinically Relevant Coronary Artery Segmentation
AUTHORS: JO�O LOUREN�O SILVA et. al.
CATEGORY: eess.IV [eess.IV, cs.CV, cs.LG]
HIGHLIGHT: Based on the EfficientNet and the UNet++ architectures, we propose a line of efficient and high-performance segmentation models using a new decoder architecture, the EfficientUNet++, whose best-performing version achieved average dice scores of 0.8904 and 0.7526 for the artery and catheter classes, respectively, and an average generalized dice score of 0.9234.