计算机视觉论文-2021-07-02

本专栏是计算机视觉方向论文收集积累，时间：2021年7月2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: GlyphCRM: Bidirectional Encoder Representation for Chinese Character with Its Glyph
AUTHORS: YUNXIN LI et. al.
CATEGORY: cs.AI [cs.AI, cs.CL, cs.CV]
HIGHLIGHT: Inspired by previous methods, we innovatively propose a Chinese pre-trained representation model named as GlyphCRM, which abandons the ID-based character embedding method yet solely based on sequential character images.

2, TITLE: Interviewer-Candidate Role Play: Towards Developing Real-World NLP Systems
AUTHORS: Neeraj Varshney ; Swaroop Mishra ; Chitta Baral
CATEGORY: cs.CL [cs.CL, cs.AI, cs.CV, cs.LG]
HIGHLIGHT: In this work, we take a step towards bridging this gap and present a multi-stage task that simulates a typical human-human questioner-responder interaction such as an interview.

3, TITLE: Circuit Complexity of Visual Search
AUTHORS: Kei Uchizawa ; Haruki Abe
CATEGORY: cs.CC [cs.CC, cs.CV, cs.LG, cs.NE]
HIGHLIGHT: We employ a threshold circuit or a discretized circuit (such as a sigmoid circuit or a ReLU circuit with discretization) as our models of neural networks, and consider the following four computational resources: [i] the number of neurons (size), [ii] the number of levels (depth), [iii] the number of active neurons outputting non-zero values (energy), and [iv] synaptic weight resolution (weight).

4, TITLE: Action Transformer: A Self-Attention Model for Short-Time Human Action Recognition
AUTHORS: Vittorio Mazzia ; Simone Angarano ; Francesco Salvetti ; Federico Angelini ; Marcello Chiaberge
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: In this work, we introduce Action Transformer (AcT), a simple, fully self-attentional architecture that consistently outperforms more elaborated networks that mix convolutional, recurrent, and attentive layers.

5, TITLE: Attention Bottlenecks for Multimodal Fusion
AUTHORS: ARSHA NAGRANI et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Instead, we introduce a novel transformer based architecture that uses `fusion bottlenecks' for modality fusion at multiple layers.

6, TITLE: PoliTO-IIT Submission to The EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition
AUTHORS: Chiara Plizzari ; Mirco Planamente ; Emanuele Alberti ; Barbara Caputo
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this report, we describe the technical details of our submission to the EPIC-Kitchens-100 Unsupervised Domain Adaptation (UDA) Challenge in Action Recognition.

7, TITLE: One-class Steel Detector Using Patch GAN Discriminator for Visualising Anomalous Feature Map
AUTHORS: Takato Yasuno ; Junichiro Fujii ; Sakura Fukami
CATEGORY: cs.CV [cs.CV, eess.IV, I.5.4; I.2.10]
HIGHLIGHT: In this paper, we propose a general-purpose application for steel anomaly detection that consists of the following four components.

8, TITLE: Individual Tree Detection and Crown Delineation with 3D Information from Multi-view Satellite Images
AUTHORS: Changlin Xiao ; Rongjun Qin ; Xiao Xie ; Xu Huang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To fully explore the satellite images, we propose a ITDD method using the orthophoto and digital surface model (DSM) derived from the multi-view satellite data.

9, TITLE: 3D Iterative Spatiotemporal Filtering for Classification of Multitemporal Satellite Data Sets
AUTHORS: HESSAH ALBANWAN et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Therefore, in this article we investigate he use of a multitemporal orthophoto and digital surface model derived from satellite data for spatiotemporal classification.

10, TITLE: MIDV-2020: A Comprehensive Benchmark Dataset for Identity Document Analysis
AUTHORS: KONSTANTIN BULATOV et. al.
CATEGORY: cs.CV [cs.CV, cs.DL, 68T10]
HIGHLIGHT: In this paper, we present a dataset MIDV-2020 which consists of 1000 video clips, 2000 scanned images, and 1000 photos of 1000 unique mock identity documents, each with unique text field values and unique artificially generated faces, with rich annotation.

11, TITLE: MASS: Multi-Attentional Semantic Segmentation of LiDAR Data for Dense Top-View Understanding
AUTHORS: KUNYU PENG et. al.
CATEGORY: cs.CV [cs.CV, cs.RO]
HIGHLIGHT: In this paper, we introduce MASS - a Multi-Attentional Semantic Segmentation model specifically built for dense top-view understanding of the driving scenes.

12, TITLE: On The Detection-to-track Association for Online Multi-object Tracking
AUTHORS: Xufeng Lin ; Chang-Tsun Li ; Victor Sanchez ; Carsten Maple
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we propose a hybrid track association (HTA) algorithm that models the historical appearance distances of a track with an incremental Gaussian mixture model (IGMM) and incorporates the derived statistical information into the calculation of the detection-to-track association cost.

13, TITLE: Inter Extreme Points Geodesics for Weakly Supervised Segmentation
AUTHORS: REUBEN DORENT et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We introduce $\textit{InExtremIS}$, a weakly supervised 3D approach to train a deep image segmentation network using particularly weak train-time annotations: only 6 extreme clicks at the boundary of the objects of interest.

14, TITLE: Towards Measuring Bias in Image Classification
AUTHORS: Nina Schaaf ; Omar de Mitri ; Hang Beom Kim ; Alexander Windberger ; Marco F. Huber
CATEGORY: cs.CV [cs.CV, cs.LG, stat.ML]
HIGHLIGHT: In this work, we present a systematic approach to uncover data bias by means of attribution maps.

15, TITLE: Improving Task Adaptation for Cross-domain Few-shot Learning
AUTHORS: Wei-Hong Li ; Xialei Liu ; Hakan Bilen
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we look at the problem of cross-domain few-shot classification that aims to learn a classifier from previously unseen classes and domains with few labeled samples.

16, TITLE: A Unified Framework of Bundle Adjustment and Feature Matching for High-Resolution Satellite Images
AUTHORS: Xiao Ling ; Xu Huang ; Rongjun Qin
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To avoid a degeneracy in the optimization, we propose a comprised solution by breaking the optimization of the global energy function into two-step suboptimizations and compute the local minimums of each suboptimization in an incremental manner.

17, TITLE: Few-Shot Learning with A Strong Teacher
AUTHORS: Han-Jia Ye ; Lu Ming ; De-Chuan Zhan ; Wei-Lun Chao
CATEGORY: cs.CV [cs.CV, cs.AI, cs.LG]
HIGHLIGHT: In this paper, we point out two potential weaknesses of this approach.

18, TITLE: Egocentric Image Captioning for Privacy-Preserved Passive Dietary Intake Monitoring
AUTHORS: JIANING QIU et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a privacy-preserved secure solution (i.e., egocentric image captioning) for dietary assessment with passive monitoring, which unifies food recognition, volume estimation, and scene understanding.

19, TITLE: VideoLightFormer: Lightweight Action Recognition Using Transformers
AUTHORS: Raivo Koot ; Haiping Lu
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: In this work, we fill this gap and investigate the use of transformers for efficient action recognition.

20, TITLE: E-DSSR: Efficient Dynamic Surgical Scene Reconstruction with Transformer-based Stereoscopic Depth Perception
AUTHORS: YONGHAO LONG et. al.
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: In this work, we present an efficient reconstruction pipeline for highly dynamic surgical scenes that runs at 28 fps.

21, TITLE: Semi-Sparsity for Smoothing Filters
AUTHORS: Junqing Huang ; Haihui Wang ; Xuechao Wang ; Michael Ruzhansky
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose an interesting semi-sparsity smoothing algorithm based on a novel sparsity-inducing optimization framework.

22, TITLE: Drone Swarm Patrolling with Uneven Coverage Requirements
AUTHORS: Claudio Piciarelli ; Gian Luca Foresti
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we focus on visual coverage optimization with drone-mounted camera sensors.

23, TITLE: SSC: Semantic Scan Context for Large-Scale Place Recognition
AUTHORS: Lin Li ; Xin Kong ; Xiangrui Zhao ; Tianxin Huang ; Yong Liu
CATEGORY: cs.CV [cs.CV, cs.RO]
HIGHLIGHT: Concretely, we propose a novel global descriptor, Semantic Scan Context, which explores semantic information to represent scenes more effectively.

24, TITLE: Deep Auxiliary Learning for Visual Localization Using Colorization Task
AUTHORS: Mi Tian ; Qiong Nie ; Hao Shen ; Xiahua Xia
CATEGORY: cs.CV [cs.CV, cs.RO]
HIGHLIGHT: To this end, we propose a novel auxiliary learning strategy for camera localization by introducing scene-specific high-level semantics from self-supervised representation learning task.

25, TITLE: Generic Event Boundary Detection Challenge at CVPR 2021 Technical Report: Cascaded Temporal Attention Network (CASTANET)
AUTHORS: Dexiang Hong ; Congcong Li ; Longyin Wen ; Xinyao Wang ; Libo Zhang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This report presents the approach used in the submission of Generic Event Boundary Detection (GEBD) Challenge at CVPR21.

26, TITLE: End-to-end Compression Towards Machine Vision: Network Architecture Design and Optimization
AUTHORS: Shurun Wang ; Zhao Wang ; Shiqi Wang ; Yan Ye
CATEGORY: cs.CV [cs.CV, cs.MM, eess.IV]
HIGHLIGHT: In this paper, we show that the design and optimization of network architecture could be further improved for compression towards machine vision.

27, TITLE: IMiGUE: An Identity-free Video Dataset for Micro-Gesture Understanding and Emotion Analysis
AUTHORS: XIN LIU et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We introduce a new dataset for the emotional artificial intelligence research: identity-free video dataset for Micro-Gesture Understanding and Emotion analysis (iMiGUE).

28, TITLE: Orthonormal Product Quantization Network for Scalable Face Image Retrieval
AUTHORS: Ming Zhang ; Xuefei Zhe ; Hong Yan
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Unlike prior deep quantization methods where the codewords for quantization are learned from data, we propose a novel scheme using predefined orthonormal vectors as codewords, which aims to enhance the quantization informativeness and reduce the codewords' redundancy.

29, TITLE: On The Practicality of Deterministic Epistemic Uncertainty
AUTHORS: JANIS POSTELS et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: On the premise of informative representations, these deterministic uncertainty methods (DUMs) achieve strong performance on detecting out-of-distribution (OOD) data while adding negligible computational costs at inference time.

30, TITLE: Deep Orthogonal Fusion: Multimodal Prognostic Biomarker Discovery Integrating Radiology, Pathology, Genomic, and Clinical Data
AUTHORS: NATHANIEL BRAMAN et. al.
CATEGORY: cs.CV [cs.CV, cs.LG, cs.MM, q-bio.GN, q-bio.QM]
HIGHLIGHT: To maximize the information gleaned from each modality, we introduce a multimodal orthogonalization (MMO) loss term that increases model performance by incentivizing constituent embeddings to be more complementary.

31, TITLE: Global Filter Networks for Image Classification
AUTHORS: Yongming Rao ; Wenliang Zhao ; Zheng Zhu ; Jiwen Lu ; Jie Zhou
CATEGORY: cs.CV [cs.CV, cs.AI, cs.LG]
HIGHLIGHT: In this paper, we present the Global Filter Network (GFNet), a conceptually simple yet computationally efficient architecture, that learns long-term spatial dependencies in the frequency domain with log-linear complexity.

32, TITLE: Simple Training Strategies and Model Scaling for Object Detection
AUTHORS: Xianzhi Du ; Barret Zoph ; Wei-Chih Hung ; Tsung-Yi Lin
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: In this paper, we methodically evaluate a variety of these techniques to understand where most of the improvements in modern detection systems come from.

33, TITLE: Focal Self-attention for Local-Global Interactions in Vision Transformers
AUTHORS: JIANWEI YANG et. al.
CATEGORY: cs.CV [cs.CV, cs.AI, cs.LG]
HIGHLIGHT: In this paper, we present focal self-attention, a new mechanism that incorporates both fine-grained local and coarse-grained global interactions.

34, TITLE: OPT: Omni-Perception Pre-Trainer for Cross-Modal Understanding and Generation
AUTHORS: JING LIU et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose an Omni-perception Pre-Trainer (OPT) for cross-modal understanding and generation, by jointly modeling visual, text and audio resources.

35, TITLE: DVS-Attacks: Adversarial Attacks on Dynamic Vision Sensors for Spiking Neural Networks
AUTHORS: Alberto Marchisio ; Giacomo Pira ; Maurizio Martina ; Guido Masera ; Muhammad Shafique
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: Toward this, we propose DVS-Attacks, a set of stealthy yet efficient adversarial attack methodologies targeted to perturb the event sequences that compose the input of the SNNs.

36, TITLE: CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows
AUTHORS: XIAOYI DONG et. al.
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: We present CSWin Transformer, an efficient and effective Transformer-based backbone for general-purpose vision tasks.

37, TITLE: CLIP-It! Language-Guided Video Summarization
AUTHORS: Medhini Narasimhan ; Anna Rohrbach ; Trevor Darrell
CATEGORY: cs.CV [cs.CV, cs.AI, cs.MM]
HIGHLIGHT: This work introduces CLIP-It, a single framework for addressing both generic and query-focused video summarization, typically approached separately in the literature.

38, TITLE: AutoFormer: Searching Transformers for Visual Recognition
AUTHORS: Minghao Chen ; Houwen Peng ; Jianlong Fu ; Haibin Ling
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we propose a new one-shot architecture search framework, namely AutoFormer, dedicated to vision transformer search.

39, TITLE: Fair Visual Recognition in Limited Data Regime Using Self-Supervision and Self-Distillation
AUTHORS: Pratik Mazumder ; Pravendra Singh ; Vinay P. Namboodiri
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a novel approach to address this problem.

40, TITLE: CLDA: Contrastive Learning for Semi-Supervised Domain Adaptation
AUTHORS: Ankit Singh
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a simple Contrastive Learning framework for semi-supervised Domain Adaptation (CLDA) that attempts to bridge the intra-domain gap between the labeled and unlabeled target distributions and inter-domain gap between source and unlabeled target distribution in SSDA.

41, TITLE: Generating Synthetic Training Data for Deep Learning-Based UAV Trajectory Prediction
AUTHORS: Stefan Becker ; Ronny Hug ; Wolfgang H�bner ; Michael Arens ; Brendan T. Morris
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Towards this end, we present an approach for generating synthetic trajectory data of unmanned-aerial-vehicles (UAVs) in image space.

42, TITLE: CBNetV2: A Composite Backbone Network Architecture for Object Detection
AUTHORS: TINGTING LIANG et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a novel backbone network, namely CBNetV2, by constructing compositions of existing open-sourced pre-trained backbones.

43, TITLE: Overhead-MNIST: Machine Learning Baselines for Image Classification
AUTHORS: Erik Larsen ; David Noever ; Korey MacVittie ; John Lilly
CATEGORY: cs.CV [cs.CV, cs.AI, cs.LG]
HIGHLIGHT: We present results for the overall best performing algorithm as a baseline for edge deployability and future performance improvement: a convolutional neural network (CNN) scoring 0.965 categorical accuracy on unseen test data.

44, TITLE: Learning to Disambiguate Strongly Interacting Hands Via Probabilistic Per-pixel Part Segmentation
AUTHORS: ZICONG FAN et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Motivated by this insight, we propose DIGIT, a novel method for estimating the 3D poses of two interacting hands from a single monocular image.

45, TITLE: Segmenting 3D Hybrid Scenes Via Zero-Shot Learning
AUTHORS: Bo Liu ; Qiulei Dong ; Zhanyi Hu
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To this end, we propose a network to synthesize point features for various classes of objects by leveraging the semantic features of both seen and unseen object classes, called PFNet. Besides we also introduce two benchmarks for algorithmic evaluation by re-organizing the public S3DIS and ScanNet datasets under six different data splits.

46, TITLE: Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win The Jackpot?
AUTHORS: XIAOLONG MA et. al.
CATEGORY: cs.LG [cs.LG, cs.AI, cs.CV]
HIGHLIGHT: Based on our analysis, we summarize a guideline for parameter settings in regards of specific architecture characteristics, which we hope to catalyze the research progress on the topic of lottery ticket hypothesis.

47, TITLE: Revisiting Knowledge Distillation: An Inheritance and Exploration Framework
AUTHORS: ZHEN HUANG et. al.
CATEGORY: cs.LG [cs.LG, cs.AI, cs.CV]
HIGHLIGHT: In this paper, we propose a novel inheritance and exploration knowledge distillation framework (IE-KD), in which a student model is split into two parts - inheritance and exploration.

48, TITLE: A Survey on Graph-Based Deep Learning for Computational Histopathology
AUTHORS: David Ahmedt-Aristizabal ; Mohammad Ali Armin ; Simon Denman ; Clinton Fookes ; Lars Petersson
CATEGORY: cs.LG [cs.LG, cs.CV, q-bio.TO]
HIGHLIGHT: In this review, we provide a conceptual grounding of graph-based deep learning and discuss its current success for tumor localization and classification, tumor invasion and staging, image retrieval, and survival prediction.

49, TITLE: Unsupervised Model Drift Estimation with Batch Normalization Statistics for Dataset Shift Detection and Model Selection
AUTHORS: Wonju Lee ; Seok-Yong Byun ; Jooeun Kim ; Minje Park ; Kirill Chechil
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: In this paper, we propose a novel method of model drift estimation by exploiting statistics of batch normalization layer on unlabeled test data.

50, TITLE: Scalable Certified Segmentation Via Randomized Smoothing
AUTHORS: Marc Fischer ; Maximilian Baader ; Martin Vechev
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: We present a new certification method for image and point cloud segmentation based on randomized smoothing.

51, TITLE: Generalization and Robustness Implications in Object-Centric Learning
AUTHORS: ANDREA DITTADI et. al.
CATEGORY: cs.LG [cs.LG, cs.CV, stat.ML]
HIGHLIGHT: In this paper, we train state-of-the-art unsupervised models on five common multi-object datasets and evaluate segmentation accuracy and downstream object property prediction.

52, TITLE: FedMix: Approximation of Mixup Under Mean Augmented Federated Learning
AUTHORS: Tehrim Yoon ; Sumin Shin ; Sung Ju Hwang ; Eunho Yang
CATEGORY: cs.LG [cs.LG, cs.AI, cs.CV, cs.DC]
HIGHLIGHT: To resolve this issue, we propose a simple framework, Mean Augmented Federated Learning (MAFL), where clients send and receive averaged local data, subject to the privacy requirements of target applications.

53, TITLE: Stabilizing Deep Q-Learning with ConvNets and Vision Transformers Under Data Augmentation
AUTHORS: Nicklas Hansen ; Hao Su ; Xiaolong Wang
CATEGORY: cs.LG [cs.LG, cs.CV, cs.RO]
HIGHLIGHT: In this paper, we investigate causes of instability when using data augmentation in common off-policy RL algorithms.

54, TITLE: Dep-$L_0$: Improving $L_0$-based Network Sparsification Via Dependency Modeling
AUTHORS: Yang Li ; Shihao Ji
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: To mitigate this deficiency, we propose a dependency modeling of binary gates, which can be modeled effectively as a multi-layer perceptron (MLP).

55, TITLE: AdaXpert: Adapting Neural Architecture for Growing Data
AUTHORS: SHUAICHENG NIU et. al.
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: To address this, we present a neural architecture adaptation method, namely Adaptation eXpert (AdaXpert), to efficiently adjust previous architectures on the growing data.

56, TITLE: Multi-modal Graph Learning for Disease Prediction
AUTHORS: SHUAI ZHENG et. al.
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: In this paper, we propose an end-to-end Multimodal Graph Learning framework (MMGL) for disease prediction.

57, TITLE: Improving Human Motion Prediction Through Continual Learning
AUTHORS: Mohammad Samin Yasar ; Tariq Iqbal
CATEGORY: cs.RO [cs.RO, cs.CV]
HIGHLIGHT: In this work, we propose a modular sequence learning approach that allows end-to-end training while also having the flexibility of being fine-tuned.

58, TITLE: Learning to See Before Learning to Act: Visual Pre-training for Manipulation
AUTHORS: Lin Yen-Chen ; Andy Zeng ; Shuran Song ; Phillip Isola ; Tsung-Yi Lin
CATEGORY: cs.RO [cs.RO, cs.CV]
HIGHLIGHT: Our key insight is that outputs of standard vision models highly correlate with affordance maps commonly used in manipulation.

59, TITLE: Automated Detection and Diagnosis of Diabetic Retinopathy: A Comprehensive Survey
AUTHORS: Vasudevan Lakshminarayanan ; Hoda Kherdfallah ; Arya Sarkar ; J. Jothi Balaji
CATEGORY: eess.IV [eess.IV, cs.CV, J.3, I.4, I.2]
HIGHLIGHT: This review covers the literature dealing with AI approaches to DR that have been published in the open literature over a five year span (2016-2021).

60, TITLE: DivergentNets: Medical Image Segmentation By Network Ensemble
AUTHORS: Vajira Thambawita ; Steven A. Hicks ; P�l Halvorsen ; Michael A. Riegler
CATEGORY: eess.IV [eess.IV, cs.CV, cs.LG]
HIGHLIGHT: For our contribution to the EndoCV 2021 segmentation challenge, we propose two separate approaches.

61, TITLE: Feasibility of Haralick's Texture Features for The Classification of Chromogenic In-situ Hybridization Images
AUTHORS: STOYAN PAVLOV et. al.
CATEGORY: eess.IV [eess.IV, cs.CV, q-bio.QM]
HIGHLIGHT: This paper presents a proof of concept for the usefulness of second-order texture features for the qualitative analysis and classification of chromogenic in-situ hybridization whole slide images in high-throughput imaging experiments.

62, TITLE: Lossless Coding of Point Cloud Geometry Using A Deep Generative Model
AUTHORS: Dat Thanh Nguyen ; Maurice Quach ; Giuseppe Valenzise ; Pierre Duhamel
CATEGORY: eess.IV [eess.IV, cs.CV, cs.LG]
HIGHLIGHT: This paper proposes a lossless point cloud (PC) geometry compression method that uses neural networks to estimate the probability distribution of voxel occupancy.

63, TITLE: Supervised Segmentation with Domain Adaptation for Small Sampled Orbital CT Images
AUTHORS: SUNGHO SUH et. al.
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: In this paper, we have explored supervised segmentation using domain adaptation for optic nerve and orbital tumor, when only small sampled CT images are given.

64, TITLE: Explainable Diabetic Retinopathy Detection and Retinal Image Generation
AUTHORS: Yuhao Niu ; Lin Gu ; Yitian Zhao ; Feng Lu
CATEGORY: eess.IV [eess.IV, cs.CV, cs.LG]
HIGHLIGHT: Inspired by Koch's Postulates, the foundation in evidence-based medicine (EBM) to identify the pathogen, we propose to exploit the interpretability of deep learning application in medical diagnosis.