计算机视觉论文-2021-07-28

本专栏是计算机视觉方向论文收集积累，时间：2021年7月28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: Language Grounding with 3D Objects
AUTHORS: Jesse Thomason ; Mohit Shridhar ; Yonatan Bisk ; Chris Paxton ; Luke Zettlemoyer
CATEGORY: cs.CL [cs.CL, cs.AI, cs.CV, cs.LG, cs.RO]
HIGHLIGHT: In this work, we introduce a novel reasoning task that targets both visual and non-visual language about 3D objects.

2, TITLE: Self-Supervised Video Object Segmentation By Motion-Aware Mask Propagation
AUTHORS: Bo Miao ; Mohammed Bennamoun ; Yongsheng Gao ; Ajmal Mian
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We propose a self-supervised spatio-temporal matching method coined Motion-Aware Mask Propagation (MAMP) for semi-supervised video object segmentation.

3, TITLE: CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization Via Conditional Normalizing Flows
AUTHORS: Denis Gudovskiy ; Shun Ishizaka ; Kazuki Kozuka
CATEGORY: cs.CV [cs.CV, cs.AI, cs.LG]
HIGHLIGHT: In this paper, we propose a real-time model and analytically derive its relationship to prior methods.

4, TITLE: ENHANCE (ENriching Health Data By ANnotations of Crowd and Experts): A Case Study for Skin Lesion Classification
AUTHORS: Ralf Raumanns ; Gerard Schouten ; Max Joosten ; Josien P. W. Pluim ; Veronika Cheplygina
CATEGORY: cs.CV [cs.CV, cs.HC, cs.LG]
HIGHLIGHT: We present ENHANCE, an open dataset with multiple annotations to complement the existing ISIC and PH2 skin lesion classification datasets.

5, TITLE: Perception-and-Regulation Network for Salient Object Detection
AUTHORS: Jinchao Zhu ; Xiaoyu Zhang ; Xian Fang ; Junnan Liu
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we focus on the feature relationship and propose a novel global attention unit, which we term the "perception- and-regulation" (PR) block, that adaptively regulates the feature fusion process by explicitly modeling interdependencies between features.

6, TITLE: Cross-modal Consensus Network for Weakly Supervised Temporal Action Localization
AUTHORS: Fa-Ting Hong ; Jia-Chang Feng ; Dan Xu ; Ying Shan ; Wei-Shi Zheng
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we argue that the features extracted from the pretrained extractor, e.g., I3D, are not the WS-TALtask-specific features, thus the feature re-calibration is needed for reducing the task-irrelevant information redundancy.

7, TITLE: Nearest Neighborhood-Based Deep Clustering for Source Data-absent Unsupervised Domain Adaptation
AUTHORS: SONG TANG et. al.
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: This paper proposes a novel deep clustering method for this challenging task.

8, TITLE: Remember What You Have Drawn: Semantic Image Manipulation with Memory
AUTHORS: Xiangxi Shi ; Zhonghua Wu ; Guosheng Lin ; Jianfei Cai ; Shafiq Joty
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Therefore, in this paper, we propose a memory-based Image Manipulation Network (MIM-Net), where a set of memories learned from images is introduced to synthesize the texture information with the guidance of the textual description.

9, TITLE: Identify Apple Leaf Diseases Using Deep Learning Algorithm
AUTHORS: Daping Zhang ; Hongyu Yang ; Jiayu Cao
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: To address this problem, we apply CNNs to plant disease recognition by building a classification model.

10, TITLE: DV-Det: Efficient 3D Point Cloud Object Detection with Dynamic Voxelization
AUTHORS: Zhaoyu Su ; Pin Siang Tan ; Yu-Hsing Wang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we propose a novel two-stage framework for the efficient 3D point cloud object detection.

11, TITLE: Multi-Scale Local-Temporal Similarity Fusion for Continuous Sign Language Recognition
AUTHORS: PAN XIE et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To address the issue, we propose to adaptively fuse local features via temporal similarity for this task.

12, TITLE: Segmentation in Style: Unsupervised Semantic Image Segmentation with Stylegan and CLIP
AUTHORS: Daniil Pakhomov ; Sanchit Hira ; Narayani Wagle ; Kemar E. Green ; Nassir Navab
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We introduce a method that allows to automatically segment images into semantically meaningful regions without human supervision.

13, TITLE: Dynamic and Static Object Detection Considering Fusion Regions and Point-wise Features
AUTHORS: Andr�s G�mez ; Thomas Genevois ; Jerome Lussereau ; Christian Laugier
CATEGORY: cs.CV [cs.CV, cs.RO]
HIGHLIGHT: This paper proposes a new approach to detect static and dynamic objects in front of an autonomous vehicle.

14, TITLE: Predicting Take-over Time for Autonomous Driving with Real-World Data: Robust Data Augmentation, Models, and Evaluation
AUTHORS: Akshay Rangesh ; Nachiket Deo ; Ross Greer ; Pujitha Gunaratne ; Mohan M. Trivedi
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Here, we introduce a scheme for data augmentation for such a dataset.

15, TITLE: Discriminative-Generative Representation Learning for One-Class Anomaly Detection
AUTHORS: XUAN XIA et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In order to improve the representation learning ability of generator, we propose a self-supervised learning framework combining generative methods and discriminative methods.

16, TITLE: Feature Fusion Methods for Indexing and Retrieval of Biometric Data: Application to Face Recognition with Privacy Protection
AUTHORS: Pawel Drozdowski ; Fabian Stockhardt ; Christian Rathgeb ; Dail� Osorio-Roig ; Christoph Busch
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, a method of protected indexing of biometric data is presented.

17, TITLE: H3D-Net: Few-Shot High-Fidelity 3D Head Reconstruction
AUTHORS: EDUARD RAMON et. al.
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: In this paper, we tackle these limitations for the specific problem of few-shot full 3D head reconstruction, by endowing coordinate-based representations with a probabilistic shape prior that enables faster convergence and better generalization when using few input images (down to three).

18, TITLE: A Comprehensive Study on Colorectal Polyp Segmentation with ResUNet++, Conditional Random Field and Test-Time Augmentation
AUTHORS: DEBESH JHA et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we demonstrate that further improvements to the overall prediction performance of the ResUNet++ architecture can be achieved by using conditional random field and test-time augmentation.

19, TITLE: Computer Vision-Based Guidance Assistance Concept for Plowing Using RGB-D Camera
AUTHORS: Erkin T�rk�z ; Ertug Olcay ; Timo Oksanen
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This paper proposes a concept of computer vision-based guidance assistance for agricultural vehicles to increase the accuracy in plowing and reduce driver's cognitive burden in long-lasting tillage operations.

20, TITLE: A Physiologically-adapted Gold Standard for Arousal During A Stress Induced Scenario
AUTHORS: ALICE BAIRD et. al.
CATEGORY: cs.CV [cs.CV, cs.LG, cs.SD]
HIGHLIGHT: In this contribution, we utilise a dataset which includes continuous emotion and physiological signals - Heartbeats per Minute (BPM), Electrodermal Activity (EDA), and Respiration-rate - captured during a stress induced scenario (Trier Social Stress Test).

21, TITLE: Vision-Guided Forecasting -- Visual Context for Multi-Horizon Time Series Forecasting
AUTHORS: Eitan Kosman ; Dotan Di Castro
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: In this paper, we tackle multi-horizon forecasting of vehicle states by fusing the two modalities.

22, TITLE: Disentangled Implicit Shape and Pose Learning for Scalable 6D Pose Estimation
AUTHORS: YILIN WEN et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we present a novel approach for scalable 6D pose estimation, by self-supervised learning on synthetic data of multiple objects using a single autoencoder.

23, TITLE: Enriching Local and Global Contexts for Temporal Action Localization
AUTHORS: Zixin Zhu ; Wei Tang ; Le Wang ; Nanning Zheng ; Gang Hua
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We address this challenge by enriching both the local and global contexts in the popular two-stage temporal localization framework, where action proposals are first generated followed by action classification and temporal boundary regression.

24, TITLE: Unsupervised Outlier Detection Using Memory and Contrastive Learning
AUTHORS: NING HUYAN et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Unsupervised Outlier Detection Using Memory and Contrastive Learning

25, TITLE: BridgeNet: A Joint Learning Network of Depth Map Super-Resolution and Monocular Depth Estimation
AUTHORS: QI TANG et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Inspired by the multi-task learning, we propose a joint learning network of depth map super-resolution (DSR) and monocular depth estimation (MDE) without introducing additional supervision labels.

26, TITLE: Exploring Sequence Feature Alignment for Domain Adaptive Detection Transformers
AUTHORS: WEN WANG et. al.
CATEGORY: cs.CV [cs.CV, cs.LG, 68T45 (Primary) 68T07 (Secondary), I.2.10; I.4.9]
HIGHLIGHT: To address this issue, we propose a novel Sequence Feature Alignment (SFA) method that is specially designed for the adaptation of detection transformers.

27, TITLE: Adaptive Denoising Via GainTuning
AUTHORS: SREYAS MOHAN et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Here we propose "GainTuning", in which CNN models pre-trained on large datasets are adaptively and selectively adjusted for individual test images.

28, TITLE: Analyzing Vehicle Pedestrian Interactions Combining Data Cube Structure and Predictive Collision Risk Estimation Model
AUTHORS: Byeongjoon Noh ; Hansaem Park ; Hwasoo Yeo
CATEGORY: cs.CV [cs.CV, cs.CY]
HIGHLIGHT: This study introduces a new concept of a pedestrian safety system that combines the field and the centralized processes.

29, TITLE: Rethinking Counting and Localization in Crowds:A Purely Point-Based Framework
AUTHORS: QINGYU SONG et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a purely point-based framework for joint crowd counting and individual localization.

30, TITLE: Learning Local Recurrent Models for Human Mesh Recovery
AUTHORS: RUNZE LI et. al.
CATEGORY: cs.CV [cs.CV, cs.LG, cs.RO]
HIGHLIGHT: To address these issues, we present a new method for video mesh recovery that divides the human mesh into several local parts following the standard skeletal model.

31, TITLE: MonoIndoor: Towards Good Practice of Self-Supervised Monocular Depth Estimation for Indoor Environments
AUTHORS: Pan Ji ; Runze Li ; Bir Bhanu ; Yi Xu
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, special considerations are given to those challenges and a set of good practices are consolidated for improving the performance of self-supervised monocular depth estimation in indoor environments.

32, TITLE: Image Scene Graph Generation (SGG) Benchmark
AUTHORS: XIAOTIAN HAN et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This paper presents main features of our benchmark and a comprehensive ablation study of scene graph generation models using the Visual Genome and OpenImages Visual relationship detection datasets.

33, TITLE: Technical Report: Quality Assessment Tool for Machine Learning with Clinical CT
AUTHORS: RIQIANG GAO et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Here, we create and illustrate a pipeline specifically designed to identify and resolve issues encountered with large-scale data mining of clinically acquired CT data.

34, TITLE: PiSLTRc: Position-informed Sign Language Transformer with Content-aware Convolution
AUTHORS: Pan Xie ; Mengyi Zhao ; Xiaohui Hu
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To address these issues, we propose a new model architecture, namely PiSLTRc, with two distinctive characteristics: (i) content-aware and position-aware convolution layers.

35, TITLE: Real-Time Activity Recognition and Intention Recognition Using A Vision-based Embedded System
AUTHORS: Sahar Darafsh ; Saeed Shiry Ghidary ; Morteza Saheb Zamani
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this research, we introduce a real-time activity recognition to recognize people's intentions to pass or not pass a door.

36, TITLE: Adaptive Boundary Proposal Network for Arbitrary Shape Text Detection
AUTHORS: Shi-Xue Zhang ; Xiaobin Zhu ; Chun Yang ; Hongfa Wang ; Xu-Cheng Yin
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we propose a novel adaptive boundary proposal network for arbitrary shape text detection, which can learn to directly produce accurate boundary for arbitrary shape text without any post-processing.

37, TITLE: Towards Efficient Tensor Decomposition-Based DNN Model Compression with Optimization Framework
AUTHORS: Miao Yin ; Yang Sui ; Siyu Liao ; Bo Yuan
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: In this paper, we propose a systematic framework for tensor decomposition-based model compression using Alternating Direction Method of Multipliers (ADMM).

38, TITLE: Adversarial Attacks with Time-Scale Representations
AUTHORS: ALBERTO SANTAMARIA-PANG et. al.
CATEGORY: cs.CV [cs.CV, cs.AI, cs.CR]
HIGHLIGHT: We propose a novel framework for real-time black-box universal attacks which disrupts activations of early convolutional layers in deep learning models.

39, TITLE: Semantically Self-Aligned Network for Text-to-Image Part-aware Person Re-identification
AUTHORS: Zefeng Ding ; Changxing Ding ; Zhiyin Shao ; Dacheng Tao
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Accordingly, in this paper, we propose a Semantically Self-Aligned Network (SSAN) to handle the above problems. Finally, to expedite future research in text-to-image ReID, we build a new database named ICFG-PEDES.

40, TITLE: Circular-Symmetric Correlation Layer Based on FFT
AUTHORS: Bahar Azari ; Deniz Erdogmus
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: We propose a Circular-symmetric Correlation Layer (CCL) based on the formalism of roto-translation equivariant correlation on the continuous group $S^1 \times \mathbb{R}$, and implement it efficiently using the well-known Fast Fourier Transform (FFT) algorithm.

41, TITLE: CalCROP21: A Georeferenced Multi-spectral Dataset of Satellite Imagery and Crop Labels
AUTHORS: RAHUL GHOSH et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we create a new semantic segmentation benchmark dataset, which we call CalCROP21, for the diverse crops in the Central Valley region of California at 10m spatial resolution using a Google Earth Engine based robust image processing pipeline and a novel attention based spatio-temporal semantic segmentation algorithm STATT. We have released the dataset and the processing pipeline code for generating the benchmark dataset.

42, TITLE: Co-Transport for Class-Incremental Learning
AUTHORS: Da-Wei Zhou ; Han-Jia Ye ; De-Chuan Zhan
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: As a result, we propose CO-transport for class Incremental Learning (COIL), which learns to relate across incremental tasks with the class-wise semantic relationship.

43, TITLE: StarEnhancer: Learning Real-Time and Style-Aware Image Enhancement
AUTHORS: Yuda Song ; Hui Qian ; Xin Du
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a deep learning-based image enhancement method covering multiple tonal styles using only a single model dubbed StarEnhancer.

44, TITLE: Transferable Knowledge-Based Multi-Granularity Aggregation Network for Temporal Action Localization: Submission to ActivityNet Challenge 2021
AUTHORS: HAISHENG SU et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, to train a supervised temporal action localizer, we adopt Temporal Context Aggregation Network (TCANet) to generate high-quality action proposals through ``local and global" temporal context aggregation and complementary as well as progressive boundary refinement.

45, TITLE: RGL-NET: A Recurrent Graph Learning Framework for Progressive Part Assembly
AUTHORS: Abhinav Narayan Harish ; Rajendra Nagar ; Shanmuganathan Raman
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we tackle this problem using a recurrent graph learning framework considering inter-part relations and the progressive update of the part pose.

46, TITLE: Uniformity in Heterogeneity:Diving Deep Into Count Interval Partition for Crowd Counting
AUTHORS: CHANGAN WANG et. al.
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: Following the above two theoretically demonstrated criterions, we propose a simple yet effective model termed Uniform Error Partition Network (UEPNet), which achieves state-of-the-art performance on several challenging datasets.

47, TITLE: CKConv: Learning Feature Voxelization for Point Cloud Analysis
AUTHORS: SUNGMIN WOO et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we present Cubic Kernel Convolution (CKConv) that learns to voxelize the features of local points by exploiting both continuous and discrete convolutions.

48, TITLE: Coarse to Fine: Domain Adaptive Crowd Counting Via Adversarial Scoring Network
AUTHORS: ZHIKANG ZOU et. al.
CATEGORY: cs.CV [cs.CV, cs.MM]
HIGHLIGHT: To facilitate this issue, this paper proposes a novel adversarial scoring network (ASNet) to gradually bridge the gap across domains from coarse to fine granularity.

49, TITLE: Real-time Keypoints Detection for Autonomous Recovery of The Unmanned Ground Vehicle
AUTHORS: JIE LI et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This paper proposes a novel autonomous recovery framework with a low-cost monocular vision system to provide accurate positioning and attitude estimation of the UGV during navigation.

50, TITLE: Greedy Gradient Ensemble for Robust Visual Question Answering
AUTHORS: Xinzhe Han ; Shuhui Wang ; Chi Su ; Qingming Huang ; Qi Tian
CATEGORY: cs.CV [cs.CV, cs.CL, cs.LG]
HIGHLIGHT: Language bias is a critical issue in Visual Question Answering (VQA), where models often exploit dataset biases for the final decision without considering the image information.

51, TITLE: Parallel Detection for Efficient Video Analytics at The Edge
AUTHORS: Yanzhao Wu ; Ling Liu ; Ramana Kompella
CATEGORY: cs.DC [cs.DC, cs.CV]
HIGHLIGHT: We use the offline detection as a reference model, and examine the root cause by analyzing the mismatch among the incoming video streaming rate, video processing rate for object detection, and output rate for real time detection visualization of video streaming.

52, TITLE: Deep Reinforcement Learning for L3 Slice Localization in Sarcopenia Assessment
AUTHORS: OTHMANE LAOUSY et. al.
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: In this paper, we propose a deep reinforcement learning method for accurate localization of the L3 CT slice.

53, TITLE: Improving ClusterGAN Using Self-AugmentedInformation Maximization of Disentangling LatentSpaces
AUTHORS: Tanmoy Dam ; Sreenatha G. Anavatti ; Hussein A. Abbass
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: In this paper, we proposeself-augmentation information maximization improved Clus-terGAN (SIMI-ClusterGAN) to learn the distinctive priorsfrom the data.

54, TITLE: COPS: Controlled Pruning Before Training Starts
AUTHORS: Paul Wimmer ; Jens Mehnert ; Alexandru Condurache
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: In this work we do not concentrate on a single pruning criterion, but provide a framework for combining arbitrary GSSs to create more powerful pruning strategies.

55, TITLE: Energy-Based Open-World Uncertainty Modeling for Confidence Calibration
AUTHORS: YEZHEN WANG et. al.
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: To address this problem, we for the first time propose a novel $K$+1-way softmax formulation, which incorporates the modeling of open-world uncertainty as the extra dimension.

56, TITLE: Continual Learning with Neuron Activation Importance
AUTHORS: Sohee Kim ; Seungkyu Lee
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: In this paper, we propose a neuron activation importance-based regularization method for stable continual learning regardless of the order of tasks.

57, TITLE: Multi-modal Estimation of The Properties of Containers and Their Content: Survey and Evaluation
AUTHORS: ALESSIO XOMPERO et. al.
CATEGORY: cs.MM [cs.MM, cs.CV, cs.SD, eess.AS]
HIGHLIGHT: In this paper, we present an open benchmarking framework and an in-depth comparative analysis of recent methods that estimate the capacity of a container, as well as the type, mass, and amount of its content.

58, TITLE: Angel's Girl for Blind Painters: An Efficient Painting Navigation System Validated By Multimodal Evaluation Approach
AUTHORS: HANG LIU et. al.
CATEGORY: cs.MM [cs.MM, cs.AI, cs.CV]
HIGHLIGHT: Therefore, to maximally bridge this gap, we propose a painting navigation system to assist blind people in painting and artistic creation.

59, TITLE: VIPose: Real-time Visual-Inertial 6D Object Pose Tracking
AUTHORS: Rundong Ge ; Giuseppe Loianno
CATEGORY: cs.RO [cs.RO, cs.CV]
HIGHLIGHT: In this work, we introduce a novel Deep Neural Network (DNN) called VIPose, that combines inertial and camera data to address the object pose tracking problem in real-time.

60, TITLE: Optimizing Operating Points for High Performance Lesion Detection and Segmentation Using Lesion Size Reweighting
AUTHORS: Brennan Nichyporuk ; Justin Szeto ; Douglas L. Arnold ; Tal Arbel
CATEGORY: eess.IV [eess.IV, cs.CV, cs.LG]
HIGHLIGHT: In this work, we propose a novel reweighing strategy to eliminate this performance gap, increasing small pathology detection performance while maintaining segmentation accuracy.

61, TITLE: SaRNet: A Dataset for Deep Learning Assisted Search and Rescue with Satellite Imagery
AUTHORS: Michael Thoreau ; Frazer Wilson
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: We propose a novel remote sensing object detection dataset for deep learning assisted SaR.

62, TITLE: Sharp U-Net: Depthwise Convolutional Network for Biomedical Image Segmentation
AUTHORS: Hasib Zunair ; A. Ben Hamza
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: To address these limitations, we propose a simple, yet effective end-to-end depthwise encoder-decoder fully convolutional network architecture, called Sharp U-Net, for binary and multi-class biomedical image segmentation.

63, TITLE: A Persistent Homology-based Topological Loss for CNN-based Multi-class Segmentation of CMR
AUTHORS: Nick Byrne ; James R Clough ; Isra Valverde ; Giovanni Montana ; Andrew P King
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: Our work extends these approaches to the task of multi-class segmentation.

64, TITLE: Improved-Mask R-CNN: Towards An Accurate Generic MSK MRI Instance Segmentation Platform (Data from The Osteoarthritis Initiative)
AUTHORS: Banafshe Felfeliyan ; Abhilash Hareendranathan ; Gregor Kuntze ; Jacob L. Jaremko ; Janet L. Ronsky
CATEGORY: eess.IV [eess.IV, cs.CV, cs.LG]
HIGHLIGHT: This study deployed Mask R-CNN instance segmentation and improved it (improved-Mask R-CNN (iMaskRCNN)) to obtain a more accurate generalized segmentation for OA-associated tissues.