计算机视觉论文-2021-07-08

本专栏是计算机视觉方向论文收集积累，时间：2021年7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: Samplets: A New Paradigm for Data Compression
AUTHORS: Helmut Harbrecht ; Michael Multerer
CATEGORY: math.NA [math.NA, cs.CV, cs.LG, cs.NA]
HIGHLIGHT: In this article, we introduce the novel concept of samplets by transferring the construction of Tausch-White wavelets to the realm of data.

2, TITLE: Blind Image Super-Resolution: A Survey and Beyond
AUTHORS: Anran Liu ; Yihao Liu ; Jinjin Gu ; Yu Qiao ; Chao Dong
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This paper serves as a systematic review on recent progress in blind image SR, and proposes a taxonomy to categorize existing methods into three different classes according to their ways of degradation modelling and the data used for solving the SR model.

3, TITLE: Introducing The Structural Bases of Typicality Effects in Deep Learning
AUTHORS: Omar Vidal Pino ; Erickson Rangel Nascimento ; Mario Fernando Montenegro Campos
CATEGORY: cs.CV [cs.CV, cs.AI, math.RT, 68T07 (Primary) 68Q55 (Secondary), I.2.4; I.2.6; I.2.10; I.4.8; I.4.10; I.5.1]
HIGHLIGHT: In this paper, we hypothesize that the effects of the degree of typicality in natural semantic categories can be generated based on the structure of artificial categories learned with deep learning models.

4, TITLE: MuVAM: A Multi-View Attention-based Model for Medical Visual Question Answering
AUTHORS: HAIWEI PAN et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Since most current medical VQA models focus on visual content, ignoring the importance of text, this paper proposes a multi-view attention-based model(MuVAM) for medical visual question answering which integrates the high-level semantics of medical images on the basis of text description.

5, TITLE: FasterPose: A Faster Simple Baseline for Human Pose Estimation
AUTHORS: HANBIN DAI et. al.
CATEGORY: cs.CV [cs.CV, I.2.8]
HIGHLIGHT: In this paper, we propose a design paradigm for cost-effective network with LR representation for efficient pose estimation, named FasterPose.

6, TITLE: Hierarchical Semantic Segmentation Using Psychometric Learning
AUTHORS: Lu Yin ; Vlado Menkovski ; Shiwei Liu ; Mykola Pechenizkiy
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: In this work, we develop a novel approach to collect segmentation annotations from experts based on psychometric testing.

7, TITLE: Scalable Data Balancing for Unlabeled Satellite Imagery
AUTHORS: Deep Patel ; Erin Gao ; Anirudh Koul ; Siddha Ganju ; Meher Anand Kasam
CATEGORY: cs.CV [cs.CV, cs.LG, eess.IV]
HIGHLIGHT: We present a new iterative method to balance unlabeled data.

8, TITLE: Categorical Relation-Preserving Contrastive Knowledge Distillation for Medical Image Classification
AUTHORS: XIAOHAN XING et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To address these issues, we propose a novel Categorical Relation-preserving Contrastive Knowledge Distillation (CRCKD) algorithm, which takes the commonly used mean-teacher model as the supervisor.

9, TITLE: PoseRN: A 2D Pose Refinement Network for Bias-free Multi-view 3D Human Pose Estimation
AUTHORS: Akihiko Sayo ; Diego Thomas ; Hiroshi Kawasaki ; Yuta Nakashima ; Katsushi Ikeuchi
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We propose a new 2D pose refinement network that learns to predict the human bias in the estimated 2D pose.

10, TITLE: Visual Odometry with An Event Camera Using Continuous Ray Warping and Volumetric Contrast Maximization
AUTHORS: YIFU WANG et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We present a new solution to tracking and mapping with an event camera.

11, TITLE: Multi-modal Affect Analysis Using Standardized Data Within Subjects in The Wild
AUTHORS: SACHIHIRO YOUOKU et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we introduce the affective recognition method focusing on facial expression (EXP) and valence-arousal calculation that was submitted to the Affective Behavior Analysis in-the-wild (ABAW) 2021 Contest.

12, TITLE: Learning Invariant Representation with Consistency and Diversity for Semi-supervised Source Hypothesis Transfer
AUTHORS: Xiaodong Wang ; Junbao Zhuo ; Shuhao Cui ; Shuhui Wang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To tackle the above issues, we propose Consistency and Diversity Learning (CDL), a simple but effective framework for SSHT by facilitating prediction consistency between two randomly augmented unlabeled data and maintaining the prediction diversity when adapting model to target domain.

13, TITLE: Cross-View Exocentric to Egocentric Video Synthesis
AUTHORS: Gaowen Liu ; Hao Tang ; Hugo Latapie ; Jason Corso ; Yan Yan
CATEGORY: cs.CV [cs.CV, cs.MM]
HIGHLIGHT: In this paper, we investigate the exocentric (third-person) view to egocentric (first-person) view video generation task.

14, TITLE: Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge Distillation
AUTHORS: Bingchen Zhao ; Kai Han
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we tackle the problem of novel visual category discovery, i.e., grouping unlabelled images from new classes into different semantic partitions by leveraging a labelled dataset that contains images from other different but relevant categories.

15, TITLE: Bi-level Feature Alignment for Versatile Image Translation and Manipulation
AUTHORS: FANGNENG ZHAN et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This paper presents a versatile image translation and manipulation framework that achieves accurate semantic and style guidance in image generation by explicitly building a correspondence.

16, TITLE: Poly-NL: Linear Complexity Non-local Layers with Polynomials
AUTHORS: FRANCESCA BABILONI et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We overcome the efficiency limitation of non-local blocks by framing them as special cases of 3rd order polynomial functions.

17, TITLE: Edge-aware Bidirectional Diffusion for Dense Depth Estimation from Light Fields
AUTHORS: Numair Khan ; Min H. Kim ; James Tompkin
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We present an algorithm to estimate fast and accurate depth maps from light fields via a sparse set of depth edges and gradients.

18, TITLE: Partial 3D Object Retrieval Using Local Binary QUICCI Descriptors and Dissimilarity Tree Indexing
AUTHORS: Bart Iver van Blokland ; Theoharis Theoharis
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: A complete pipeline is presented for accurate and efficient partial 3D object retrieval based on Quick Intersection Count Change Image (QUICCI) binary local descriptors and a novel indexing tree.

19, TITLE: E-PixelHop: An Enhanced PixelHop Method for Object Classification
AUTHORS: Yijing Yang ; Vasileios Magoulianitis ; C. -C. Jay Kuo
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Based on PixelHop and PixelHop++, which are recently developed using the successive subspace learning (SSL) framework, we propose an enhanced solution for object classification, called E-PixelHop, in this work.

20, TITLE: Disentangle Your Dense Object Detector
AUTHORS: ZEHUI CHEN et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we investigate three such important conjunctions: 1) only samples assigned as positive in classification head are used to train the regression head; 2) classification and regression share the same input feature and computational fields defined by the parallel head architecture; and 3) samples distributed in different feature pyramid layers are treated equally when computing the loss.

21, TITLE: GLiT: Neural Architecture Search for Global and Local Image Transformer
AUTHORS: BOYU CHEN et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We introduce the first Neural Architecture Search (NAS) method to find a better transformer architecture for image recognition.

22, TITLE: Action Units Recognition Using Improved Pairwise Deep Architecture
AUTHORS: JUNYA SAITO et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In the Affective Behavior Analysis in-the-wild (ABAW) 2020 competition, we proposed a new automatic Action Units (AUs) recognition method using a pairwise deep architecture to derive the Pseudo-Intensities of each AU and then convert them into predicted intensities.

23, TITLE: Controlled Caption Generation for Images Through Adversarial Attacks
AUTHORS: Nayyer Aafaq ; Naveed Akhtar ; Wei Liu ; Mubarak Shah ; Ajmal Mian
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: In contrast, we propose a GAN-based algorithm for crafting adversarial examples for neural image captioning that mimics the internal representation of the CNN such that the resulting deep features of the input image enable a controlled incorrect caption generation through the recurrent network.

24, TITLE: A Convolutional Neural Network for Teeth Margin Detection on 3-dimensional Dental Meshes
AUTHORS: Hu Chen ; Hong Li ; Bifu Hu ; Kenan Ma ; Yuchun Sun
CATEGORY: cs.CV [cs.CV, cs.AI, cs.GR]
HIGHLIGHT: We proposed a convolutional neural network for vertex classification on 3-dimensional dental meshes, and used it to detect teeth margins.

25, TITLE: Learn to Learn Metric Space for Few-Shot Segmentation of 3D Shapes
AUTHORS: Xiang Li ; Lingjing Wang ; Yi Fang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we introduce a meta-learning-based method for few-shot 3D shape segmentation where only a few labeled samples are provided for the unseen classes.

26, TITLE: SpectralFormer: Rethinking Hyperspectral Image Classification with Transformers
AUTHORS: DANFENG HONG et. al.
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: To solve this issue, we rethink HS image classification from a sequential perspective with transformers, and propose a novel backbone network called \ul{SpectralFormer}.

27, TITLE: Long Short-Term Transformer for Online Action Detection
AUTHORS: MINGZE XU et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we present Long Short-term TRansformer (LSTR), a new temporal modeling algorithm for online action detection, by employing a long- and short-term memories mechanism that is able to model prolonged sequence data.

28, TITLE: Deep Convolutional Correlation Iterative Particle Filter for Visual Tracking
AUTHORS: Reza Jalil Mozhdehi ; Henry Medeiros
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This work proposes a novel framework for visual tracking based on the integration of an iterative particle filter, a deep convolutional neural network, and a correlation filter.

29, TITLE: Group Sampling for Unsupervised Person Re-identification
AUTHORS: XUMENG HAN et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a simple yet effective approach, termed Group Sampling, to alleviate the negative impact of noisy pseudo labels within unsupervised person re-ID models.

30, TITLE: VIN: Voxel-based Implicit Network for Joint 3D Object Detection and Segmentation for Lidars
AUTHORS: Yuanxin Zhong ; Minghan Zhu ; Huei Peng
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: A unified neural network structure is presented for joint 3D object detection and point cloud segmentation in this paper.

31, TITLE: Learning Stixel-based Instance Segmentation
AUTHORS: MONTY SANTAROSSA et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work we present StixelPointNet, a novel method to perform fast instance segmentation directly on Stixels.

32, TITLE: Video-Based Camera Localization Using Anchor View Detection and Recursive 3D Reconstruction
AUTHORS: Hajime Taira ; Koki Onbe ; Naoyuki Miyashita ; Masatoshi Okutomi
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper we introduce a new camera localization strategy designed for image sequences captured in challenging industrial situations such as industrial parts inspection.

33, TITLE: FBC-GAN: Diverse and Flexible Image Synthesis Via Foreground-Background Composition
AUTHORS: Kaiwen Cui ; Gongjie Zhang ; Fangneng Zhan ; Jiaxing Huang ; Shijian Lu
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This paper presents a novel Foreground-Background Composition GAN (FBC-GAN) that performs image generation by generating foreground objects and background scenes concurrently and independently, followed by composing them with style and geometrical consistency.

34, TITLE: Mitigating Generation Shifts for Generalized Zero-Shot Learning
AUTHORS: ZHI CHEN et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we conduct an in-depth analysis on this issue and propose a novel Generation Shifts Mitigating Flow (GSMFlow) framework, which is comprised of multiple conditional affine coupling layers for learning unseen data synthesis efficiently and effectively.

35, TITLE: WeClick: Weakly-Supervised Video Semantic Segmentation with Click Annotations
AUTHORS: PEIDONG LIU et. al.
CATEGORY: cs.CV [cs.CV, cs.AI, cs.MM]
HIGHLIGHT: In this work, we propose an effective weakly-supervised video semantic segmentation pipeline with click annotations, called WeClick, for saving laborious annotating effort by segmenting an instance of the semantic class with only a single click.

36, TITLE: Greedy Offset-Guided Keypoint Grouping for Human Pose Estimation
AUTHORS: Jia Li ; Linhua Xiang ; Jiwei Chen ; Zengfu Wang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We propose a simple yet reliable bottom-up approach with a good trade-off between accuracy and efficiency for the problem of multi-person pose estimation.

37, TITLE: Trans4Trans: Efficient Transformer for Transparent Object Segmentation to Help Visually Impaired People Navigate in The Real World
AUTHORS: JIAMING ZHANG et. al.
CATEGORY: cs.CV [cs.CV, cs.HC, cs.RO]
HIGHLIGHT: To tackle this issue, we construct a wearable system with a novel dual-head Transformer for Transparency (Trans4Trans) model, which is capable of segmenting general and transparent objects and performing real-time wayfinding to assist people walking alone more safely.

38, TITLE: Urban Tree Species Classification Using Aerial Imagery
AUTHORS: Emily Waters ; Mahdi Maktabdar Oghaz ; Lakshmi Babu Saheer
CATEGORY: cs.CV [cs.CV, cs.AI, cs.LG]
HIGHLIGHT: Experimental results show our best model achieves an average accuracy of 60% over 6 tree species.

39, TITLE: Is 2D Heatmap Representation Even Necessary for Human Pose Estimation?
AUTHORS: YANJIE LI et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To address these issues, we propose a \textbf{Sim}ple yet promising \textbf{D}isentangled \textbf{R}epresentation for keypoint coordinate (\emph{SimDR}), reformulating human keypoint localization as a task of classification.

40, TITLE: HIDA: Towards Holistic Indoor Understanding for The Visually Impaired Via Semantic Instance Segmentation with A Wearable Solid-State LiDAR Sensor
AUTHORS: HUAYAO LIU et. al.
CATEGORY: cs.CV [cs.CV, cs.HC, cs.RO]
HIGHLIGHT: To tackle these issues, we propose HIDA, a lightweight assistive system based on 3D point cloud instance segmentation with a solid-state LiDAR sensor, for holistic indoor detection and avoidance.

41, TITLE: IntraLoss: Further Margin Via Gradient-Enhancing Term for Deep Face Recognition
AUTHORS: CHENGZHI JIANG et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose the `gradient-enhancing term' that concentrates on the distribution characteristics within the class.

42, TITLE: Learning Vision Transformer with Squeeze and Excitation for Facial Expression Recognition
AUTHORS: Mouath Aouayeb ; Wassim Hamidouche ; Catherine Soladie ; Kidiyo Kpalma ; Renaud Seguier
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Therefore, we propose in this paper to learn a vision Transformer jointly with a Squeeze and Excitation (SE) block for FER task.

43, TITLE: Self-supervised Outdoor Scene Relighting
AUTHORS: YE YU et. al.
CATEGORY: cs.CV [cs.CV, cs.GR]
HIGHLIGHT: In contrast, we propose a self-supervised approach for relighting.

44, TITLE: Rotation Transformation Network: Learning View-Invariant Point Cloud for Classification and Segmentation
AUTHORS: Shuang Deng ; Bo Liu ; Qiulei Dong ; Zhanyi Hu
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we aim to provide an insight into spatial manipulation modules.

45, TITLE: Plot2Spectra: An Automatic Spectra Extraction Tool
AUTHORS: WEIXIN JIANG et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we develop a plot digitizer, named Plot2Spectra, to extract data points from spectroscopy graph images in an automatic fashion, which makes it possible for large scale data acquisition and analysis.

46, TITLE: Deep Learning Based Micro-expression Recognition: A Survey
AUTHORS: Yante Li ; Jinsheng Wei ; Seyednavid Mohammadifoumani ; Yang Liu ; Guoying Zhao
CATEGORY: cs.CV [cs.CV, cs.HC]
HIGHLIGHT: In this survey, we provide a comprehensive review of deep micro-expression recognition (MER), including datasets, deep MER pipeline, and the bench-marking of most influential methods.

47, TITLE: GA-NET: Global Attention Network for Point Cloud Semantic Segmentation
AUTHORS: Shuang Deng ; Qiulei Dong
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Addressing this problem, we propose a global attention network for point cloud semantic segmentation, named as GA-Net, consisting of a point-independent global attention module and a point-dependent global attention module for obtaining contextual information of 3D point clouds in this paper.

48, TITLE: Egocentric Videoconferencing
AUTHORS: MOHAMED ELGHARIB et. al.
CATEGORY: cs.GR [cs.GR, cs.CV]
HIGHLIGHT: We introduce a method for egocentric videoconferencing that enables hands-free video calls, for instance by people wearing smart glasses or other mixed-reality devices.

49, TITLE: Structured Denoising Diffusion Models in Discrete State-Spaces
AUTHORS: Jacob Austin ; Daniel Johnson ; Jonathan Ho ; Danny Tarlow ; Rianne van den Berg
CATEGORY: cs.LG [cs.LG, cs.AI, cs.CL, cs.CV]
HIGHLIGHT: Here, we introduce Discrete Denoising Diffusion Probabilistic Models (D3PMs), diffusion-like generative models for discrete data that generalize the multinomial diffusion model of Hoogeboom et al. 2021, by going beyond corruption processes with uniform transition probabilities.

50, TITLE: Differentiable Architecture Pruning for Transfer Learning
AUTHORS: Nicolo Colombo ; Yang Gao
CATEGORY: cs.LG [cs.LG, cs.CV, stat.ML]
HIGHLIGHT: We propose a new gradient-based approach for extracting sub-architectures from a given large model.

51, TITLE: Predicting with Confidence on Unseen Distributions
AUTHORS: Devin Guillory ; Vaishaal Shankar ; Sayna Ebrahimi ; Trevor Darrell ; Ludwig Schmidt
CATEGORY: cs.LG [cs.LG, cs.CV, stat.ML, I.2.10]
HIGHLIGHT: Our work connects techniques from domain adaptation and predictive uncertainty literature, and allows us to predict model accuracy on challenging unseen distributions without access to labeled data.

52, TITLE: KaFiStO: A Kalman Filtering Framework for Stochastic Optimization
AUTHORS: ARAM DAVTYAN et. al.
CATEGORY: cs.LG [cs.LG, cs.CV, math.OC, stat.ML]
HIGHLIGHT: We propose to consider the loss as a noisy observation with respect to some reference optimum.

53, TITLE: Maintaining A Reliable World Model Using Action-aware Perceptual Anchoring
AUTHORS: Ying Siu Liang ; Dongkyu Choi ; Kenneth Kwok
CATEGORY: cs.RO [cs.RO, cs.CV]
HIGHLIGHT: In this paper, we present a model for action-aware perceptual anchoring that enables robots to track objects in a persistent manner.

54, TITLE: RAM-VO: Less Is More in Visual Odometry
AUTHORS: Iury Cleveston ; Esther L. Colombini
CATEGORY: cs.RO [cs.RO, cs.AI, cs.CV, cs.LG]
HIGHLIGHT: In this work, we propose the RAM-VO, an extension of the Recurrent Attention Model (RAM) for visual odometry tasks.

55, TITLE: Transformer Network for Significant Stenosis Detection in CCTA of Coronary Arteries
AUTHORS: Xinghua Ma ; Gongning Luo ; Wei Wang ; Kuanquan Wang
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: In this paper, we propose a Transformer network (TR-Net) for the automatic detection of significant stenosis (i.e. luminal narrowing > 50%) while practically completing the computer-assisted diagnosis of CAD.

56, TITLE: Image Complexity Guided Network Compression for Biomedical Image Segmentation
AUTHORS: Suraj Mishra ; Danny Z. Chen ; X. Sharon Hu
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: To address this, we propose an image complexity-guided network compression technique for biomedical image segmentation.

57, TITLE: End-to-End Simultaneous Learning of Single-particle Orientation and 3D Map Reconstruction from Cryo-electron Microscopy Data
AUTHORS: YOUSSEF S. G. NASHED et. al.
CATEGORY: eess.IV [eess.IV, cs.CV, q-bio.QM]
HIGHLIGHT: Here, we present an end-to-end unsupervised approach that learns individual particle orientations from cryo-EM data while reconstructing the average 3D map of the biomolecule, starting from a random initialization.

58, TITLE: Bone Surface Reconstruction and Clinical Features Estimation from Sparse Landmarks and Statistical Shape Models: A Feasibility Study on The Femur
AUTHORS: Alireza Asvadi ; Guillaume Dardenne ; Jocelyne Troccaz ; Valerie Burdin
CATEGORY: eess.IV [eess.IV, cs.CV, physics.med-ph]
HIGHLIGHT: In this study, we investigated a method allowing the determination of the femur bone surface as well as its mechanical axis from some easy-to-identify bony landmarks.

59, TITLE: GAN-based Data Augmentation for Chest X-ray Classification
AUTHORS: Shobhita Sundaram ; Neha Hulkund
CATEGORY: eess.IV [eess.IV, cs.CV, cs.LG, I.2.10]
HIGHLIGHT: In this work, we evaluate the use of GAN- based data augmentation to artificially expand the CheXpert dataset of chest radiographs.

60, TITLE: A Deep Residual Star Generative Adversarial Network for Multi-domain Image Super-Resolution
AUTHORS: Rao Muhammad Umer ; Asad Munir ; Christian Micheloni
CATEGORY: eess.IV [eess.IV, cs.CV, cs.LG]
HIGHLIGHT: To handle the multiple degradation, i.e. refers to multi-domain image super-resolution, we propose a deep Super-Resolution Residual StarGAN (SR2*GAN), a novel and scalable approach that super-resolves the LR images for the multiple LR domains using only a single model.

61, TITLE: AGD-Autoencoder: Attention Gated Deep Convolutional Autoencoder for Brain Tumor Segmentation
AUTHORS: Tim Cvetko
CATEGORY: eess.IV [eess.IV, cs.CV, cs.LG]
HIGHLIGHT: In this paper, we propose a novel attention gate (AG model) for brain tumor segmentation that utilizes both the edge detecting unit and the attention gated network to highlight and segment the salient regions from fMRI images.