2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)最新文献_第3页

Student Engagement Dataset 学生参与度数据集

2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) Pub Date : 2021-10-01 DOI: 10.1109/ICCVW54120.2021.00405

K. Delgado, Juan Manuel Origgi, Tania Hasanpoor, Hao Yu, Danielle A. Allessio, I. Arroyo, William Lee, Margrit Betke, B. Woolf, Sarah Adel Bargal

引用次数: 19

Weakly-Supervised Semantic Segmentation by Learning Label Uncertainty 基于标签不确定性学习的弱监督语义分割

2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) Pub Date : 2021-10-01 DOI: 10.1109/ICCVW54120.2021.00193

R. Neven, D. Neven, Bert De Brabandere, M. Proesmans, Toon Goedem'e

{"title":"Weakly-Supervised Semantic Segmentation by Learning Label Uncertainty","authors":"R. Neven, D. Neven, Bert De Brabandere, M. Proesmans, Toon Goedem'e","doi":"10.1109/ICCVW54120.2021.00193","DOIUrl":"https://doi.org/10.1109/ICCVW54120.2021.00193","url":null,"abstract":"Since the rise of deep learning, many computer vision tasks have seen significant advancements. However, the downside of deep learning is that it is very data-hungry. Especially for segmentation problems, training a deep neural net requires dense supervision in the form of pixel-perfect image labels, which are very costly. In this paper, we present a new loss function to train a segmentation network with only a small subset of pixel-perfect labels, but take the advantage of weakly-annotated training samples in the form of cheap bounding-box labels. Unlike recent works which make use of box-to-mask proposal generators, our loss trains the network to learn a label uncertainty within the bounding-box, which can be leveraged to perform online bootstrapping (i.e. transforming the boxes to segmentation masks), while training the network. We evaluated our method on binary segmentation tasks, as well as a multi-class segmentation task (CityScapes vehicles and persons). We trained each task on a dataset comprised of only 18% pixel-perfect and 82% bounding-box labels, and compared the results to a baseline model trained on a completely pixel-perfect dataset. For the binary segmentation tasks, our method achieves an IoU score which is 98.33% as good as our baseline model, while for the multi-class task, our method is 97.12% as good as our baseline model (77.5 vs. 79.8 mIoU).","PeriodicalId":226794,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124583102","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Emotion Recognition With Sequential Multi-task Learning Technique 基于顺序多任务学习技术的情绪识别

2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) Pub Date : 2021-10-01 DOI: 10.1109/ICCVW54120.2021.00400

Phan Tran Dac Thinh, Hoang Manh Hung, Hyung-Jeong Yang, Soohyung Kim, Gueesang Lee

引用次数: 4

A transformer-based framework for automatic COVID19 diagnosis in chest CTs 基于变压器的胸部ct自动诊断框架

2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) Pub Date : 2021-10-01 DOI: 10.1109/ICCVW54120.2021.00063

Lei Zhang, Yan-mao Wen

{"title":"A transformer-based framework for automatic COVID19 diagnosis in chest CTs","authors":"Lei Zhang, Yan-mao Wen","doi":"10.1109/ICCVW54120.2021.00063","DOIUrl":"https://doi.org/10.1109/ICCVW54120.2021.00063","url":null,"abstract":"Automated diagnosis of covid19 in chest CTs is becoming a clinically important technique to support precision and efficient diagnosis and treatment planning. A few efforts have been made to automatically diagnose the COVID-19 in CTs using CNNs, and the task still remains a challenge. In this paper, we present a transformer-based framework for COVID19 classification. We attempt to expand the adaption of vision transformer as a robust feature learner to the 3D CTs to diagnose the COVID-19. The framework consists of two main stages: lung segmentation using UNet followed by the classification, in which the features extracted from each CT slice using Swin transformer in a CT scan are aggregated into 3D volume level feature. We also investigated the performance of using the robust CNNs (BiT and EfficientNetV2) as backbones in the framework. The dataset from the ICCV workshop: MIA-COV19D, is used in our experiments. The evaluation results show that the method with the backbone of Swin transformer gain the best F1 score of 0.935 on the validation dataset, while the CNN based backbone of EfficientNetV2 has the competitive classification performance with the best precision of 93.7%. The final prediction model with Swin transformer achieves the F1 score of 0.84 on the test dataset, which doesn’t require an additional post-processing stage.","PeriodicalId":226794,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114881055","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 26

ToFNest: Efficient normal estimation for time-of-flight depth cameras ToFNest:飞行时间深度相机的有效正常估计

2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) Pub Date : 2021-10-01 DOI: 10.1109/ICCVW54120.2021.00205

Szilárd Molnár, Benjamin Kelényi, L. Tamás

引用次数: 3

Point Cloud Object Segmentation Using Multi Elevation-Layer 2D Bounding-Boxes 基于多高程层二维边界盒的点云目标分割

2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) Pub Date : 2021-10-01 DOI: 10.1109/ICCVW54120.2021.00438

Tristan Brodeur, H. Aliakbarpour, S. Suddarth

{"title":"Point Cloud Object Segmentation Using Multi Elevation-Layer 2D Bounding-Boxes","authors":"Tristan Brodeur, H. Aliakbarpour, S. Suddarth","doi":"10.1109/ICCVW54120.2021.00438","DOIUrl":"https://doi.org/10.1109/ICCVW54120.2021.00438","url":null,"abstract":"Segmentation of point clouds is a necessary pre-processing technique when object discrimination is needed for scene understanding. In this paper, we propose a segmentation technique utilizing 2D bounding-box data obtained via the orthographic projection of 3D points onto a plane at multiple elevation layers. Connected components is utilized to obtain bounding-box data, and a consistency metric between bounding-boxes at various elevation layers helps determine the classification of the bounding-box to an object of the scene. The merging of point data within each 2D bounding-box results in an object-segmented point cloud. Our method conducts segmentation using only the topological information of the point data within a dataset, requiring no extra computation of normals, creation of an octree or k-d tree, nor a dependency on RGB or intensity data associated with a point. Initial experiments are run on a set of point cloud datasets obtained via photogrammetric means, as well as some open-source, LIDAR-generated point clouds, showing the method to be capture agnostic. Results demonstrate the efficacy of this method in obtaining a distinct set of objects contained within a point cloud.","PeriodicalId":226794,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124123718","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Deep Quaternion Pose Proposals for 6D Object Pose Tracking 用于6D目标姿态跟踪的深度四元数姿态建议

2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) Pub Date : 2021-10-01 DOI: 10.1109/ICCVW54120.2021.00032

Mateusz Majcher, B. Kwolek

{"title":"Deep Quaternion Pose Proposals for 6D Object Pose Tracking","authors":"Mateusz Majcher, B. Kwolek","doi":"10.1109/ICCVW54120.2021.00032","DOIUrl":"https://doi.org/10.1109/ICCVW54120.2021.00032","url":null,"abstract":"In this work we study quaternion pose distributions for tracking in RGB image sequences the 6D pose of an object selected from a set of objects, for which common models were trained in advance. We propose an unit quaternion representation of the rotational state space for a particle filter, which is then integrated with the particle swarm optimization to shift samples toward local maximas. Owing to k-means++ we better maintain multimodal probability distributions. We train convolutional neural networks to estimate the 2D positions of fiducial points and then to determine PnP-based object pose hypothesis. A CNN is utilized to estimate the positions of fiducial points in order to calculate PnP-based object pose hypothesis. A common Siamese neural network for all objects, which is trained on keypoints from current and previous frame is employed to guide the particles towards predicted pose of the object. Such a key-point based pose hypothesis is injected into the probability distribution that is recursively updated in a Bayesian framework. The 6D object pose tracker is evaluated on Nvidia Jetson AGX Xavier both on synthetic and real sequences of images acquired from a calibrated RGB camera.","PeriodicalId":226794,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126328698","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

LiteEdge: Lightweight Semantic Edge Detection Network 轻量级语义边缘检测网络

2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) Pub Date : 2021-10-01 DOI: 10.1109/ICCVW54120.2021.00300

Hao Wang, Hasan Al-Banna Mohamed, Zuowen Wang, Bodo Rueckauer, Shih-Chii Liu

引用次数: 1

A Semi-self-supervised Learning Approach for Wheat Head Detection using Extremely Small Number of Labeled Samples 基于极少量标记样本的小麦抽穗检测半自监督学习方法

2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) Pub Date : 2021-10-01 DOI: 10.1109/ICCVW54120.2021.00155

Keyhan Najafian, Ali Ghanbari, I. Stavness, Lingling Jin, G. Shirdel, Farhad Maleki

{"title":"A Semi-self-supervised Learning Approach for Wheat Head Detection using Extremely Small Number of Labeled Samples","authors":"Keyhan Najafian, Ali Ghanbari, I. Stavness, Lingling Jin, G. Shirdel, Farhad Maleki","doi":"10.1109/ICCVW54120.2021.00155","DOIUrl":"https://doi.org/10.1109/ICCVW54120.2021.00155","url":null,"abstract":"Most of the success of deep learning is owed to supervised learning, where a large-scale annotated dataset is used for model training. However, developing such datasets is challenging. In this paper, we develop a semi-self-supervised learning approach for wheat head detection. The proposed method utilized a few short video clips and only one annotated image from each video clip of wheat fields to simulate a large computationally annotated dataset used for model building. Considering the domain gap be-tween the simulated and real images, we applied two do-main adaptation steps to alleviate the challenge of distributional shift. The resulting model achieved high performance when applied to real unannotated datasets. When fine-tuned on the dataset from the Global Wheat Head Detection Challenge, the performance was further improved. The model achieved a mean average precision of 0.827, where an over-lap of 50% or more between a predicted bounding box and ground truth was considered as a correct prediction. Al-though the utility of the proposed methodology was shown by applying it to wheat head detection, the proposed method is not limited to this application and could be used for other domains, such as detecting different crop types, alleviating the barrier of lack of large-scale annotated datasets in those domains.","PeriodicalId":226794,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125747674","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 10

Improving Key Human Features for Pose Transfer 改进姿势转移的关键人体特征

2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) Pub Date : 2021-10-01 DOI: 10.1109/ICCVW54120.2021.00223

Victor-Andrei Ivan, Ionut Mistreanu, Andrei Leica, Sung-Jun Yoon, Manri Cheon, Junwoo Lee, Jinsoo Oh

引用次数: 2