2021 IEEE Winter Conference on Applications of Computer Vision (WACV)最新文献_第3页

Part Segmentation of Unseen Objects using Keypoint Guidance 基于关键点制导的未见物体部分分割

2021 IEEE Winter Conference on Applications of Computer Vision (WACV) Pub Date : 2021-01-01 DOI: 10.1109/WACV48630.2021.00178

Shujon Naha, Qingyang Xiao, Prianka Banik, Md Alimoor Reza, David J. Crandall

{"title":"Part Segmentation of Unseen Objects using Keypoint Guidance","authors":"Shujon Naha, Qingyang Xiao, Prianka Banik, Md Alimoor Reza, David J. Crandall","doi":"10.1109/WACV48630.2021.00178","DOIUrl":"https://doi.org/10.1109/WACV48630.2021.00178","url":null,"abstract":"While object part segmentation is useful for many applications, typical approaches require a large amount of labeled data to train a model for good performance. To reduce the labeling effort, weak supervision cues such as object keypoints have been used to generate pseudo-part annotations which can subsequently be used to train larger models. However, previous weakly-supervised part segmentation methods require the same object classes during both training and testing. We propose a new model to use key-point guidance for segmenting parts of novel object classes given that they have similar structures as seen objects — different types of four-legged animals, for example. We show that a non-parametric template matching approach is more effective than pixel classification for part segmentation, especially for small or less frequent parts. To evaluate the generalizability of our approach, we introduce two new datasets that contain 200 quadrupeds in total with both key-point and part segmentation annotations. We show that our approach can outperform existing models by a large margin on the novel object part segmentation task using limited part segmentation labels during training.","PeriodicalId":236300,"journal":{"name":"2021 IEEE Winter Conference on Applications of Computer Vision (WACV)","volume":"126 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127408265","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: 4

Learning of low-level feature keypoints for accurate and robust detection 学习低级特征关键点，实现准确和鲁棒的检测

2021 IEEE Winter Conference on Applications of Computer Vision (WACV) Pub Date : 2021-01-01 DOI: 10.1109/WACV48630.2021.00231

Suwichaya Suwanwimolkul, S. Komorita, K. Tasaka

引用次数: 13

SinGAN-GIF: Learning a Generative Video Model from a Single GIF SinGAN-GIF:从单个GIF中学习生成视频模型

2021 IEEE Winter Conference on Applications of Computer Vision (WACV) Pub Date : 2021-01-01 DOI: 10.1109/WACV48630.2021.00135

Rajat Arora, Yong Jae Lee

引用次数: 12

DANCE : A Deep Attentive Contour Model for Efficient Instance Segmentation DANCE:一种用于高效实例分割的深度关注轮廓模型

2021 IEEE Winter Conference on Applications of Computer Vision (WACV) Pub Date : 2021-01-01 DOI: 10.1109/WACV48630.2021.00039

Zichen Liu, J. Liew, Xiangyu Chen, Jiashi Feng

{"title":"DANCE : A Deep Attentive Contour Model for Efficient Instance Segmentation","authors":"Zichen Liu, J. Liew, Xiangyu Chen, Jiashi Feng","doi":"10.1109/WACV48630.2021.00039","DOIUrl":"https://doi.org/10.1109/WACV48630.2021.00039","url":null,"abstract":"Contour-based instance segmentation methods are attractive due to their efficiency. However, existing contour-based methods either suffer from lossy representation, complex pipeline or difficulty in model training, resulting in sub-par mask accuracy on challenging datasets like MS-COCO. In this work, we propose a novel deep attentive contour model, named DANCE, to achieve better instance segmentation accuracy while remaining good efficiency. To this end, DANCE applies two new designs: attentive contour deformation to refine the quality of segmentation contours and segment-wise matching to ease the model training. Comprehensive experiments demonstrate DANCE excels at deforming the initial contour in a more natural and efficient way towards the real object boundaries. Effectiveness of DANCE is also validated on the COCO dataset, which achieves 38.1% mAP and outperforms all other contour-based instance segmentation models. To the best of our knowledge, DANCE is the first contour-based model that achieves comparable performance to pixel-wise segmentation models. Code is available at https://github.com/lkevinzc/dance.","PeriodicalId":236300,"journal":{"name":"2021 IEEE Winter Conference on Applications of Computer Vision (WACV)","volume":"505 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123585676","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: 31

Efficient Attention: Attention with Linear Complexities 有效注意力:具有线性复杂性的注意力

2021 IEEE Winter Conference on Applications of Computer Vision (WACV) Pub Date : 2021-01-01 DOI: 10.1109/WACV48630.2021.00357

Shen Zhuoran, Zhang Mingyuan, Zhao Haiyu, Yifan Shuai, Li Hongsheng

{"title":"Efficient Attention: Attention with Linear Complexities","authors":"Shen Zhuoran, Zhang Mingyuan, Zhao Haiyu, Yifan Shuai, Li Hongsheng","doi":"10.1109/WACV48630.2021.00357","DOIUrl":"https://doi.org/10.1109/WACV48630.2021.00357","url":null,"abstract":"Dot-product attention has wide applications in computer vision and natural language processing. However, its memory and computational costs grow quadratically with the input size. Such growth prohibits its application on high- resolution inputs. To remedy this drawback, this paper proposes a novel efficient attention mechanism equivalent to dot-product attention but with substantially less memory and computational costs. Its resource efficiency allows more widespread and flexible integration of attention modules into a network, which leads to better accuracies. Empirical evaluations demonstrated the effectiveness of its advantages. Efficient attention modules brought significant performance boosts to object detectors and instance segmenters on MS-COCO 2017. Further, the resource efficiency democratizes attention to complex models, where high costs prohibit the use of dot-product attention. As an exemplar, a model with efficient attention achieved state-of- the-art accuracies for stereo depth estimation on the Scene Flow dataset. Code is available at https://github.com/cmsflash/efficient-attention.","PeriodicalId":236300,"journal":{"name":"2021 IEEE Winter Conference on Applications of Computer Vision (WACV)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123611853","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: 2

SChISM: Semantic Clustering via Image Sequence Merging for Images of Human-Decomposition SChISM:基于图像序列合并的人类分解图像语义聚类

2021 IEEE Winter Conference on Applications of Computer Vision (WACV) Pub Date : 2021-01-01 DOI: 10.1109/WACV48630.2021.00224

Sara Mousavi, Dylan Lee, Tatianna Griffin, Kelley Cross, D. Steadman, A. Mockus

引用次数: 2

Subject Guided Eye Image Synthesis with Application to Gaze Redirection 对象引导眼图像合成及其在注视重定向中的应用

2021 IEEE Winter Conference on Applications of Computer Vision (WACV) Pub Date : 2021-01-01 DOI: 10.1109/WACV48630.2021.00006

Harsimran Kaur, R. Manduchi

{"title":"Subject Guided Eye Image Synthesis with Application to Gaze Redirection","authors":"Harsimran Kaur, R. Manduchi","doi":"10.1109/WACV48630.2021.00006","DOIUrl":"https://doi.org/10.1109/WACV48630.2021.00006","url":null,"abstract":"We propose a method for synthesizing eye images from segmentation masks with a desired style. The style encompasses attributes such as skin color, texture, iris color, and personal identity. Our approach generates an eye image that is consistent with a given segmentation mask and has the attributes of the input style image. We apply our method to data augmentation as well as to gaze redirection. The previous techniques of synthesizing real eye images from synthetic eye images for data augmentation lacked control over the generated attributes. We demonstrate the effectiveness of the proposed method in synthesizing realistic eye images with given characteristics corresponding to the synthetic labels for data augmentation, which is further useful for various tasks such as gaze estimation, eye image segmentation, pupil detection, etc. We also show how our approach can be applied to gaze redirection using only synthetic gaze labels, improving the previous state of the art results. The main contributions of our paper are i) a novel approach for Style-Based eye image generation from segmentation mask; ii) the use of this approach for gaze-redirection without the need for gaze annotated real eye images","PeriodicalId":236300,"journal":{"name":"2021 IEEE Winter Conference on Applications of Computer Vision (WACV)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129710015","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: 8

Can Selfless Learning improve accuracy of a single classification task? 无私学习能提高单个分类任务的准确性吗?

2021 IEEE Winter Conference on Applications of Computer Vision (WACV) Pub Date : 2021-01-01 DOI: 10.1109/WACV48630.2021.00409

Soumya Roy, Bharat Bhusan Sau

引用次数: 0

CAT-Net: Compression Artifact Tracing Network for Detection and Localization of Image Splicing CAT-Net:用于图像拼接检测和定位的压缩伪影跟踪网络

2021 IEEE Winter Conference on Applications of Computer Vision (WACV) Pub Date : 2021-01-01 DOI: 10.1109/WACV48630.2021.00042

Myung-Joon Kwon, In-Jae Yu, Seung-Hun Nam, Heung-Kyu Lee

引用次数: 40

Shape from semantic segmentation via the geometric Rényi divergence 形状从语义分割通过几何rsamnyi发散

2021 IEEE Winter Conference on Applications of Computer Vision (WACV) Pub Date : 2021-01-01 DOI: 10.1109/WACV48630.2021.00236

T. Koizumi, W. Smith

引用次数: 1