今日CS.CV計算機視覺論文速覽
Fri, 25 Jan 2019
Totally 29 papers
?? 續:第二部分 ?
Interesting:
- U-nets and GAN補全被遮擋的人,基于被遮擋的輸入,通過神經網絡的處理和“想象”,生成出沒有遮擋、像素級的、并與原來保持相同視覺屬性的圖像。研究人員基于U-net和GAN以及特殊為去遮擋人體設定的結構進行實作。(from 意大利 摩德納雷焦艾米莉亞大學)
資料集:
occluded RAP<—RAP:A Richly Annotated Dataset for Pedestrian Attribute Recognition,
AiC Attributes in Crowd
- 利用深度面部圖生成RGB彩色臉, 通過神經網絡重建出來合理的面部圖像可以用于多種模式識别問題,生成不同環境(shadows, light variations or darkness)下的人臉資料集。(from 意大利 摩德納雷焦艾米莉亞大學) 從深度圖生成RGB圖的過程: 原圖和生成圖,雖然不一緻,但生成的面部圖像時合理的有效的。
資料集:MotorMark from paper from AImageLab
tip:facelandmark 5point dataset
- 點雲空間相關性預測,基于神經網絡通過原始點雲資料預測兩個部分點雲的空間相關性,并從中學到了點雲的語義特征表示。(from HPI 哈索·普拉特納學院 德國) 模型的架構如下圖所示: 相關方法: 資料集:ModelNet
-
基于自注意力機制的無監督圖像遷移,其任務在給定非配對資料下學習從一個域到另一個域的轉換。但目前方法沒強調域間幾何和結構的變化。
自注意力機制(Han Zhang, 2018):
本文的方法:資料集:
cat2dog: This datasets are used in DRIT. (Hsin-Ying Lee,2018) This dataset contains cat(871) and dog(1,364).
img2dog: This dataset contains faces(CelebA dataset,202,599) and dog(cat2dog dataset, 1,364).
img2cat: This dataset contains faces(CelebA dataset,202,599) and cat(cat2dog dataset, 871).
portrait: This datasets are used in DRIT. (Hsin-Ying Lee,2018) This dataset contains portrait(1,814) and face photo(6,452).
edge2shoes: This dataset are used in MUNIT. (Huang et al., 2018) This dataset contains edges(50,025) and shoes(50,025).
相關方法:unsupervised image-to-image translation models(CycleGAN (Zhu et al., 2017), DRIT (HsinYing Lee, 2018), UNIT (Liu et al., 2017), MUNIT (Huang et al., 2018)。
-
半監督Img2Img遷移,(from D. J. Sanghvi工程學院印度)
通過條件機率的方法使得遷移與所有局域、全局和内容特征獨立。
code:http://github.com/ozamanan/semisit
ref:Img2img PAPER collection
Daily Computer Vision Papers
[1] *Title: Learning Disentangled Representations with Reference-Based Variational Autoencoders
Authors:Adria Ruiz, Oriol Martinez, Xavier Binefa, Jakob Verbeek
[2] Title: CT synthesis from MR images for orthopedic applications in the lower arm using a conditional generative adversarial network
Authors:Frank Zijlstra, Koen Willemsen, Mateusz C. Florkow, Ralph J.B. Sakkers, Harrie H. Weinans, Bart C.H. van der Wal, Marijn van Stralen, Peter R. Seevinck
[3] Title: Application of Decision Rules for Handling Class Imbalance in Semantic Segmentation
Authors:Robin Chan, Matthias Rottmann, Fabian Hüger, Peter Schlicht, Hanno Gottschalk
[4] *Title: Using CycleGANs for effectively reducing image variability across OCT devices and improving retinal fluid segmentation
Authors:Philipp Seeböck, David Romo-Bucheli, Sebastian Waldstein, Hrvoje Bogunović, José Ignacio Orlando, Bianca S. Gerendas, Georg Langs, Ursula Schmidt-Erfurth
[5] *Title: 3D Backbone Network for 3D Object Detection
Authors:Xuesong Li, Jose E Guivant, Ngaiming Kwok, Yongzhi Xu
[6] *Title: Deep Reasoning with Multi-scale Context for Salient Object Detection
Authors:Zun Li, Congyan Lang, Yunpeng Chen, Junhao Liew, Jiashi Feng
[7] Title: Semantic Matching by Weakly Supervised 2D Point Set Registration
Authors:Zakaria Laskar, Hamed R. Tavakoli, Juho Kannala
[8] *Title: Semi-Supervised Semantic Matching
Authors:Zakaria Laskar, Juho Kannala
[9] Title: Whole slide image registration for the study of tumor heterogeneity
Authors:Leslie Solorzano, Gabriela M. Almeida, Bárbara Mesquita, Diana Martins, Carla Oliveira, Carolina Wählby
[10] *Title: Anomaly Detection in Road Traffic Using Visual Surveillance: A Survey
Authors:Santhosh Kelathodi Kumaran, Debi Prosad Dogra, Partha Pratim Roy
[11] *Title: A Novel Self-Intersection Penalty Term for Statistical Body Shape Models and Its Applications in 3D Pose Estimation
Authors:Zaiqiang Wu, Wei Jiang, Hao Luo, Lin Cheng
[12] *Title: Unsupervised Image-to-Image Translation with Self-Attention Networks
Authors:Taewon Kang, Kwang Hee Lee
[13] *Title: Visualizing Topographic Independent Component Analysis with Movies
Authors:Zhimin Chen, Darius Parvin, Maedbh King, Susan Hao
[14] Title: Reciprocal Translation between SAR and Optical Remote Sensing Images with Cascaded-Residual Adversarial Networks
Authors:Shilei Fu, Feng Xu, Ya-Qiu Jin
[15] *Title: Object Detection based on Region Decomposition and Assembly
Authors:Seung-Hwan Bae
[16] *Title: MREAK : Morphological Retina Keypoint Descriptor
Authors:Himanshu Vaghela, Manan Oza, Sudhir Bagul
[17] *Title: Semi-Supervised Image-to-Image Translation
Authors:Manan Oza, Himanshu Vaghela, Sudhir Bagul
[18] Title: Synergistic Image and Feature Adaptation: Towards Cross-Modality Domain Adaptation for Medical Image Segmentation
Authors:Cheng Chen, Qi Dou, Hao Chen, Jing Qin, Pheng-Ann Heng
[19] *Title: A PCB Dataset for Defects Detection and Classification
Authors:Weibo Huang, Peng Wei
[20] Title: Correcting rural building annotations in OpenStreetMap using convolutional neural networks
Authors:John E. Vargas-Muñoz, Sylvain Lobry, Alexandre X. Falcão, Devis Tuia
[21] Title: Siamese Networks with Location Prior for Landmark Tracking in Liver Ultrasound Sequences
Authors:Alvaro Gomariz, Weiye Li, Ece Ozkan, Christine Tanner, Orcun Goksel
[22] *Title: Domain Translation with Conditional GANs: from Depth to RGB Face-to-Face
Authors:Matteo Fabbri, Guido Borghi, Fabio Lanzi, Roberto Vezzani, Simone Calderara, Rita Cucchiara
[23] *Title: Can Adversarial Networks Hallucinate Occluded People With a Plausible Aspect?
Authors:Federico Fulgeri, Matteo Fabbri, Stefano Alletto, Simone Calderara, Rita Cucchiara
[24] Title: Never Forget: Balancing Exploration and Exploitation via Learning Optical Flow
Authors:Hsuan-Kung Yang, Po-Han Chiang, Kuan-Wei Ho, Min-Fong Hong, Chun-Yi Lee
[25] *Title: Spherical sampling methods for the calculation of metamer mismatch volumes
Authors:Michal Mackiewicz, Hans Jakob Rivertz, Graham D. Finlayson
[26] *Title: Context Prediction for Unsupervised Deep Learning on Point Clouds
Authors:Jonathan Sauder, Bjarne Sievers
[27] Title: Deep Learning on Attributed Graphs: A Journey from Graphs to Their Embeddings and Back
Authors:Martin Simonovsky
[28] Title: Trajectory Normalized Gradients for Distributed Optimization
Authors:Jianqiao Wangni, Ke Li, Jianbo Shi, Jitendra Malik
[29] *Title: Hypergraph Convolution and Hypergraph Attention
Authors:Song Bai, Feihu Zhang, Philip H.S. Torr
Papers from arxiv.org
更多精彩請移步首頁
pic from pixels.com