出品 | 深度學習這件小事公眾號
[1] GreedyFool: Distortion-Aware Sparse Adversarial Attack作者 | Xiaoyi Dong, Dongdong Chen, Jianmin Bao, Chuan Qin, Lu Yuan, Weiming Zhang, Nenghai Yu, Dong Chen連結 | https://arxiv.org/abs/2010.13773 項目連結 | https://github.com/LightDXY/GreedyFool備註 | To appear in NeurIPS 2020[2] GAN Mask R-CNN:Instance semantic segmentation benefits from generativeadversarial networks作者 | Quang H. Le, Kamal Youcef-Toumi, Dzmitry Tsetserukou, Ali Jahanian連結 | https://arxiv.org/abs/2010.13757 [3] Handgun detection using combined human pose and weapon appearance作者 | Jesus Ruiz-Santaquiteria, Alberto Velasco-Mata, Noelia Vallez, Gloria Bueno, Juan Antonio Alvarez, Oscar Deniz連結 | https://arxiv.org/abs/2010.13753 備註 | 26 pages, 17 figures[4] Demo Abstract: Indoor Positioning System in Visually-Degraded Environments with Millimetre-Wave Radar and Inertial Sensors作者 | Zhuangzhuang Dai, Muhamad Risqi U. Saputra, Chris Xiaoxuan Lu, Niki Trigoni, Andrew Markham連結 | https://arxiv.org/abs/2010.13750 備註 | Appear as demo abstract at the ACM Conference on Embedded Networked Sensor Systems (SenSys 2020)[5] ActiveNet: A computer-vision based approach to determine lethargy作者 | Aitik Gupta, Aadit Agarwal連結 | https://arxiv.org/abs/2010.13714 備註 | Accepted at The ACM India Joint International Conference on Data Science and Management of Data (CoDS-COMAD) 2021[6] Distributed Multi-Target Tracking in Camera Networks作者 | Sara Casao, Ana C. Murillo, Eduardo Montijano連結 | https://arxiv.org/abs/2010.13701 [7] Face Frontalization Based on Robustly Fitting a Deformable Shape Model to 3D Landmarks作者 | Zhiqi Kang, Mostafa Sadeghi, Radu Horaud連結 | https://arxiv.org/abs/2010.13676 備註 | Submitted to IEEE Transactions on Multimedia[8] SCFusion: Real-time Incremental Scene Reconstruction with Semantic Completion作者 | Shun-Cheng Wu, Keisuke Tateno, Nassir Navab, Federico Tombari連結 | https://arxiv.org/abs/2010.13662 備註 | Accepted in International Conference on 3D Vision 2020[9] Fewer is More: A Deep Graph Metric Learning Perspective Using Fewer Proxies作者 | Yuehua Zhu, Muli Yang, Cheng Deng, Wei Liu連結 | https://arxiv.org/abs/2010.13636 項目連結 | https://github.com/YuehuaZhu/ProxyGML備註 | Accepted in NeurIPS 2020 as a spotlight paper. [10] Classification of Important Segments in Educational Videos using Multimodal Features作者 | Junaid Ahmed Ghauri, Sherzod Hakimov, Ralph Ewerth連結 | https://arxiv.org/abs/2010.13626 備註 | Proceedings of the CIKM 2020 Workshops, October 19 to 20, Galway, Ireland[11] SHARP 2020: The 1st Shape Recovery from Partial Textured 3D Scans Challenge Results作者 | Alexandre Saint, Anis Kacem, Kseniya Cherenkova, Konstantinos Papadopoulos, Julian Chibane, Gerard Pons-Moll, Gleb Gusev, David Fofi, Djamila Aouada, Bjorn Ottersten連結 | https://arxiv.org/abs/2010.13508 備註 | SHARP workshop, ECCV 2020[12] Hierarchical Neural Architecture Search for Deep Stereo Matching作者 | Xuelian Cheng, Yiran Zhong, Mehrtash Harandi, Yuchao Dai, Xiaojun Chang, Tom Drummond, Hongdong Li, Zongyuan Ge連結 | https://arxiv.org/abs/2010.13501 備註 | Accepted at NeurIPS 2020; Xuelian Cheng and Yiran Zhong made equal contribution[13] Activation Map Adaptation for Effective Knowledge Distillation作者 | Zhiyuan Wu, Hong Qi, Yu Jiang, Minghao Zhao, Chupeng Cui, Zongmin Yang, Xinhui Xue連結 | https://arxiv.org/abs/2010.13500 [14] A Centroid Loss for Weakly Supervised Semantic Segmentation in Quality Control and Inspection Application作者 | Kai Yao, Alberto Ortiz, Francisco Bonnin-Pascual連結 | https://arxiv.org/abs/2010.13433 [15] Multi-object tracking with self-supervised associating network作者 | Tae-young Chung, Heansung Lee, Myeong Ah Cho, Suhwan Cho, Sangyoun Lee連結 | https://arxiv.org/abs/2010.13424 [16] Lane detection in complex scenes based on end-to-end neural network作者 | Wenbo Liu, Fei Yan, Kuan Tang, Jiyong Zhang, Tao Deng連結 | https://arxiv.org/abs/2010.13422 備註 | Accepted by 2020 China Automation Congress (CAC)[17] Residual Recurrent CRNN for End-to-End Optical Music Recognition on Monophonic Scores作者 | Aozhi Liu, Lipei Zhang, Yaqi Mei, Sitong Lian, Maokun Han, Wen Cheng, Yuyu Liu, Zifeng Cai, Zhaohua Zhu, Baoqiang Han, Jing Xiao連結 | https://arxiv.org/abs/2010.13418 備註 | 5 pages, 4 figures, 1 table[18] Flexible Piecewise Curves Estimation for Photo Enhancement作者 | Chongyi Li, Chunle Guo, Qiming Ai, Shangchen Zhou, Chen Change Loy連結 | https://arxiv.org/abs/2010.13412 [19] Video-based Facial Expression Recognition using Graph Convolutional Networks作者 | Daizong Liu, Hongting Zhang, Pan Zhou連結 | https://arxiv.org/abs/2010.13386 備註 | Accepted by ICPR2020[20] Where to Look and How to Describe: Fashion Image Retrieval with an Attentional Heterogeneous Bilinear Network作者 | Haibo Su, Peng Wang, Lingqiao Liu, Hui Li, Zhen Li, Yanning Zhang連結 | https://arxiv.org/abs/2010.13357 [21] PSF-LO: Parameterized Semantic Features Based Lidar Odometry作者 | Guibin Chen, BoSheng Wang, XiaoLiang Wang, Huanjun Deng, Bing Wang, Shuo Zhang連結 | https://arxiv.org/abs/2010.13355 [22] Semi supervised segmentation and graph-based tracking of 3D nuclei in time-lapse microscopy作者 | S. Shailja, Jiaxiang Jiang, B.S. Manjunath連結 | https://arxiv.org/abs/2010.13343 備註 | To be submitted to ISBI 2021[23] EDNet: Improved DispNet for Efficient Disparity Estimation作者 | Songyan Zhang, Zhicheng Wang連結 | https://arxiv.org/abs/2010.13338 [24] Robust Pre-Training by Adversarial Contrastive Learning作者 | Ziyu Jiang, Tianlong Chen, Ting Chen, Zhangyang Wang連結 | https://arxiv.org/abs/2010.13337 [25] View-Invariant, Occlusion-Robust Probabilistic Embedding for Human Pose作者 | Ting Liu, Jennifer J. Sun, Long Zhao, Jiaping Zhao, Liangzhe Yuan, Yuxiao Wang, Liang-Chieh Chen, Florian Schroff, Hartwig Adam連結 | https://arxiv.org/abs/2010.13321 項目連結 | https://github.com/google-research/google-research/tree/master/poem[26] Zero-Shot Learning from scratch (ZFS): leveraging local compositional representations作者 | Tristan Sylvain, Linda Petrini, R Devon Hjelm連結 | https://arxiv.org/abs/2010.13320 備註 | ICML 2019 Workshop on Understanding and Improving General-ization in Deep Learning, Long Beach, California, 2019 Spotlight presentation. arXiv admin note: text overlap with arXiv:1912.12179[27] Structural Prior Driven Regularized Deep Learning for Sonar Image Classification作者 | Isaac D. Gerg, Vishal Monga連結 | https://arxiv.org/abs/2010.13317 備註 | To appear in TGRS, 2021[28] AdaFuse: Adaptive Multiview Fusion for Accurate Human Pose Estimation in the Wild作者 | Zhe Zhang, Chunyu Wang, Weichao Qiu, Wenhu Qin, Wenjun Zeng連結 | https://arxiv.org/abs/2010.13302 [29] Global Image Segmentation Process using Machine Learning algorithm & Convolution Neural Network method for Self- Driving Vehicles作者 | Tirumalapudi Raviteja, Rajay Vedaraj .I.S連結 | https://arxiv.org/abs/2010.13294 [30] Attack Agnostic Adversarial Defense via Visual Imperceptible Bound作者 | Saheb Chhabra, Akshay Agarwal, Richa Singh, Mayank Vatsa連結 | https://arxiv.org/abs/2010.13247 [31] MixNet for Generalized Face Presentation Attack Detection作者 | Nilay Sanghvi, Sushant Kumar Singh, Akshay Agarwal, Mayank Vatsa, Richa Singh連結 | https://arxiv.org/abs/2010.13246 [32] Generalized Iris Presentation Attack Detection Algorithm under Cross-Database Settings作者 | Mehak Gupta, Vishal Singh, Akshay Agarwal, Mayank Vatsa, Richa Singh連結 | https://arxiv.org/abs/2010.13244 [33] Human or Machine? It Is Not What You Write, But How You Write It作者 | Luis A. Leiva, Moises Diaz, Miguel A. Ferrer, Réjean Plamondon連結 | https://arxiv.org/abs/2010.13231 備註 | Proceedings of the 25th Intl. Conf. on Pattern Recognition (ICPR), 2020[34] Weakly-Supervised Amodal Instance Segmentation with Compositional Priors作者 | Yihong Sun, Adam Kortylewski, Alan Yuille連結 | https://arxiv.org/abs/2010.13175 [35] Neuron Merging: Compensating for Pruned Neurons作者 | Woojeong Kim, Suhyun Kim, Mincheol Park, Geonseok Jeon連結 | https://arxiv.org/abs/2010.13160 [36] Correspondence Learning via Linearly-invariant Embedding作者 | Riccardo Marin, Marie-Julie Rakotosaona, Simone Melzi, Maks Ovsjanikov連結 | https://arxiv.org/abs/2010.13136 [37] Monocular Depth Estimation via Listwise Ranking using the Plackett-Luce model作者 | Julian Lienen, Eyke Hüllermeier連結 | https://arxiv.org/abs/2010.13118 備註 | 9 pages of content, 11 pages in total, 1 figure, 5 tables[38] Empowering Knowledge Distillation via Open Set Recognition for Robust 3D Point Cloud Classification作者 | Ayush Bhardwaj, Sakshee Pimpale, Saurabh Kumar, Biplab Banerjee連結 | https://arxiv.org/abs/2010.13114 備註 | Preprint. Under consideration at Pattern Recognition Letters[39] Scribble-based Weakly Supervised Deep Learning for Road Surface Extraction from Remote Sensing Images作者 | Yao Wei, Shunping Ji連結 | https://arxiv.org/abs/2010.13106 備註 | 12 pages, 8 figures, submitted to IEEE Transactions on Geoscience and Remote Sensing[40] Coherent Loss: A Generic Framework for Stable Video Segmentation作者 | Mingyang Qian, Yi Fu, Xiao Tan, Yingying Li, Jinqing Qi, Huchuan Lu, Shilei Wen, Errui Ding連結 | https://arxiv.org/abs/2010.13085 [41] Fast and Accurate Light Field Saliency Detection through Feature Extraction作者 | Sahan Hemachandra, Ranga Rodrigo, Chamira Edussooriya連結 | https://arxiv.org/abs/2010.13073 [42] Applying convolutional neural networks to extremely sparse image datasets using an image subdivision approach連結 | https://arxiv.org/abs/2010.13054 [43] CLRGaze: Contrastive Learning of Representations for Eye Movement Signals作者 | Louise Gillian C. Bautista, Prospero C. Naval Jr連結 | https://arxiv.org/abs/2010.13046 [44] APB2FaceV2: Real-Time Audio-Guided Multi-Face Reenactment作者 | Jiangning Zhang, Xianfang Zeng, Chao Xu, Jun Chen, Yong Liu, Yunliang Jiang連結 | https://arxiv.org/abs/2010.13017 [45] Classification of Spot-welded Joints in Laser Thermography Data using Convolutional Neural Networks作者 | Linh Kästner, Samim Ahmadi, Florian Jonietz, Mathias Ziegler, Peter Jung, Giuseppe Caire, Jens Lambrecht連結 | https://arxiv.org/abs/2010.12976 [46] Deep Denoising For Scientific Discovery: A Case Study In Electron Microscopy作者 | Sreyas Mohan, Ramon Manzorro, Joshua L. Vincent, Binh Tang, Dev Yashpal Sheth, Eero P. Simoncelli, David S. Matteson, Peter A. Crozier, Carlos Fernandez-Granda連結 | https://arxiv.org/abs/2010.12970 項目連結 | https://sreyas-mohan.github.io/electron-microscopy-denoising/[47] Video Understanding based on Human Action and Group Activity Recognition作者 | Zijian Kuang, Xinran Tie連結 | https://arxiv.org/abs/2010.12968 [48] Advancing Non-Contact Vital Sign Measurement using Synthetic Avatars作者 | Daniel McDuff, Javier Hernandez, Erroll Wood, Xin Liu, Tadas Baltrusaitis連結 | https://arxiv.org/abs/2010.12949 [49] RUArt: A Novel Text-Centered Solution for Text-Based Visual Question Answering作者 | Zan-Xia Jin, Heran Wu, Chun Yang, Fang Zhou, Jingyan Qin, Lei Xiao, Xu-Cheng Yin連結 | https://arxiv.org/abs/2010.12917 [50] Classifying Eye-Tracking Data Using Saliency Maps作者 | Shafin Rahman, Sejuti Rahman, Omar Shahid, Md. Tahmeed Abdullah, Jubair Ahmed Sourov連結 | https://arxiv.org/abs/2010.12913 備註 | Accepted in: International Conference on Pattern Recognition (ICPR)[51] Discriminative feature generation for classification of imbalanced data作者 | Sungho Suh, Paul Lukowicz, Yong Oh Lee連結 | https://arxiv.org/abs/2010.12888 備註 | Submitted to Pattern Recognition, Elsevier[52] Persian Handwritten Digit, Character, and Words Recognition by Using Deep Learning Methods作者 | Mehdi Bonyani, Simindokht Jahangard連結 | https://arxiv.org/abs/2010.12880 [53] Beyond VQA: Generating Multi-word Answer and Rationale to Visual Questions作者 | Radhika Dua, Sai Srinivas Kancheti, Vineeth N Balasubramanian連結 | https://arxiv.org/abs/2010.12852 [54] REDE: End-to-end Object 6D Pose Robust Estimation Using Differentiable Outliers Elimination作者 | Weitong Hua, Zhongxiang Zhou, Jun Wu, Yue Wang, Rong Xiong連結 | https://arxiv.org/abs/2010.12807 [55] Improving the generalization of network based relative pose regression: dimension reduction as a regularizer作者 | Xiaqing Ding, Yue Wang, Li Tang, Yanmei Jiao, Rong Xiong連結 | https://arxiv.org/abs/2010.12796 [56] Real-time Non-line-of-Sight imaging of dynamic scenes作者 | Ji Hyun Nam, Eric Brandt, Sebastian Bauer, Xiaochun Liu, Eftychios Sifakis, Andreas Velten連結 | https://arxiv.org/abs/2010.12737 [57] Investigating Saturation Effects in Integrated Gradients作者 | Vivek Miglani, Narine Kokhlikyan, Bilal Alsallakh, Miguel Martin, Orion Reblitz-Richardson連結 | https://arxiv.org/abs/2010.12697 備註 | Presented at ICML Workshop on Human Interpretability in Machine Learning (WHI 2020)[58] Unsupervised Dense Shape Correspondence using Heat Kernels作者 | Mehmet Aygün, Zorah Lähner, Daniel Cremers連結 | https://arxiv.org/abs/2010.12682 備註 | In International Conference on 3D Vision (3DV), 2020[59] 3DBooSTeR: 3D Body Shape and Texture Recovery作者 | Alexandre Saint, Anis Kacem, Kseniya Cherenkova, Djamila Aouada連結 | https://arxiv.org/abs/2010.12670 備註 | SHARP Workshop, European Conference on Computer Vision (ECCV), 2020[60] Position and Rotation Invariant Sign Language Recognition from 3D Point Cloud Data with Recurrent Neural Networks作者 | Prasun Roy, Saumik Bhattacharya, Partha Pratim Roy, Umapada Pal連結 | https://arxiv.org/abs/2010.12669 [61] Attention-Guided Network for Iris Presentation Attack Detection作者 | Cunjian Chen, Arun Ross連結 | https://arxiv.org/abs/2010.12631 [62] Exemplary Natural Images Explain CNN Activations Better than Feature Visualizations作者 | Judy Borowski, Roland S. Zimmermann, Judith Schepers, Robert Geirhos, Thomas S. A. Wallis, Matthias Bethge, Wieland Brendel連結 | https://arxiv.org/abs/2010.12606 [63] ST-GREED: Space-Time Generalized Entropic Differences for Frame Rate Dependent Video Quality Prediction作者 | Pavan C. Madhusudana, Neil Birkbeck, Yilin Wang, Balu Adsumilli, Alan C. Bovik連結 | https://arxiv.org/abs/2010.13715 [64] Deep Low-rank plus Sparse Network for Dynamic MR Imaging作者 | Wenqi Huang, Ziwen Ke, Zhuo-Xu Cui, Jing Cheng, Zhilang Qiu, Sen Jia, Yanjie Zhu, Dong Liang連結 | https://arxiv.org/abs/2010.13677 [65] A ReLU Dense Layer to Improve the Performance of Neural Networks作者 | Alireza M. Javid, Sandipan Das, Mikael Skoglund, Saikat Chatterjee連結 | https://arxiv.org/abs/2010.13572 備註 | Submitted to ICASSP 2021[66] Towards Scale-Invariant Graph-related Problem Solving by Iterative Homogeneous Graph Neural Networks作者 | Hao Tang, Zhiao Huang, Jiayuan Gu, Bao-Liang Lu, Hao Su連結 | https://arxiv.org/abs/2010.13547 備註 | To appear at NeurIPS 2020[67] Robust Disentanglement of a Few Factors at a Time作者 | Benjamin Estermann, Markus Marks, Mehmet Fatih Yanik連結 | https://arxiv.org/abs/2010.13527 項目連結 | https://github.com/besterma/robust_disentanglement備註 | The first two authors contributed equally. [68] Optimization for Medical Image Segmentation: Theory and Practice when evaluating with Dice Score or Jaccard Index作者 | Tom Eelbode, Jeroen Bertels, Maxim Berman, Dirk Vandermeulen, Frederik Maes, Raf Bisschops, Matthew B. Blaschko連結 | https://arxiv.org/abs/2010.13499 備註 | 15 pages, 14 figures, accepted for publication in IEEE Transactions on Medical Imaging (2020)[69] VoteNet++: Registration Refinement for Multi-Atlas Segmentation作者 | Zhipeng Ding, Marc Niethammer連結 | https://arxiv.org/abs/2010.13484 [70] Does contextual information improve 3D U-Net based brain tumor segmentation?作者 | Iulian Emil Tampu, Neda Haj-Hosseini, Anders Eklund連結 | https://arxiv.org/abs/2010.13460 [71] Matthews Correlation Coefficient Loss for Deep Convolutional Networks: Application to Skin Lesion Segmentation作者 | Kumar Abhishek, Ghassan Hamarneh連結 | https://arxiv.org/abs/2010.13454 [72] On Embodied Visual Navigation in Real Environments Through Habitat作者 | Marco Rosano, Antonino Furnari, Luigi Gulino, Giovanni Maria Farinella連結 | https://arxiv.org/abs/2010.13439 備註 | Published in International Conference on Pattern Recognition (ICPR), 2020[73] What is the best data augmentation approach for brain tumor segmentation using 3D U-Net?作者 | Marco Domenico Cirillo, David Abramian, Anders Eklund連結 | https://arxiv.org/abs/2010.13372 [74] Robustness May Be at Odds with Fairness: An Empirical Study on Class-wise Accuracy作者 | Philipp Benz, Chaoning Zhang, Adil Karjauv, In So Kweon連結 | https://arxiv.org/abs/2010.13365 [75] Deep Sequential Learning for Cervical Spine Fracture Detection on Computed Tomography Imaging作者 | Hojjat Salehinejad, Edward Ho, Hui-Ming Lin, Priscila Crivellaro, Oleksandra Samorodova, Monica Tafur Arciniegas, Zamir Merali, Suradech Suthiphosuwan, Aditya Bharatha, Kristen Yeom, Muhammad Mamdani, Jefferson Wilson, Errol Colak連結 | https://arxiv.org/abs/2010.13336 [76] A Dark and Bright Channel Prior Guided Deep Network for Retinal Image Quality Assessment作者 | Ziwen Xu, Beiji Zou, Qing Liu連結 | https://arxiv.org/abs/2010.13313 [77] Geometrically Matched Multi-source Microscopic Image Synthesis Using Bidirectional Adversarial Networks作者 | Jun Zhuang, Dali Wang連結 | https://arxiv.org/abs/2010.13308 備註 | Preprint. Under review[78] Interpreting Uncertainty in Model Predictions For COVID-19 Diagnosis作者 | Gayathiri Murugamoorthy, Naimul Khan連結 | https://arxiv.org/abs/2010.13271 備註 | Submitted to ISBI 2021[79] Co-embedding of Nodes and Edges with Graph Neural Networks作者 | Xiaodong Jiang, Ronghang Zhu, Pengsheng Ji, Sheng Li連結 | https://arxiv.org/abs/2010.13242 備註 | This manuscript has been accepted by the IEEE Transactions on Pattern Analysis and Machine Intelligence[80] Self-Supervised Training For Low Dose CT Reconstruction作者 | Mehmet Ozan Unal, Metin Ertas, Isa Yildirim連結 | https://arxiv.org/abs/2010.13232 [81] SUREMap: Predicting Uncertainty in CNN-based Image Reconstruction Using Stein's Unbiased Risk Estimate作者 | Ruangrawee Kitichotkul, Christopher A. Metzler, Frank Ong, Gordon Wetzstein連結 | https://arxiv.org/abs/2010.13214 [82] Gestop : Customizable Gesture Control of Computer Systems作者 | Sriram Krishna, Nishant Sinha連結 | https://arxiv.org/abs/2010.13197 備註 | 5 pages, 5 figures, to appear in the proceedings of the 8th ACM IKDD CODS and 26th COMAD (CODS-COMAD '21)[83] Improving the Reconstruction of Disentangled Representation Learners via Multi-Stage Modelling作者 | Akash Srivastava, Yamini Bansal, Yukun Ding, Cole Hurwitz, Kai Xu, Bernhard Egger, Prasanna Sattigeri, Josh Tenenbaum, David D. Cox, Dan Gutfreund連結 | https://arxiv.org/abs/2010.13187 [84] Unsupervised Super-Resolution: Creating High-Resolution Medical Images from Low-Resolution Anisotropic Examples作者 | Jörg Sander, Bob D. de Vos, Ivana Išgum連結 | https://arxiv.org/abs/2010.13172 備註 | accepted at the SPIE Medical Imaging 2021 conference[85] Context Aware 3D UNet for Brain Tumor Segmentation作者 | Parvez Ahmad, Saqib Qamar, Linlin Shen, Adnan Saeed連結 | https://arxiv.org/abs/2010.13082 備註 | MICCAI 2020 Brain Lesions (BrainLes) Workshop[86] Dynamic Adversarial Patch for Evading Object Detection Models作者 | Shahar Hoory, Tzvika Shapira, Asaf Shabtai, Yuval Elovici連結 | https://arxiv.org/abs/2010.13070 [87] Automated triage of COVID-19 from various lung abnormalities using chest CT features作者 | Dor Amran, Maayan Frid-Adar, Nimrod Sagie, Jannette Nassar, Asher Kabakovitch, Hayit Greenspan連結 | https://arxiv.org/abs/2010.12967 備註 | This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible[88] LagNetViP: A Lagrangian Neural Network for Video Prediction作者 | Christine Allen-Blanchette, Sushant Veer, Anirudha Majumdar, Naomi Ehrich Leonard連結 | https://arxiv.org/abs/2010.12932 [89] Non-local Meets Global: An Iterative Paradigm for Hyperspectral Image Restoration作者 | Wei He, Quanming Yao, Chao Li, Naoto Yokoya, Qibin Zhao, Hongyan Zhang, Liangpei Zhang連結 | https://arxiv.org/abs/2010.12921 [90] Weakly-supervised VisualBERT: Pre-training without Parallel Images and Captions作者 | Liunian Harold Li, Haoxuan You, Zhecan Wang, Alireza Zareian, Shih-Fu Chang, Kai-Wei Chang連結 | https://arxiv.org/abs/2010.12831 [91] Modularity Improves Out-of-Domain Instruction Following作者 | Rodolfo Corona, Daniel Fried, Coline Devin, Dan Klein, Trevor Darrell連結 | https://arxiv.org/abs/2010.12764 [92] The RobotSlang Benchmark: Dialog-guided Robot Localization and Navigation作者 | Shurjo Banerjee, Jesse Thomason, Jason J. Corso連結 | https://arxiv.org/abs/2010.12639 備註 | Conference on Robot Learning 2020[93] S2cGAN: Semi-Supervised Training of Conditional GANs with Fewer Labels作者 | Arunava Chakraborty, Rahul Ragesh, Mahir Shah, Nipun Kwatra連結 | https://arxiv.org/abs/2010.12622