每日论文速递:计算机视觉相关(11月8日更新版)

作者:Hsu
转载自:深度学习这件小事
原文链接:

计算机视觉(11月8日更新版)

[1] The Curious Layperson: Fine-Grained Image Recognition without Expert Labels作者 | Subhabrata Choudhury, Iro Laina, Christian Rupprecht, Andrea Vedaldi链接 | arxiv.org/abs/2111.0365 项目链接 | robots.ox.ac.uk/~vgg/re备注 | To appear in BMVC 2021 (Oral).

[2] Normalizing Flow as a Flexible Fidelity Objective for Photo-Realistic Super-resolution作者 | Andreas Lugmayr, Martin Danelljan, Fisher Yu, Luc Van Gool, Radu Timofte链接 | arxiv.org/abs/2111.0364

[3] TermiNeRF: Ray Termination Prediction for Efficient Neural Rendering作者 | Martin Piala, Ronald Clark链接 | arxiv.org/abs/2111.0364 项目链接 | projects.mackopes.com/t备注 | 3DV 2021;

[4] BBC-Oxford British Sign Language Dataset作者 | Samuel Albanie, Gül Varol, Liliane Momeni, Hannah Bull, Triantafyllos Afouras, Himel Chowdhury, Neil Fox, Bencie Woll, Rob Cooper, Andrew McParland, Andrew Zisserman链接 | arxiv.org/abs/2111.0363

[5] Single Image Deraining Network with Rain Embedding Consistency and Layered LSTM作者 | Yizhou Li, Yusuke Monno, Masatoshi Okutomi链接 | arxiv.org/abs/2111.0361 备注 | Accepted by WACV2022, January 2022

[6] Edge Tracing using Gaussian Process Regression作者 | Jamie Burke, Stuart King链接 | arxiv.org/abs/2111.0360 项目链接 | github.com/jaburke166/g备注 | Accepted to be published in IEEE Transactions on Image Processing.

[7] AGPCNet: Attention-Guided Pyramid Context Networks for Infrared Small Target Detection作者 | Tianfang Zhang, Siying Cao, Tian Pu, Zhenming Peng链接 | arxiv.org/abs/2111.0358

[8] Spatial-Temporal Residual Aggregation for High Resolution Video Inpainting作者 | Vishnu Sanjay Ramiya Srinivasan, Rui Ma, Qiang Tang, Zili Yi, Zhan Xu链接 | arxiv.org/abs/2111.0357 项目链接 | github.com/Ascend-Resea备注 | Accepted by BMVC 2021.

[9] Synchronized Smartphone Video Recording System of Depth and RGB Image Frames with Sub-millisecond Precision作者 | Marsel Faizullin, Anastasiia Kornilova, Azat Akhmetyanov, Konstantin Pakulev, Andrey Sadkov, Gonzalo Ferrer链接 | arxiv.org/abs/2111.0355 备注 | IEEE Sensors Journal submitted paper

[10] Interpreting Representation Quality of DNNs for 3D Point Cloud Processing作者 | Wen Shen, Qihan Ren, Dongrui Liu, Quanshi Zhang链接 | arxiv.org/abs/2111.0354

[11] Semantic Consistency in Image-to-Image Translation for Unsupervised Domain Adaptation作者 | Stephan Brehm, Sebastian Scherer, Rainer Lienhart链接 | arxiv.org/abs/2111.0352

[12] Visualizing the Emergence of Intermediate Visual Patterns in DNNs作者 | Mingjie Li, Shaobo Wang, Quanshi Zhang链接 | arxiv.org/abs/2111.0350

[13] Event-based Motion Segmentation by Cascaded Two-Level Multi-Model Fitting作者 | Xiuyuan Lu, Yi Zhou, Shaojie Shen链接 | arxiv.org/abs/2111.0348 备注 | Accepted for presentation at the 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2021)

[14] Improving Visual Quality of Image Synthesis by A Token-based Generator with Transformers作者 | Yanhong Zeng, Huan Yang, Hongyang Chao, Jianbo Wang, Jianlong Fu链接 | arxiv.org/abs/2111.0348 备注 | NeurIPS 2021

[15] DriveGuard: Robustification of Automated Driving Systems with Deep Spatio-Temporal Convolutional Autoencoder作者 | Andreas Papachristodoulou, Christos Kyrkou, Theocharis Theocharides链接 | arxiv.org/abs/2111.0348 备注 | 2021 IEEE Winter Conference on Applications of Computer Vision Workshops (WACVW)

[16] Nondestructive Testing of Composite Fibre Materials with Hyperspectral Imaging : Evaluative Studies in the EU H2020 FibreEUse Project作者 | Yijun Yan, Jinchang Ren, Huan Zhao, James F.C. Windmill, Winifred Ijomah, Jesper de Wit, Justus von Freeden链接 | arxiv.org/abs/2111.0344

[17] Solving Traffic4Cast Competition with U-Net and Temporal Domain Adaptation作者 | Vsevolod Konyakhin, Nina Lukashina, Aleksei Shpilman链接 | arxiv.org/abs/2111.0342 备注 | Conference on Neural Information Processing Systems (NeurIPS 2021) Traffic4cast Competition

[18] Sampling Equivariant Self-attention Networks for Object Detection in Aerial Images作者 | Guo-Ye Yang, Xiang-Li Li, Ralph R. Martin, Shi-Min Hu链接 | arxiv.org/abs/2111.0342

[19] Structure-aware Image Inpainting with Two Parallel Streams作者 | Zhilin Huang, Chujun Qin, Ruixin Liu, Zhenyu Weng, Yuesheng Zhu链接 | arxiv.org/abs/2111.0341 备注 | rejected by IJCAI 2021

[20] MSC-VO: Exploiting Manhattan and Structural Constraints for Visual Odometry作者 | Joan P. Company-Corcoles, Emilio Garcia-Fidalgo, Alberto Ortiz链接 | arxiv.org/abs/2111.0340 备注 | Submitted to RAL + ICRA 2022

[21] SSA: Semantic Structure Aware Inference for Weakly Pixel-Wise Dense Predictions without Cost作者 | Yanpeng Sun, Zechao Li链接 | arxiv.org/abs/2111.0339

[22] A Deep Learning Generative Model Approach for Image Synthesis of Plant Leaves作者 | Alessandrop Benfenati, Davide Bolzi, Paola Causin, Roberto Oberti链接 | arxiv.org/abs/2111.0338

[23] Seamless Satellite-image Synthesis作者 | Jialin Zhu, Tom Kelly链接 | arxiv.org/abs/2111.0338

[24] Negative Sample is Negative in Its Own Way: Tailoring Negative Sentences for Image-Text Retrieval作者 | Zhihao Fan, Zhongyu Wei, Zejun Li, Siyuan Wang, Jianqing Fan链接 | arxiv.org/abs/2111.0334

[25] KORSAL: Key-point Detection based Online Real-Time Spatio-Temporal Action Localization作者 | Kalana Abeywardena, Shechem Sumanthiran, Sakuna Jayasundara, Sachira Karunasena, Ranga Rodrigo, Peshala Jayasekara链接 | arxiv.org/abs/2111.0331

[26] FBNet: Feature Balance Network for Urban-Scene Segmentation作者 | Lei Gan, Huabin Huang, Banghuai Li, Ye Yuan链接 | arxiv.org/abs/2111.0328 备注 | Tech Report

[27] Recognizing Vector Graphics without Rasterization作者 | Xinyang Jiang, Lu Liu, Caihua Shan, Yifei Shen, Xuanyi Dong, Dongsheng Li链接 | arxiv.org/abs/2111.0328

[28] Remote Sensing Image Super-resolution and Object Detection: Benchmark and State of the Art作者 | Yi Wang, Syed Muhammad Arsalan Bashir, Mahrukh Khan, Qudrat Ullah, Rui Wang, Yilin Song, Zhe Guo, Yilong Niu链接 | arxiv.org/abs/2111.0326 备注 | Submitted to Elsevier journal for review

[29] Technical Report: Disentangled Action Parsing Networks for Accurate Part-level Action Parsing作者 | Xuanhan Wang, Xiaojia Chen, Lianli Gao, Lechao Chen, Jingkuan Song链接 | arxiv.org/abs/2111.0322

[30] Fast Camouflaged Object Detection via Edge-based Reversible Re-calibration Network作者 | Ge-Peng Ji, Lei Zhu, Mingchen Zhuge, Keren Fu链接 | arxiv.org/abs/2111.0321 备注 | Accepted by Pattern Recognition 2022

[31] Addressing Multiple Salient Object Detection via Dual-Space Long-Range Dependencies作者 | Bowen Deng, Andrew P. French, Michael P. Pound链接 | arxiv.org/abs/2111.0319

[32] EditGAN: High-Precision Semantic Image Editing作者 | Huan Ling, Karsten Kreis, Daiqing Li, Seung Wook Kim, Antonio Torralba, Sanja Fidler链接 | arxiv.org/abs/2111.0318

[33] StyleCLIPDraw: Coupling Content and Style in Text-to-Drawing Synthesis作者 | Peter Schaldenbrand, Zhixuan Liu, Jean Oh链接 | arxiv.org/abs/2111.0313

[34] Attention on Classification for Fire Segmentation作者 | Milad Niknejad, Alexandre Bernardino链接 | arxiv.org/abs/2111.0312

[35] Skeleton-Split Framework using Spatial Temporal Graph Convolutional Networks for Action Recogntion作者 | Motasem Alsawadi, Miguel Rio链接 | arxiv.org/abs/2111.0310

[36] Voxel-based 3D Detection and Reconstruction of Multiple Objects from a Single Image作者 | Feng Liu, Xiaoming Liu链接 | arxiv.org/abs/2111.0309 备注 | NeurIPS 2021

[37] A Unified Game-Theoretic Interpretation of Adversarial Robustness作者 | Jie Ren, Die Zhang, Yisen Wang, Lu Chen, Zhanpeng Zhou, Yiting Chen, Xu Cheng, Xin Wang, Meng Zhou, Jie Shi, Quanshi Zhang链接 | arxiv.org/abs/2111.0353 备注 | arXiv admin note: substantial text overlap with arXiv:2103.07364

[38] Cross Modality 3D Navigation Using Reinforcement Learning and Neural Style Transfer作者 | Cesare Magnetti, Hadrien Reynaud, Bernhard Kainz链接 | arxiv.org/abs/2111.0348

[39] BiosecurID: a multimodal biometric database作者 | Julian Fierrez, Javier Galbally, Javier Ortega-Garcia, et al.链接 | arxiv.org/abs/2111.0347 备注 | Published at Pattern Analysis and Applications journal

[40] ProSTformer: Pre-trained Progressive Space-Time Self-attention Model for Traffic Flow Forecasting作者 | Xiao Yan, Xianghua Gan, Jingjing Tang, Rui Wang链接 | arxiv.org/abs/2111.0345

[41] Generalized Radiograph Representation Learning via Cross-supervision between Images and Free-text Radiology Reports作者 | Hong-Yu Zhou, Xiaoyu Chen, Yinghao Zhang, Ruibang Luo, Liansheng Wang, Yizhou Yu链接 | arxiv.org/abs/2111.0345 备注 | Technical Report

[42] Numerisation D'un Siecle de Paysage Ferroviaire Français : recul du rail, conséquences territoriales et coût environnemental作者 | Robert Jeansoulin (LIGM)链接 | arxiv.org/abs/2111.0343 备注 | in French.

[43] A bone suppression model ensemble to improve COVID-19 detection in chest X-rays作者 | Sivaramakrishnan Rajaraman, Gregg Cohen, Les folio, Sameer Antani链接 | arxiv.org/abs/2111.0340

[44] Versatile Learned Video Compression作者 | Runsen Feng, Zongyu Guo, Zhizheng Zhang, Zhibo Chen链接 | arxiv.org/abs/2111.0338

[45] Segmentation of 2D Brain MR Images作者 | Angad Ripudaman Singh Bajwa链接 | arxiv.org/abs/2111.0337

[46] Hepatic vessel segmentation based on 3Dswin-transformer with inductive biased multi-head self-attention作者 | Mian Wu, Yinling Qian, Xiangyun Liao, Qiong Wang, Pheng-Ann Heng链接 | arxiv.org/abs/2111.0336

[47] Frequency-Aware Physics-Inspired Degradation Model for Real-World Image Super-Resolution作者 | Zhenxing Dong, Hong Cao, Wang Shen, Yu Gan, Yuye Ling, Guangtao Zhai, Yikai Su链接 | arxiv.org/abs/2111.0330

[48] Pathological Analysis of Blood Cells Using Deep Learning Techniques作者 | Virender Ranga, Shivam Gupta, Priyansh Agrawal, Jyoti Meena链接 | arxiv.org/abs/2111.0327

[49] Learning of Frequency-Time Attention Mechanism for Automatic Modulation Recognition作者 | Shangao Lin, Yuan Zeng, Yi Gong链接 | arxiv.org/abs/2111.0325

[50] Multi-Spectral Multi-Image Super-Resolution of Sentinel-2 with Radiometric Consistency Losses and Its Effect on Building Delineation作者 | Muhammed Razzak, Gonzalo Mateo-Garcia, Luis Gómez-Chova, Yarin Gal, Freddie Kalaitzis链接 | arxiv.org/abs/2111.0323

[51] GraN-GAN: Piecewise Gradient Normalization for Generative Adversarial Networks作者 | Vineeth S. Bhaskara, Tristan Aumentado-Armstrong, Allan Jepson, Alex Levinshtein链接 | arxiv.org/abs/2111.0316 备注 | WACV 2022 Main Conference Paper (Submitted: 18 Aug 2021, Accepted: 4 Oct 2021)

[52] PDBL: Improving Histopathological Tissue Classification with Plug-and-Play Pyramidal Deep-Broad Learning作者 | Jiatai Lin, Guoqiang Han, Xipeng Pan, Hao Chen, Danyi Li, Xiping Jia, Zhenwei Shi, Zhizhen Wang, Yanfen Cui, Haiming Li, Changhong Liang, Li Liang, Zaiyi Liu, Chu Han链接 | arxiv.org/abs/2111.0306




机器学习/深度学习算法/自然语言处理交流群

已建立机器学习算法-自然语言处理微信交流群!想要进交流群进行学习的同学,可以直接加我的微信号:HIT_NLP。加的时候备注一下:知乎+学校+昵称 (不加备注不会接受同意,望谅解),想进pytorch群,备注知乎+学校+昵称+Pytorch即可。然后我们就可以拉你进群了。群里已经有非得多国内外高校同学,交流氛围非常好。

强烈推荐大家关注机器学习算法与自然语言处理账号和机器学习算法与自然语言处理微信公众号,可以快速了解到最新优质的干货资源。

推荐阅读

每日论文速递:自然语言处理相关(11月8日更新版) - 知乎 (zhihu.com)

开始卷Survey了! - 知乎 (zhihu.com)

2021EMNLP开幕,复旦黄萱菁任程序主席:中国投稿量最高,接收207篇,仅次于美国 - 知乎 (zhihu.com)

丁香园在语义匹配任务上的探索与实践 - 知乎 (zhihu.com)

进入BERT时代,向量语义检索我们关注什么 - 知乎 (zhihu.com)

每日论文速递:自然语言处理相关(11月5日更新版) - 知乎 (zhihu.com)

每日论文速递:计算机视觉相关(11月5日更新版) - 知乎 (zhihu.com)

助力AAAI2022 Rebuttal! - 知乎 (zhihu.com)

每日论文速递:自然语言处理相关(11月4日更新版) - 知乎 (zhihu.com)

每日论文速递:计算机视觉相关(11月4日更新版) - 知乎 (zhihu.com)

清华大学:2021元宇宙研究报告! - 知乎 (zhihu.com)

SLU:任务型对话系统的卡脖子问题! - 知乎 (zhihu.com)

每日论文速递:自然语言处理相关(11月3日更新版) - 知乎 (zhihu.com)

每日论文速递:计算机视觉相关(11月3日更新版) - 知乎 (zhihu.com)

每日论文速递:自然语言处理相关(11月2日更新版) - 知乎 (zhihu.com)

每日论文速递:计算机视觉相关(11月2日更新版) - 知乎 (zhihu.com)

清华大学:2021元宇宙研究报告! - 知乎 (zhihu.com)

博士申请 | 蒙特利尔大学计算机系助理教授刘邦博士招博士生/硕士生若干名 - 知乎 (zhihu.com)

卷向VL! - 知乎 (zhihu.com)

机器翻译前沿十问:开源来源于无私的分享 | 东北大学肖桐专访 - 知乎 (zhihu.com)

北大万小军:如何应对科研中的困难与挑战 - 知乎 (zhihu.com)

实习招聘 | 微软亚洲研究院招聘talking face synthesis方向研究实习生 - 知乎 (zhihu.com)

实习招聘 | 创新工场首席科学家、原ACL主席、MSRA副院长周明老师招聘实习生 - 知乎 (zhihu.com)

IBM Watson「败走中国」内幕:认知推理远未成熟,却言必AI - 知乎 (zhihu.com)

60亿击败1750亿、验证胜过微调:OpenAI发现GPT-3解决数学题,并非参数越大越好 - 知乎 (zhihu.com)

Jeff Dean亲自揭秘谷歌下一代AI架构:通用、稀疏且高效,网友不买帐:毫无新意 - 知乎 (zhihu.com)

EMNLP 2021奖项公布,剑桥刘方宇、哥大杨子小帆一作论文分获最佳长、短论文奖 - 知乎 (zhihu.com)

NeurIPS 2021有哪些值得读的NLP论文? - 知乎 (zhihu.com)

图神经网络:Graph Neural Networks - 知乎 (zhihu.com)

2022 AI趋势8大预测 - 知乎 (zhihu.com)

招聘 | 百度搜索策略部招聘机器学习/数据挖掘/NLP/视觉算法工程师 - 知乎 (zhihu.com)

哈工大车万翔:如何做一个精彩的学术报告 - 知乎 (zhihu.com)

编辑于 2021-11-08 22:36