Correspondence Networks with Adaptive Neighbourhood Consensus (CVPR2020)
Shuda Li, Kai Han, Theo W. Costain, Henry Howard-Jenkins, Victor Prisacariu
[paper]
DeepEMD: Few-Shot Image Classification with Differentiable Earth Mover's Distance and Structured Classifiers (CVPR2020)
Chi Zhang, Yujun Cai, Guosheng Lin, Chunhua Shen
[paper]
Chained Representation Cycling: Learning to Estimate 3D Human Pose and Shape by Cycling Between Representations (AAAI2020)
Nadine Rueegg, Christoph Lassner, Michael J. Black, Konrad Schindler
[paper]
All you need is a good representation: A multi-level and classifier-centric representation for few-shot learning
Shaoli Huang, Dacheng Tao
[paper]
Unsupervised Visual Representation Learning with Increasing Object Shape Bias
Zhibo Wang, Shen Yan, Xiaoyu Zhang, Niels Lobo
[paper]
Supporting stylists by recommending fashion style
Tobias Kuhn, Steven Bourke, Levin Brinkmann, Tobias Buchwald, Conor Digan, Hendrik Hache, Sebastian Jaeger, Patrick Lehmann, Oskar Maier, Stefan Matting, Yura Okulovsky
[paper]
Counterfactual Visual Explanations (ICML2019)
Yash Goyal, Ziyan Wu, Jan Ernst, Dhruv Batra, Devi Parikh, Stefan Lee
[paper]
Cerberus: A Multi-headed Derenderer
Boyang Deng, Simon Kornblith, Geoffrey Hinton
[paper]
Learning 3D Human Dynamics from Video (CVPR2019)
[project]
[code]
Convolutional Mesh Regression for Single-Image Human Shape Reconstruction (CVPR2019 oral)
[project]
Detailed Human Shape Estimation from a Single Image by Hierarchical Mesh Deformation
Hao Zhu, Xinxin Zuo, Sen Wang, Xun Cao, Ruigang Yang
[paper]
Objects as Points
Xingyi Zhou, Dequan Wang, Philipp Krähenbühl
[paper]
Semantic Soft Segmentation (SIGGRAPH2018)
[project]
Im2Flow: Motion Hallucination from Static Images for Action Recognition (CVPR2018)
Ruohan Gao, Bo Xiong, Kristen Grauman
[paper]
[code]
Solving Archaeological Puzzles
Niv Derech, Ayellet Tal, Ilan Shimshoni
[paper]
Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimation
Mohamed Omran, Christoph Lassner, Gerard Pons-Moll, Peter V. Gehler, Bernt Schiele
[paper]
[code]
Graph R-CNN for Scene Graph Generation (ECCV2018)
Jianwei Yang, Jiasen Lu, Stefan Lee, Dhruv Batra, Devi Parikh
[paper]
Neural Best-Buddies: Sparse Cross-Domain Correspondence (SIGGRAPH2018)
Kfir Aberman, Jing Liao, Mingyi Shi, Dani Lischinski, Baoquan Chen, Daniel Cohen-Or
[paper]
[code]
[qiita]
How do Convolutional Neural Networks Learn Design? (ICPR2018)
Shailza Jolly, Brian Kenji Iwana, Ryohei Kuroki, Seiichi Uchida
[paper]
画像検索 (特定物体認識) — 古典手法、マッチング、深層学習、Kaggle
[link]
UNet++: A Nested U-Net Architecture for Medical Image Segmentation
Zongwei Zhou, Md Mahfuzur Rahman Siddiquee, Nima Tajbakhsh, Jianming Liang
[paper]
Deep Clustering for Unsupervised Learning of Visual Features (ECCV2018)
Mathilde Caron, Piotr Bojanowski, Armand Joulin, Matthijs Douze
[paper]
Visual Affordance and Function Understanding: A Survey
Mohammed Hassanin, Salman Khan, Murat Tahtali
[paper]
DOOBNet: Deep Object Occlusion Boundary Detection from an Image
Guoxia Wang, Xiaohui Liang, Frederick W. B. Li
[paper]
Video Object Segmentation with Language Referring Expressions
Anna Khoreva, Anna Rohrbach, Bernt Schiele
[paper]
Dynamic Few-Shot Visual Learning without Forgetting (CVPR2018)
Spyros Gidaris, Nikos Komodakis
[paper]
RotationNet: Joint Object Categorization and Pose Estimation Using Multiviews from Unsupervised Viewpoints (CVPR2018)
[project
Binge Watching: Scaling Affordance Learning from Sitcoms (CVPR2017)
[paper]
Feedback-prop: Convolutional Neural Network Inference under Partial Evidence (CVPR2018)
Tianlu Wang, Kota Yamaguchi, Vicente Ordonez
[paper]
Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation
Naoto Inoue, Ryosuke Furuta, Toshihiko Yamasaki, Kiyoharu Aizawa
[project]
[paper]
DeepVoting: A Robust and Explainable Deep Network for Semantic Part Detection under Partial Occlusion
Zhishuai Zhang, Cihang Xie, Jianyu Wang, Lingxi Xie, Alan L. Yuille
[paper]
A Survey on Acceleration of Deep Convolutional Neural Networks
Jian Cheng, Peisong Wang, Gang Li, Qinghao Hu, Hanqing Lu
[paper]
Incremental Learning Through Deep Adaptation
Amir Rosenfeld, John K. Tsotsos
[paper]
A Note on the Inception Score
Shane Barratt, Rishi Sharma
[paper]