Tatsuya Harada
Computer Vision and Pattern Recognition · 2012–2020
A researcher in the Science corpus: 21 papers; trusts 3,207 researchers and is trusted by 2,713 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 511 citations into it; #1,022 of 21,973 by trust here, #2,462 by citations
- Artificial Intelligence — 322 citations into it; #2,258 of 36,961 by trust here, #2,845 by citations
- Representation & Self-Supervised Learning — 103 citations into it
- Generative Models — 82 citations into it; #243 of 1,963 by trust here, #582 by citations
- Evaluation & Benchmarks — 58 citations into it
- Model Architectures — 58 citations into it
- Optimization & Training — 56 citations into it
- Media Technology — 48 citations into it; #1,190 of 3,630 by trust here, #1,654 by citations
Whom Tatsuya Harada trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Krizhevsky
- Geoffrey E. Hinton
- Kaiming He
- Diederik P. Kingma
- Karen Simonyan
- Yoshua Bengio
- Yann LeCun
- Ross B. Girshick
- Ilya Sutskever
- Andrew Zisserman
Who trusts Tatsuya Harada overall
- Kuniaki Saito
- Aravindh Mahendran
- Jian Liang
- Andrea Vedaldi
- Miaoyun Zhao
- Garrett Wilson
- Alexey Dosovitskiy
- Mohammad Rostami
- Yulai Cong
- Kaiyang Zhou
Papers from Tatsuya Harada's perspective
Ordered by how strongly the researchers Tatsuya Harada trusts endorse each paper. Same corpus, a different order for every researcher.
- ImageNet classification with deep convolutional neural networks
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- ImageNet: A large-scale hierarchical image database
- Long Short-Term Memory
- Gradient-based learning applied to document recognition
- Attention is All you Need (Neural Information Processing Systems)
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- ImageNet Large Scale Visual Recognition Challenge
- Going deeper with convolutions
Their papers
- Neural 3D Mesh Renderer (2017) — 1,168 citations
- Image Generation From Small Datasets via Batch Statistics Adaptation (2019) — 211 citations
- Adversarial Dropout Regularization (2017) — 296 citations
- Graphical Gaussian Vector for Image Categorization (2012) — 8 citations
- Maximum Classifier Discrepancy for Unsupervised Domain Adaptation (2017) — 2,008 citations
- Open Set Domain Adaptation by Backpropagation (2018) — 610 citations
- Between-Class Learning for Image Classification (2017) — 222 citations
- Image Reconstruction from Bag-of-Visual-Words (2014) — 86 citations
- Strong-Weak Distribution Alignment for Adaptive Object Detection (2018) — 756 citations
- Domain Generalization Using a Mixture of Multiple Latent Domains (2019) — 357 citations
- Asymmetric Tri-training for Unsupervised Domain Adaptation (2017) — 615 citations
- Viewpoint-Aware Video Summarization (2018) — 39 citations
- Revisiting Fine-tuning for Few-shot Learning (2019) — 67 citations
- Self-supervised Learning of 3D Objects from Natural Images (2019) — 7 citations
- Unsupervised Brain Abnormality Detection Using High Fidelity Image Reconstruction Networks (2020) — 5 citations
- Multimodal Explanations by Predicting Counterfactuality in Videos (2018) — 43 citations
- Learning to Explain With Complemental Examples (2018) — 44 citations
- MFNet: Towards real-time semantic segmentation for autonomous vehicles with multi-spectral scenes (2017) — 668 citations
- Improved Dense Trajectory with Cross Streams (2016) — 15 citations
- Implementation of a Practical Distributed Calculation System with Browsers and JavaScript, and Application to Distributed Deep Learning (2015) — 10 citations