Scott D. Cohen
Computer Vision and Pattern Recognition · 2010–2021
A researcher in the Science corpus: 25 papers; trusts 3,098 researchers and is trusted by 1,808 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 749 citations into it; #1,315 of 21,973 by trust here, #1,651 by citations
- Artificial Intelligence — 284 citations into it; #20,274 of 36,961 by trust here, #11,943 by citations
- Multimodal Learning — 100 citations into it
- Natural Language Processing — 86 citations into it
- Evaluation & Benchmarks — 82 citations into it
- Model Architectures — 71 citations into it
- Aerospace Engineering — 47 citations into it
- Media Technology — 44 citations into it; #2,546 of 3,630 by trust here, #964 by citations
Whom Scott D. Cohen trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Kaiming He
- Ross B. Girshick
- Geoffrey E. Hinton
- Alex Krizhevsky
- Karen Simonyan
- Diederik P. Kingma
- Yoshua Bengio
- Andrew Zisserman
- Yann LeCun
- Ilya Sutskever
Who trusts Scott D. Cohen overall
- J. Liew
- Brian L. Price
- Konstantin Sofiiuk
- Rahaf Aljundi
- Zheng Lin
- Henghui Ding
- Kevis-Kokitsi Maninis
- Qin Liu
- Ning Xu
- Xi Chen
Papers from Scott D. Cohen's perspective
Ordered by how strongly the researchers Scott D. Cohen trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- ImageNet: A large-scale hierarchical image database
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Gradient-based learning applied to document recognition
- ImageNet Large Scale Visual Recognition Challenge
- Going deeper with convolutions
Their papers
- Deep Interactive Object Selection (2016) — 483 citations
- Context Driven Scene Parsing with Attention to Rare Classes (2014) — 162 citations
- Towards unified depth and semantic prediction from a single image (2015) — 459 citations
- YouTube-VOS: Sequence-to-Sequence Video Object Segmentation (2018) — 550 citations
- Object Contour Detection with a Fully Convolutional Encoder-Decoder Network (2016) — 389 citations
- Geodesic graph cut for interactive image segmentation (2010) — 211 citations
- Coupled Dictionary Training for Image Super-Resolution (2012) — 825 citations
- DVQA: Understanding Data Visualizations via Question Answering (2018) — 558 citations
- Sherlock: Scalable Fact Learning in Images (2015) — 27 citations
- Joint Object and Part Segmentation Using Deep Learned Potentials (2015) — 128 citations
- Discriminability Objective for Training Descriptive Captions (2018) — 211 citations
- PhraseClick: Toward Achieving Flexible Interactive Segmentation by Phrase and Click (2020) — 64 citations
- Deep GrabCut for Object Selection (2017) — 136 citations
- Semantic Object Selection (2014) — 20 citations
- Deep Image Matting (2017) — 510 citations
- Getting to 99% Accuracy in Interactive Segmentation (2020) — 40 citations
- Interactive Boundary Prediction for Object Selection (2018) — 38 citations
- Deep Interactive Thin Object Selection (2021) — 65 citations
- MultiSeg: Semantically Meaningful, Scale-Diverse Segmentations From Minimal User Input (2019) — 40 citations
- Skeleton Key: Image Captioning by Skeleton-Attribute Decomposition (2017) — 107 citations