2015
Going deeper with convolutions
47,433 citationsRead
Most cited
64 papers in total2016
SSD: Single Shot MultiBox Detector
30,402 citations
2015
Show and tell: A neural image caption generator
6,428 citationsRead
2013 · arXiv (Cornell University)
Intriguing properties of neural networks
5,635 citationsRead
2010
Why Does Unsupervised Pre-training Help Deep Learning?
2,097 citations
2016 · arXiv (Cornell University)
Static Analysis of Shape in TensorFlow Programs
1,659 citationsRead
Newest first
64 papers in total2023
- StoryBench: A Multifaceted Benchmark for Continuous Story VisualizationarXiv (Cornell University) · 1 citations
2022
- Phenaki: Variable Length Video Generation From Open Domain Textual DescriptionarXiv (Cornell University) · 79 citations
- INFOrmation Prioritization through EmPOWERment in Visual Model-Based RLarXiv (Cornell University) · 2 citations
2021
- FitVid: Overfitting in Pixel-Level Video PredictionarXiv (Cornell University) · 28 citations
- On Trade-offs of Image Prediction in Visual Model-Based Reinforcement Learning1 citations
2020
- SurfelGAN: Synthesizing Realistic Sensor Data for Autonomous DrivingIEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · 107 citations
- Model Based Reinforcement Learning for AtariInternational Conference on Learning Representations · 79 citations
- Models, Pixels, and Rewards: Evaluating Design Trade-offs in Visual Model-Based Reinforcement LearningarXiv (Cornell University) · 4 citations
2019
- The (Un)reliability of Saliency MethodsLecture notes in computer science · 469 citations
- VideoFlow: A Flow-Based Generative Model for Video80 citations
- VideoFlow: A Conditional Flow-Based Model for Stochastic Video GenerationarXiv (Cornell University) · 30 citations
- High Fidelity Video Prediction with Large Stochastic Recurrent Neural NetworksarXiv (Cornell University) · 18 citations
2018
- A Benchmark for Interpretability Methods in Deep Neural NetworksarXiv (Cornell University) · 387 citations
- Hierarchical Long-term Video Prediction without SupervisionarXiv (Cornell University) · 97 citations
- Evaluating Feature Importance EstimatesarXiv (Cornell University) · 54 citations
- Unsupervised Hierarchical Video Prediction
2017
- Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks1,635 citations
- Learning how to explain neural networks: PatternNet and PatternAttributionarXiv (Cornell University) · 290 citations
- Stochastic Variational Video PredictionarXiv (Cornell University) · 71 citations
- Show and Tell:2015MSCOCO画像キャプション攻撃から学んだ教訓【Powered by NICT】IEEE Transactions on Pattern Analysis and Machine Intelligence
2016
- Domain Separation NetworksarXiv (Cornell University) · 1,102 citations
- Show and Tell: Lessons Learned from the 2015 MSCOCO Image Captioning ChallengeIEEE Transactions on Pattern Analysis and Machine Intelligence · 916 citations
2014
- Scalable Object Detection Using Deep Neural Networks1,170 citations
- Training Deep Neural Networks on Noisy Labels with BootstrappingarXiv (Cornell University) · 762 citations
- Challenges in representation learning: A report on three machine learning contestsNeural Networks · 693 citations
- Scalable, High-Quality Object DetectionarXiv (Cornell University) · 334 citations
Research in numbers
From OpenAlex- preprint28
- article16
- conference paper11
- dissertation2
- other1
- arXiv (Cornell University)28
- IEEE Transactions on Pattern Analysis and Machine Intelligence2
- Lecture notes in computer science2
- IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)1
- Journal of Chemical Information and Modeling1
- Yoshua Bengio12
- Mohammad Babaeizadeh12
- Christian Szegedy9
- Dragomir Anguelov9
- Sergey Levine9
Experience and education
Universities
2006 to 2011Université de Montréal
Industry and labs
2013 to 2021Google (United States)
2017Alphabet (United States)
2014 to 2015Microsoft (United States)
2014Microsoft Research (United Kingdom)
2014Microsoft Research New York City (United States)
2012Yahoo (United States)
2004Max Planck Institute for Biological Cybernetics
2004Max Planck Society