De-An Huang
Computer Vision and Pattern Recognition · 2014–2022
A researcher in the Science corpus: 17 papers; trusts 2,418 researchers and is trusted by 1,105 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 555 citations into it; #1,736 of 21,973 by trust here, #2,759 by citations
- Artificial Intelligence — 493 citations into it; #6,896 of 36,961 by trust here, #5,760 by citations
- Reinforcement Learning — 122 citations into it; #1,952 of 2,250 by trust here, #1,418 by citations
- Natural Language Processing — 100 citations into it; #1,474 of 5,725 by trust here, #2,621 by citations
- Multimodal Learning — 91 citations into it
- Representation & Self-Supervised Learning — 82 citations into it; #2,202 of 3,156 by trust here, #1,640 by citations
- Control and Systems Engineering — 67 citations into it; #1,222 of 8,519 by trust here, #1,865 by citations
- Evaluation & Benchmarks — 49 citations into it
Whom De-An Huang trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Diederik P. Kingma
- Kaiming He
- Alex Krizhevsky
- Yoshua Bengio
- Ilya Sutskever
- Ross B. Girshick
- Alex Graves
- Yann LeCun
- Karen Simonyan
Who trusts De-An Huang overall
- Alexander Richard
- Amir-massoud Farahmand
- Hilde Kuehne
- Hazel Doughty
- Sergey Levine
- Fei Han
- Ivan Laptev
- Fadime Sener
- Juergen Gall
- Abhinav Kumar Gupta
Papers from De-An Huang's perspective
Ordered by how strongly the researchers De-An Huang 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)
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- ImageNet: A large-scale hierarchical image database
- Gradient-based learning applied to document recognition
- 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
- Connectionist Temporal Modeling for Weakly Supervised Action Labeling (2016) — 259 citations
- Neural Task Graphs: Generalizing to Unseen Tasks From a Single Video Demonstration (2018) — 151 citations
- Unsupervised Visual-Linguistic Reference Resolution in Instructional Videos (2017) — 57 citations
- Action-Reaction: Forecasting the Dynamics of Human Interaction (2014) — 130 citations
- MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge (2022) — 597 citations
- Finding "It": Weakly-Supervised Reference-Aware Visual Grounding in Instructional Videos (2018) — 103 citations
- Learning to Decompose and Disentangle Representations for Video Prediction (2018) — 322 citations
- Dynamic Task Prioritization for Multitask Learning (2018) — 457 citations
- Unsupervised Learning of Long-Term Motion Dynamics for Videos (2017) — 196 citations
- Forecasting Interactive Dynamics of Pedestrians with Fictitious Play (2016) — 166 citations
- Regression Planning Networks (2019) — 68 citations
- D3TW: Discriminative Differentiable Dynamic Time Warping for Weakly Supervised Action Alignment and Segmentation (2019) — 177 citations
- Spatio-Temporal Graph for Video Captioning With Knowledge Distillation (2020) — 272 citations
- PlaTe: Visually-Grounded Planning With Transformers in Procedural Tasks (2021) — 68 citations
- Procedure Planning in Instructional Videos (2019) — 129 citations
- Approximate MaxEnt Inverse Optimal Control and Its Application for Mental Simulation of Human Interactions (2015) — 29 citations
- Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models (2022) — 552 citations