Lisa Anne Hendricks
Artificial Intelligence · 2014–2022
A researcher in the Science corpus: 24 papers; trusts 2,433 researchers and is trusted by 6,010 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 846 citations into it; #1,052 of 36,961 by trust here, #366 by citations
- Computer Vision and Pattern Recognition — 562 citations into it; #538 of 21,973 by trust here, #427 by citations
- Natural Language Processing — 418 citations into it; #2,823 of 5,725 by trust here, #870 by citations
- Safety, Robustness & Interpretability — 258 citations into it; #681 of 2,259 by trust here, #161 by citations
- Multimodal Learning — 192 citations into it; #249 of 1,215 by trust here, #232 by citations
- Evaluation & Benchmarks — 169 citations into it
- Large Language Models — 114 citations into it
- Model Architectures — 68 citations into it; #247 of 2,288 by trust here, #144 by citations
Whom Lisa Anne Hendricks trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Alex Krizhevsky
- Ilya Sutskever
- Kaiming He
- Yoshua Bengio
- Karen Simonyan
- Diederik P. Kingma
- Ross B. Girshick
- Oriol Vinyals
- Sepp Hochreiter
Who trusts Lisa Anne Hendricks overall
- Trevor Darrell
- Mohit Bansal
- Anna Rohrbach
- Marcus Rohrbach
- Zhe Gan
- Matteo Stefanini
- Zeynep Akata
- Peter Anderson
- Marcella Cornia
- Ronghang Hu
Papers from Lisa Anne Hendricks's perspective
Ordered by how strongly the researchers Lisa Anne Hendricks 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
- Long-term recurrent convolutional networks for visual recognition and description (2014) — 6,439 citations
- Scaling Language Models: Methods, Analysis & Insights from Training Gopher (2021) — 1,640 citations
- Training Compute-Optimal Large Language Models (2022) — 3,535 citations
- Ethical and social risks of harm from Language Models (2021) — 1,580 citations
- Women also Snowboard: Overcoming Bias in Captioning Models (2018) — 525 citations
- Deep Compositional Captioning: Describing Novel Object Categories without Paired Training Data (2015) — 292 citations
- Localizing Moments in Video with Natural Language (2017) — 1,236 citations
- Improving alignment of dialogue agents via targeted human judgements (2022) — 676 citations
- Generating Visual Explanations (2016) — 658 citations
- Long-Term Recurrent Convolutional Networks for Visual Recognition and Description (2017)
- Multimodal Explanations: Justifying Decisions and Pointing to the Evidence (2018) — 482 citations
- Challenges in Detoxifying Language Models (2021) — 248 citations
- Object Hallucination in Image Captioning (2018) — 816 citations
- Captioning Images with Diverse Objects (2016) — 186 citations
- Taxonomy of Risks posed by Language Models (2022) — 1,066 citations
- Grounding Visual Explanations (2018) — 241 citations
- Decoupling the Role of Data, Attention, and Losses in Multimodal Transformers (2021) — 134 citations
- Towards a Visual Privacy Advisor: Understanding and Predicting Privacy Risks in Images (2017) — 423 citations
- Improving LSTM-based Video Description with Linguistic Knowledge Mined from Text (2016) — 122 citations
- Deep Compositional Captioning: Describing Novel Object Categories without Paired Training Data (2016)