Desmond Elliott
Artificial Intelligence · with Specia · 2013–2022
A researcher in the Science corpus: 16 papers; trusts 1,689 researchers and is trusted by 1,438 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 323 citations into it; #2,041 of 36,961 by trust here, #3,409 by citations
- Computer Vision and Pattern Recognition — 301 citations into it; #1,516 of 21,973 by trust here, #1,953 by citations
- Natural Language Processing — 196 citations into it; #1,193 of 5,725 by trust here, #1,813 by citations
- Multimodal Learning — 123 citations into it; #48 of 1,215 by trust here, #182 by citations
- Evaluation & Benchmarks — 115 citations into it; #457 of 3,155 by trust here, #785 by citations
- Model Architectures — 41 citations into it
- Language and Linguistics — 19 citations into it
- Large Language Models — 18 citations into it
Whom Desmond Elliott trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Yoshua Bengio
- Geoffrey E. Hinton
- Kaiming He
- Alex Krizhevsky
- Diederik P. Kingma
- Ilya Sutskever
- Karen Simonyan
- Michael J. Denkowski
- Ross B. Girshick
- Christian Szegedy
Who trusts Desmond Elliott overall
- Ozan Caglayan
- Loïc Barrault
- Lucia Specia
- Aditya Mogadala
- Pranava Swaroop Madhyastha
- Zhuosheng Zhang
- Jean-Benoit Delbrouck
- Douwe Kiela
- Shaowei Yao
- Po-Yao (Bernie) Huang
Papers from Desmond Elliott's perspective
Ordered by how strongly the researchers Desmond Elliott 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)
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
- ImageNet Large Scale Visual Recognition Challenge
Their papers
- Image Description using Visual Dependency Representations (2013) — 309 citations
- Multi30K: Multilingual English-German Image Descriptions (2016) — 660 citations
- Comparing Automatic Evaluation Measures for Image Description (2014) — 136 citations
- A Shared Task on Multimodal Machine Translation and Crosslingual Image Description (2016) — 255 citations
- Findings of the Third Shared Task on Multimodal Machine Translation (2018) — 160 citations
- Findings of the Second Shared Task on Multimodal Machine Translation and Multilingual Image Description (2017) — 233 citations
- Imagination Improves Multimodal Translation (2017) — 149 citations
- Automatic Description Generation from Images: A Survey of Models, Datasets, and Evaluation Measures (2016) — 393 citations
- How2: A Large-scale Dataset for Multimodal Language Understanding (2018) — 326 citations
- Automatic Description Generation from Images: A Survey of Models, Datasets, and Evaluation Measures (Extended Abstract) (2017) — 25 citations
- Measuring the Diversity of Automatic Image Descriptions (2018) — 49 citations
- Revisiting Transformer-based Models for Long Document Classification (2022) — 102 citations
- Adversarial Removal of Demographic Attributes Revisited (2019) — 63 citations
- Talking about other people: an endless range of possibilities (2018) — 14 citations
- IGLUE: A Benchmark for Transfer Learning across Modalities, Tasks, and Languages (2022) — 73 citations
- Adversarial Evaluation of Multimodal Machine Translation (2018) — 95 citations