David F. Harwath
Artificial Intelligence · 2013–2022
A researcher in the Science corpus: 17 papers; trusts 2,431 researchers and is trusted by 491 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 464 citations into it; #4,865 of 36,961 by trust here, #6,707 by citations
- Computer Vision and Pattern Recognition — 354 citations into it; #2,400 of 21,973 by trust here, #3,034 by citations
- Signal Processing — 222 citations into it; #688 of 7,592 by trust here, #651 by citations
- Speech & Audio — 210 citations into it; #106 of 1,080 by trust here, #218 by citations
- Multimodal Learning — 194 citations into it; #64 of 1,215 by trust here, #255 by citations
- Representation & Self-Supervised Learning — 149 citations into it; #1,363 of 3,156 by trust here, #1,338 by citations
- Natural Language Processing — 112 citations into it; #3,125 of 5,725 by trust here, #4,392 by citations
- Evaluation & Benchmarks — 50 citations into it
Whom David F. Harwath trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- James R. Glass
- Kaiming He
- Geoffrey E. Hinton
- Karen Simonyan
- Diederik P. Kingma
- Yoshua Bengio
- Alex Krizhevsky
- Andrej Karpathy
- Antonio Torralba
- Ross B. Girshick
Who trusts David F. Harwath overall
- James R. Glass
- Herman Kamper
- Grzegorz Chrupała
- Wei-Ning Hsu
- Yonatan Belinkov
- Puyuan Peng
- Emmanuel Azuh
- Karen Livescu
- William N. Havard
- Yu-An Chung
Papers from David F. Harwath's perspective
Ordered by how strongly the researchers David F. Harwath 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
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
Their papers
- Jointly Discovering Visual Objects and Spoken Words from Raw Sensory Input (2018) — 213 citations
- AVLnet: Learning Audio-Visual Language Representations from Instructional Videos (2020) — 148 citations
- Learning Hierarchical Discrete Linguistic Units from Visually-Grounded Speech (2019) — 88 citations
- Unsupervised Learning of Spoken Language with Visual Context (2016) — 261 citations
- Learning Word-Like Units from Joint Audio-Visual Analysis (2017) — 108 citations
- Multimodal Clustering Networks for Self-supervised Learning from Unlabeled Videos (2021) — 100 citations
- A summary of the 2012 JHU CLSP workshop on zero resource speech technologies and models of early language acquisition (2013) — 113 citations
- Deep multimodal semantic embeddings for speech and images (2015) — 168 citations
- Vision as an Interlingua: Learning Multilingual Semantic Embeddings of Untranscribed Speech (2018) — 61 citations
- Grounding Spoken Words in Unlabeled Video (2019) — 24 citations
- Towards Visually Grounded Sub-word Speech Unit Discovery (2019) — 36 citations
- Text-Free Image-to-Speech Synthesis Using Learned Segmental Units (2020) — 75 citations
- Learning modality-invariant representations for speech and images (2017) — 30 citations
- Self-Supervised Representation Learning for Speech Using Visual Grounding and Masked Language Modeling (2022) — 30 citations
- Transfer Learning from Audio-Visual Grounding to Speech Recognition (2019) — 32 citations
- Towards Bilingual Lexicon Discovery From Visually Grounded Speech Audio (2019) — 15 citations
- Learning Words by Drawing Images (2019) — 9 citations