Zhe Gan
Artificial Intelligence · 2015–2023
A researcher in the Science corpus: 69 papers; trusts 4,821 researchers and is trusted by 3,322 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 2,631 citations into it; #1,044 of 36,961 by trust here, #546 by citations
- Computer Vision and Pattern Recognition — 2,342 citations into it; #913 of 21,973 by trust here, #331 by citations
- Natural Language Processing — 1,051 citations into it; #1,454 of 5,725 by trust here, #646 by citations
- Multimodal Learning — 951 citations into it; #37 of 1,215 by trust here, #19 by citations
- Evaluation & Benchmarks — 418 citations into it
- Representation & Self-Supervised Learning — 333 citations into it; #1,354 of 3,156 by trust here, #393 by citations
- Model Architectures — 319 citations into it
- Large Language Models — 295 citations into it; #143 of 810 by trust here, #365 by citations
Whom Zhe Gan trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Diederik P. Kingma
- Kaiming He
- Geoffrey E. Hinton
- Alex Krizhevsky
- Ilya Sutskever
- Yoshua Bengio
- Ross B. Girshick
- Ruslan Salakhutdinov
- Alex Graves
- Oriol Vinyals
Who trusts Zhe Gan overall
- Chunyuan Li
- Linjie Li
- Yizhe Zhang
- Yen-Chun Chen
- Jianfeng Wang
- Zhengyuan Yang
- Yunchen Pu
- Pengchuan Zhang
- Xiaowei Hu
- Yu Cheng
Papers from Zhe Gan's perspective
Ordered by how strongly the researchers Zhe Gan 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)
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- ImageNet: A large-scale hierarchical image database
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Gradient-based learning applied to document recognition
- 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
- UNITER: UNiversal Image-TExt Representation Learning (2019) — 2,659 citations
- AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks (2017) — 1,976 citations
- UNITER: Learning UNiversal Image-TExt Representations (2019) — 477 citations
- Large-Scale Adversarial Training for Vision-and-Language Representation Learning (2020) — 559 citations
- An Empirical Study of GPT-3 for Few-Shot Knowledge-Based VQA (2021) — 537 citations
- Hero: Hierarchical Encoder for Video+Language Omni-representation Pre-training (2020) — 565 citations
- Less is More: CLIPBERT for Video-and-Language Learning via Sparse Sampling (2021) — 804 citations
- Variational Autoencoder for Deep Learning of Images, Labels and Captions (2016) — 851 citations
- Scaling Up Vision-Language Pretraining for Image Captioning (2021) — 335 citations
- GIT: A Generative Image-to-text Transformer for Vision and Language (2022) — 787 citations
- VIOLET : End-to-End Video-Language Transformers with Masked Visual-token Modeling (2021) — 255 citations
- Semantic Compositional Networks for Visual Captioning (2016) — 451 citations
- Patient Knowledge Distillation for BERT Model Compression (2019) — 984 citations
- StyleNet: Generating Attractive Visual Captions with Styles (2017) — 298 citations
- An Empirical Study of Training End-to-End Vision-and-Language Transformers (2021) — 462 citations
- FreeLB: Enhanced Adversarial Training for Natural Language Understanding (2019) — 520 citations
- Tactical Rewind: Self-Correction via Backtracking in Vision-And-Language Navigation (2019) — 185 citations
- UFO: A UniFied TransfOrmer for Vision-Language Representation Learning (2021) — 65 citations
- Vision-Language Pre-training: Basics, Recent Advances, and Future Trends (2022) — 223 citations
- Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization (2018) — 318 citations