Xiyang Dai
Computer Vision and Pattern Recognition · 2017–2025
A researcher in the Science corpus: 23 papers; trusts 2,785 researchers and is trusted by 524 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 1,118 citations into it; #2,377 of 21,973 by trust here, #1,157 by citations
- Artificial Intelligence — 891 citations into it; #14,120 of 36,961 by trust here, #3,288 by citations
- Model Architectures — 308 citations into it; #501 of 2,288 by trust here, #236 by citations
- Multimodal Learning — 262 citations into it
- Representation & Self-Supervised Learning — 161 citations into it
- Evaluation & Benchmarks — 130 citations into it
- Efficiency & Compression — 106 citations into it
- Natural Language Processing — 93 citations into it
Whom Xiyang Dai trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Kaiming He
- Ross B. Girshick
- Alex Krizhevsky
- Geoffrey E. Hinton
- Diederik P. Kingma
- Yoshua Bengio
- Yann LeCun
- Karen Simonyan
- Ilya Sutskever
- Shaoqing Ren
Who trusts Xiyang Dai overall
- Jianwei Yang
- Lu Yuan
- Pengchuan Zhang
- Hao Zhang
- Chunyuan Li
- Jianfeng Gao
- Feng Li
- Bin Xiao
- Chien-Yao Wang
- Liunian Harold Li
Papers from Xiyang Dai's perspective
Ordered by how strongly the researchers Xiyang Dai 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)
- ImageNet: A large-scale hierarchical image database
- Long Short-Term Memory
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Gradient-based learning applied to document recognition
- ImageNet Large Scale Visual Recognition Challenge
- Going deeper with convolutions
Their papers
- Florence: A New Foundation Model for Computer Vision (2021) — 1,142 citations
- CvT: Introducing Convolutions to Vision Transformers (2021) — 2,478 citations
- Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding (2021) — 395 citations
- Dynamic Head: Unifying Object Detection Heads with Attentions (2021) — 964 citations
- RegionCLIP: Region-based Language-Image Pretraining (2021) — 921 citations
- Dynamic Convolution: Attention Over Convolution Kernels (2019) — 1,399 citations
- Efficient Self-supervised Vision Transformers for Representation Learning (2021) — 230 citations
- Focal Self-attention for Local-Global Interactions in Vision Transformers (2021) — 538 citations
- UFO: A UniFied TransfOrmer for Vision-Language Representation Learning (2021) — 65 citations
- BEVT: BERT Pretraining of Video Transformers (2021) — 269 citations
- Temporal Context Network for Activity Localization in Videos (2017) — 257 citations
- GLIPv2: Unifying Localization and Vision-Language Understanding (2022) — 392 citations
- Dynamic DETR: End-to-End Object Detection with Dynamic Attention (2021) — 452 citations
- Mobile-Former: Bridging MobileNet and Transformer (2021) — 695 citations
- Generalized Decoding for Pixel, Image, and Language (2022) — 380 citations
- MAN: Moment Alignment Network for Natural Language Moment Retrieval via Iterative Graph Adjustment (2018) — 344 citations
- Dynamic ReLU (2020) — 221 citations
- Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs (2025) — 509 citations
- Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks (2023) — 565 citations
- Residual Mixture of Experts (2022) — 55 citations