CoCa: Contrastive Captioners are Image-Text Foundation Models

Jiahui Yu, Zirui Wang, Vijay K. Vasudevan, +3

arXiv (Cornell University)

EngineeringMachine LearningMultimodal LearningNatural Language ProcessingMultimodal Llm +15

SimVLM: Simple Visual Language Model Pretraining with Weak Supervision

Zirui Wang, Jiahui Yu, Adams Wei Yu, +3

arXiv (Cornell University)

EngineeringMachine LearningPretraining ProcedureMultilingual PretrainingNatural Language Processing +14

Scaling Autoregressive Models for Content-Rich Text-to-Image Generation

Jiahui Yu, Yuanzhong Xu, Jing Yu Koh, +14

arXiv (Cornell University)

Image TokensEngineeringMachine LearningNatural Language ProcessingMultimodal Llm +15

NeRF--: Neural Radiance Fields Without Known Camera Parameters

Zirui Wang, Shangzhe Wu, Weidi Xie, +2

arXiv (Cornell University)

Known Camera ParametersMachine VisionImage AnalysisEngineeringDifferentiable Rendering +13

NoPe-NeRF: Optimising Neural Radiance Field with No Pose Prior

Wenjing Bian, Zirui Wang, Kejie Li, +1

Machine VisionImage AnalysisCamera TrajectoriesEngineeringDifferentiable Rendering +11

FlowNet3D++: Geometric Losses For Deep Scene Flow Estimation

Zirui Wang, Shuda Li, Henry Howard-Jenkins, +2

EngineeringMachine LearningDepth Map3D Computer VisionImage Analysis +14

On Negative Interference in Multilingual Models: Findings and A Meta-Learning Treatment

Zirui Wang, Zachary C. Lipton, Yulia Tsvetkov

NTIRE 2021 Challenge on Perceptual Image Quality Assessment

Jinjin Gu, Haoming Cai, Chao Dong, +47

Ntire 2021Enhancement WorkshopMachine VisionMachine LearningImage Analysis +12

Reveal: Retrieval-Augmented Visual-Language Pre-Training with Multi-Source Multimodal Knowledge Memory

Ziniu Hu, Ahmet İşcen, Chen Sun, +6

Artificial IntelligenceNatural Language ProcessingLarge-scale MemoryMultimodal LlmEngineering +12

Direct-PoseNet: Absolute Pose Regression with Photometric Consistency

Shuai Chen, Zirui Wang, Victor Adrian Prisacariu

2021 International Conference on 3D Vision (3DV)

EngineeringMachine LearningHuman Pose Estimation3D Pose Estimation3D Computer Vision +15