BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models

Junnan Li, Dongxu Li, Silvio Savarese, +1

arXiv (Cornell University)

EngineeringMachine LearningFrozen Image EncoderFrozen Language ModelBootstrapping Language-image Pre-training +18

BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation

Junnan Li, Dongxu Li, Caiming Xiong, +1

arXiv (Cornell University)

EngineeringMachine LearningVision-language UnderstandingBootstrapping Language-image Pre-trainingNatural Language Processing +17

Word-level Deep Sign Language Recognition from Video: A New Large-scale Dataset and Methods Comparison

Dongxu Li, Cristian Rodriguez Opazo, Xin Yu, +1

Convolutional Neural NetworkEngineeringMachine LearningHuman Pose EstimationBiometrics +18

InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning

Wenliang Dai, Junnan Li, Dongxu Li, +6

arXiv (Cornell University)

Llm Fine-tuningEngineeringMachine LearningLarge-scale Pre-trainingLarge Language Model +16

Transferring Cross-Domain Knowledge for Video Sign Language Recognition

Dongxu Li, Xin Yu, Chenchen Xu, +2

EngineeringMachine LearningSign Language InterpretationSpeech RecognitionNatural Language Processing +19

Enhanced Spatio-Temporal Interaction Learning for Video Deraining: Faster and Better

Kaihao Zhang, Dongxu Li, Wenhan Luo, +2

IEEE Transactions on Pattern Analysis and Machine Intelligence

From Images to Textual Prompts: Zero-shot Visual Question Answering with Frozen Large Language Models

Jiaxian Guo, Junnan Li, Dongxu Li, +4

Artificial IntelligenceEngineeringMachine LearningNatural Language ProcessingLarge Language Models +15

TSPNet: Hierarchical Feature Learning via Temporal Semantic Pyramid for Sign Language Translation

Dongxu Li, Chenchen Xu, Xin Yu, +4

arXiv (Cornell University)

Sign Language TranslationMachine LearningEngineeringTemporal Semantic PyramidVideo Summarization +21

ARVo: Learning All-Range Volumetric Correspondence for Video Deblurring

Dongxu Li, Chenchen Xu, Kaihao Zhang, +5

DeblurringMachine VisionMachine LearningImage AnalysisEngineering +10

cosFormer: Rethinking Softmax in Attention

Zhen Qin, Weixuan Sun, Hui Deng, +6

arXiv (Cornell University)

Structured PredictionEngineeringMachine LearningMultilingual PretrainingVanilla Transformer +19