Class-incremental Learning via Deep Model Consolidation

Junting Zhang, Jie Zhang, Shalini Ghosh, +4

Incremental LearningConvolutional Neural NetworkEngineeringMachine LearningSequential Learning +17

Talking Face Generation by Conditional Recurrent Adversarial Network

Yang Song, Jingwen Zhu, Dawei Li, +2

EngineeringMachine LearningBiometricsVideo InterpretationSpeech Recognition +17

LCANet: End-to-End Lipreading with Cascaded Attention-CTC

Kai Xu, Dawei Li, Nick Cassimatis, +1

Natural Language ProcessingConvolutional Neural NetworkEngineeringMachine LearningMulti-speaker Speech Recognition +13

RILOD

Dawei Li, Shalini Ghosh, Jingwen Zhu, +2

Convolutional Neural NetworkMachine VisionImage AnalysisData ScienceMachine Learning +12

Multi-YOLOv8: An infrared moving small object detection model based on YOLOv8 for air vehicle

Shizun Sun, Bo Mo, Junwei Xu, +3

Neurocomputing

EngineeringVideo ProcessingSmall Object DetectionAir VehicleImage Classification +15

DeepRebirth: Accelerating Deep Neural Network Execution on Mobile Devices

Dawei Li, Xiaolong Wang, Deguang Kong

Proceedings of the AAAI Conference on Artificial Intelligence

EngineeringMachine LearningMobile DevicesComputer ArchitectureSparse Neural Network +14

DeepCham: Collaborative Edge-Mediated Adaptive Deep Learning for Mobile Object Recognition

Dawei Li, Theodoros Salonidis, Nirmit Desai, +1

Convolutional Neural NetworkEngineeringMachine LearningImage AnalysisData Science +15

Class-incremental Learning via Deep Model Consolidation

Junting Zhang, Jie Zhang, Shalini Ghosh, +4

arXiv (Cornell University)

Data AugmentationDeep Neural NetworksMachine VisionMachine LearningData Science +13

DeepRebirth: Accelerating Deep Neural Network Execution on Mobile Devices

Dawei Li, Xiaolong Wang, Deguang Kong

arXiv (Cornell University)

Deep Neural NetworksEngineeringMachine LearningHardware AccelerationMobile Devices +13

Talking Face Generation by Conditional Recurrent Adversarial Network

Yang Song, Jingwen Zhu, Dawei Li, +2

arXiv (Cornell University)

Speech RecognitionMachine LearningComputer VisionEngineeringGenerative Adversarial Network +13