DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation

Hanchao Li, Pengfei Xiong, Haoqiang Fan, +1

Convolutional Neural NetworkScene AnalysisEngineeringMachine LearningImage Sequence Analysis +14

Practical Stereo Matching via Cascaded Recurrent Network with Adaptive Correlation

Jiankun Li, Peisen Wang, Pengfei Xiong, +6

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

EngineeringMachine LearningStereo ImagingDepth MapPractical Stereo Matching +16

Pyramid Attention Network for Semantic Segmentation

Hanchao Li, Pengfei Xiong, Jie An, +1

arXiv (Cornell University)

Convolutional Neural NetworkEngineeringMachine LearningPyramid Attention NetworkAttention +14

CLIP2Video: Mastering Video-Text Retrieval via Image CLIP

Han Fang, Pengfei Xiong, Luhui Xu, +1

arXiv (Cornell University)

EngineeringMachine LearningVideo SummarizationVideo RetrievalVideo Interpretation +16

Deep Fusion Network for Image Completion

Xin Hong, Pengfei Xiong, Renhe Ji, +1

EngineeringMachine LearningMulti-image FusionStyle TransferDeep Fusion Network +17

DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation

Hanchao Li, Pengfei Xiong, Haoqiang Fan, +1

arXiv (Cornell University)

Convolutional Neural NetworkScene AnalysisEngineeringMachine LearningImage Sequence Analysis +14

Video-Text as Game Players: Hierarchical Banzhaf Interaction for Cross-Modal Representation Learning

Peng Jin, Jinfa Huang, Pengfei Xiong, +5

Artificial IntelligenceGame AiEngineeringMachine LearningMultimodal Learning +21

DIP: Deep Inverse Patchmatch for High-Resolution Optical Flow

Zihua Zheng, Ni Nie, Zhi Ling, +4

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Convolutional Neural NetworkMachine VisionImage AnalysisData ScienceMachine Learning +13

Cross-lines laser aided machine vision in tube-to-tubesheet welding for welding height control

Ting Lei, Wenbin Wang, Youmin Rong, +2

Optics & Laser Technology

Geometric ModelingCross-lines LaserAdvanced Laser ProcessingMachine VisionWelding Process +2

RepGhost: A Hardware-Efficient Ghost Module via Re-parameterization

Chengpeng Chen, Zichao Guo, Haien Zeng, +2

arXiv (Cornell University)