CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification

Chun-Fu Richard Chen, Quanfu Fan, Rameswar Panda

2021 IEEE/CVF International Conference on Computer Vision (ICCV)

Convolutional Neural NetworkTransformer ModelsMachine VisionMachine LearningImage Analysis +13

A closer look at Faster R-CNN for vehicle detection

Quanfu Fan, Lisa M. Brown, John Smith

Convolutional Neural NetworkMachine VisionMachine LearningVehicle DetectionEngineering +6

Curve Matching, Time Warping, and Light Fields: New Algorithms for Computing Similarity between Curves

Alon Efrat, Quanfu Fan, Suresh Venkatasubramanian

Journal of Mathematical Imaging and Vision

Geometric ModelingLight FieldsImage AnalysisMachine VisionData Science +12

Deep Analysis of CNN-based Spatio-temporal Representations for Action Recognition

Chun-Fu Richard Chen, Rameswar Panda, Kandan Ramakrishnan, +4

EngineeringMachine LearningAction Quality AssessmentVideo InterpretationImage Analysis +14

Structured Adversarial Attack: Towards General Implementation and Better Interpretability

Kaidi Xu, Sijia Liu, Pu Zhao, +6

arXiv (Cornell University)

EngineeringMachine LearningAdversarial AttackInformation SecurityAutoencoders +14

RegionViT: Regional-to-Local Attention for Vision Transformers

Chun-Fu Chen, Rameswar Panda, Quanfu Fan

arXiv (Cornell University)

Multimodal LlmMachine VisionImage AnalysisEngineeringVisual Grounding +13

Temporal Sequence Modeling for Video Event Detection

Yu Cheng, Quanfu Fan, Sharath Pankanti, +1

EngineeringMachine LearningVideo ProcessingVideo SummarizationVideo Retrieval +17

More Is Less: Learning Efficient Video Representations by Big-Little Network and Depthwise Temporal Aggregation

Quanfu Fan, Chun-Fu Chen, Hilde Kuehne, +2

arXiv (Cornell University)

Convolutional Neural NetworkEngineeringMachine LearningBig-little NetworkVideo Retrieval +17

Big-Little Net: An Efficient Multi-Scale Feature Representation for Visual and Speech Recognition

Chun-Fu Chen, Quanfu Fan, Neil Mallinar, +2

arXiv (Cornell University)

Convolutional Neural NetworkEngineeringMachine LearningSpeech RecognitionImage Analysis +18

AdaMML: Adaptive Multi-Modal Learning for Efficient Video Recognition

Rameswar Panda, Chun-Fu Richard Chen, Quanfu Fan, +4

2021 IEEE/CVF International Conference on Computer Vision (ICCV)

EngineeringMachine LearningAction Recognition (Movement Science)Action Recognition (Computer Vision)Multimodal Learning +14