Welcome to MVP LAB
Image and Video Pattern Recognition Lab.
School of Electrical and Electronic Engineering, Yonsei University, Seoul, Korea
Recent Publications
- M. Cho et al. Relational Deep Feature Learning for Heterogeneous Face Recognition, IEEE TIFS, Accepted
- S. Cho et al. CRVOS: Clue Refining Network for Video Object Segmentation, IEEE ICIP, Oct 2020
- S. Woo et al. False Positive Removal for 3D Vehicle Detection with Penetrated Point Classifier, IEEE ICIP, Oct 2020
- S. Lee et al. Extrapolative-Interpolative Cycle-Consistency Learning for Video Frame Extrapolation, IEEE ICIP, Oct 2020
- Y. Ban et al. Protuberance of depth: Detecting interest points from a depth image, CVIU, May 2020
- H. Bae et al. Non-Visual to Visual Translation for Cross-Domain Face Recognition, IEEE Access, Mar 2020
- H. Lee et al. AdaCoF: Adaptive Collaboration of Flows for Video Frame Interpolation, IEEE CVPR, Jun 2020
- T. Kim et al. SF-CNN: A Fast Compresssion Artifacts Removal via Spatial-to-Frequency Convolutional Neural Networks, IEEE ICIP, Sep 2019
- M. Cho et al. N-RPN: Hard Example Learning for Region Proposal Networks, IEEE ICIP, Sep 2019
- M. Cho et al. NIR-to-VIS Face Recognition via Embedding Relations and Coordinates of the Pairwise Features, IAPR ICB, Jun 2019
- M. Lee et al. Sampling Operator to Learn the Scalable Correlation Filter for Visual Tracking, IEEE Access, Jan 2019
- E. Song et al. CarvingNet: Content-Guided Seam Carving using Deep Convolution Neural Network, IEEE Access, Dec 2018
- H. Lee et al. CollaboNet: Collaboration of Generative Models by Unsupervised Classification, IEEE ICIP, Oct 2018
- E. Song et al. AHD: Thermal-Image Based Adaptive Hand Detection for Enhanced Tracking System, IEEE Access, Mar 2018
- J. Choi et al. L-Tree: A Local-Area-Learning-Based Tree Induction Algorithm for Image Classification, Sensors, Jan. 2018
Stats
SCI(E) Papers
57
Finished Projects
118
Patents
86
Graduated Members
30
Research Area
| Scene Understanding |
| Scene Understanding consists of detection, tracking and recognition of the general objects in various environment. By understanding the spatiotemporal and semantic relationship in between the objects, object and scene can be modeled and reconstructed in 3D. Based on the understanding of the scene and the object, our researches can be applied to real-time applications such as Autonomous Driving and Surveillance systems. |
| Human Analysis |
| Human Analysis is to detect, track and recognize the features by analyzing the action and behavior of the people including face, hands and the entire body. Based on these recognition and detection, the extracted features can be utilized for landmark and pose estimation and gesture recognition,Furthermore, human behavior can be restored from analyzing the emotions. Our researches of the Human Analysis can be applied to various applications such as Human-Computer and Human-Mobile Device Interaction. |
| Image/Video Processing |
| Image/Video Processing analyzes the low-level features of the multimedia. It plays an important role for Scene Understanding and Human Analysis, by taking pre-processing and post processing. From analyzing the correlation of the images, having various modality, it enhances and restores the images. Our researches of the Image/Video Processing are applied to Image Enhancement and Video Coding/Streaming. |