publications

2022

  1. One-Trimap Video Matting
    European Conference on Computer Vision (ECCV), Oct, 2022
    (Acceptance: 1650/5803 ≈ 28.4%)
  2. Video Object Segmentation using Kernelized Memory Network with Multiple Kernels
    Hongje Seong, Junhyuk Hyun, and Euntai Kim
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022 (Accepted)
    (IF: 24.314 in JCR2021)
  3. Indoor Place Category Recognition for a Cleaning Robot by Fusing a Probabilistic Approach and Deep Learning
    Soowook Choe*,  Hongje Seong*, and Euntai Kim
    IEEE Transactions on Cybernetics (TCYB), Aug, 2022
    (IF: 19.118 in JCR2021, * indicates equal contribution)
  4. Spatial-Channel Transformer for Scene Recognition
    Seunghyun Baik,  Hongje Seong, Youngjo Lee, and Euntai Kim
    International Joint Conference on Neural Networks (IJCNN), Jul, 2022
  5. Correlation Verification for Image Retrieval
    Seongwon LeeHongje SeongSuhyeon Lee, and Euntai Kim
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun, 2022
    (Acceptance: 342/8161 ≈ 4.2%)
      Oral Presentation  
  6. WildNet: Learning Domain Generalized Semantic Segmentation from the Wild
    Suhyeon LeeHongje SeongSeongwon Lee, and Euntai Kim
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun, 2022
    (Acceptance: 2067/8161 ≈ 25.3%)
  7. Content Swapping: A New Image Synthesis for Construction Sign Detection in Autonomous Vehicles
    Hongje Seong, Seunghyun Baik, Youngjo Lee, Suhyeon Lee, and Euntai Kim
    Sensors, May, 2022
    (IF: 3.847 in JCR2021)
  8. Iteratively Selecting an Easy Reference Frame Makes Unsupervised Video Object Segmentation Easier
    Youngjo Lee,  Hongje Seong, and Euntai Kim
    AAAI Conference on Artificial Intelligence (AAAI), Feb, 2022
    (Acceptance: 1349/9020 ≈ 15.0%)
  9. Graph-Based Point Tracker for 3D Object Tracking in Point Clouds
    Minseong Park,  Hongje Seong, Wonje Jang, and Euntai Kim
    AAAI Conference on Artificial Intelligence (AAAI), Feb, 2022
    (Acceptance: 1349/9020 ≈ 15.0%)

2021

  1. Adjacent Feature Propagation Network (AFPNet) for Real-Time Semantic Segmentation
    Junhyuk Hyun,  Hongje Seong, Sangki Kim, and Euntai Kim
    IEEE Transactions on Systems, Man, and Cybernetics: Systems (TSMC), 2021 (Accepted)
    (IF: 13.451 in JCR2020)
  2. Universal Pooling - A New Pooling Method for Convolutional Neural Networks
    Junhyuk Hyun,  Hongje Seong, and Euntai Kim
    Expert Systems With Applications (ESWA), Oct, 2021
    (IF: 6.954 in JCR2020)
  3. Hierarchical Memory Matching Network for Video Object Segmentation
    IEEE/CVF International Conference on Computer Vision (ICCV), Oct, 2021
    (Acceptance: 1617/6236 ≈ 25.9%)
  4. Improving Nighttime Object Detection by Generating Synthetic Nighttime Dataset from Daytime Dataset
    Youngjo Lee, Suhyeon LeeHongje Seong, and Euntai Kim
    International Conference on Control, Automation and Systems (ICCAS), Oct, 2021
      Best Poster Paper Award  
  5. Loop Closure Detection in Crowded Place
    Seongwon LeeHyungGi JoHongje Seong, and Euntai Kim
    IEEE Region 10 Symposium (TENSYMP), Aug, 2021
  6. Metric Learning in Mini-batch for Robust 6-DoF Camera Relocalization in Outdoor Environments
    Gyuhyeon Pak,  Hongje Seong, and Euntai Kim
    International Conference on Ubiquitous Robots (UR), Jun, 2021
  7. The Effective Method for 3D LiDAR Point Clouds Processing
    Youngjoo Kim,  Hongje Seong, Wonje Jang, and Euntai Kim
    International Conference on Ubiquitous Robots (UR), Jun, 2021
  8. Unsupervised Domain Adaptation for Semantic Segmentation by Content Transfer
    Suhyeon Lee, Junhyuk Hyun,  Hongje Seong, and Euntai Kim
    AAAI Conference on Artificial Intelligence (AAAI), Feb, 2021
    (Acceptance: 1692/7911 ≈ 21.4%)

2020

  1. FOSNet: An End-to-End Trainable Deep Neural Network for Scene Recognition
    Hongje Seong, Junhyuk Hyun, and Euntai Kim
    IEEE Access, Dec, 2020
    (IF: 3.745 in JCR2019)
  2. Kernelized Memory Network for Video Object Segmentation
    Hongje Seong, Junhyuk Hyun, and Euntai Kim
    European Conference on Computer Vision (ECCV), Aug, 2020
    (Acceptance: 1361/5025 ≈ 27.1%)
      3rd Place Award in DAVIS20 Challenge (CVPRW-DAVIS 2020)  
  3. Is Whole Object Information Helpful for Scene Recognition?
    Hongje Seong, Junhyuk Hyun, and Euntai Kim
    International Conference on Ubiquitous Robots (UR), Jun, 2020

2019

  1. Video Multitask Transformer Network
    Hongje Seong, Junhyuk Hyun, and Euntai Kim
    IEEE/CVF International Conference on Computer Vision Workshops (ICCVW-CoVieW), Oct, 2019
      4th Place in CoVieW19 Challenge  
  2. Partial Convolution for Scene Recognition
    Hongje Seong, Junhyuk Hyun, Seongwon Lee, and Euntai Kim
    International Conference on Control, Automation and Systems (ICCAS), Oct, 2019
  3. Scene Recognition via Object-to-Scene Class Conversion: End-to-End Training
    Hongje Seong, Junhyuk Hyun, Hyunbae Chang, Suhyeon Lee, Suhan Woo, and Euntai Kim
    International Joint Conference on Neural Networks (IJCNN), Jul, 2019

2018

  1. New Feature-level Video Classification via Temporal Attention Model
    Hongje Seong, Junhyuk Hyun, Suhyeon Lee, Suhan Woo, and Euntai Kim
    ACM International Conference on Multimedia Workshops (MMW-CoVieW), Oct, 2018
      2nd Place Award in CoVieW18 Challenge