vix.ing · top · new · best · stats · spec

Kim, Seonhoon

  1. Self-supervised pre-training and contrastive representation learning for multiple-choice video QA
    2020/09/17 by Seonhoon Kim, Seohyeong Jeong, Kim, Seonhoon +7 · 2 citations
    Computer Science · #Advanced Image and Video Retrieval Techniques #Computation and Language (cs.CL) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Multimodal Machine Learning Applications
  2. Self-Distilled Self-Supervised Representation Learning
    2021/11/25 by Jiho Jang, Jang, Jiho, Seonhoon Kim +8 · 2 citations
    Computer Science · #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Multimodal Machine Learning Applications
  3. Unifying Vision-Language Representation Space with Single-tower Transformer
    2022/11/21 by Jiho Jang, Chaerin Kong, Jang, Jiho +7 · 2 citations
    Computer Science · #Computation and Language (cs.CL) #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Multimodal Machine Learning Applications #Natural Language Processing Techniques
  4. Semantic Sentence Matching with Densely-connected Recurrent and Co-attentive Information
    2018/05/29 by Seonhoon Kim, Kim, Seonhoon, In-Ho Kang +3 · 2 citations
    Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Multimodal Machine Learning Applications #Natural Language Processing Techniques #Topic Modeling
  5. What Changes Can Large-scale Language Models Bring? Intensive Study on\n HyperCLOVA: Billions-scale Korean Generative Pretrained Transformers
    2021/09/09 by Boseop Kim, HyoungSeok Kim, Kim, Boseop +70 · 1 citation
    Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Speech Recognition and Synthesis #Topic Modeling