Skip to content

Robotics and Computer Vision Lab

AI in Sensing, AI in Perception, AI in Action

  • About
    • History
    • Photo
    • Admission
  • Members
  • Publications
    • Patents
  • X-Review
  • X-Diary
  • Peer Review

Profile

신 정민

About Posts
[NeurlIPS2021]TransGAN : Two Transformers Can Make One Strong GAN
  • Posted on: 05/16/2021 –
  • Comments: 2 Comments
Attention Is All You Need 2편
  • Posted on: 04/30/2021 –
  • Comments: 1 Comment
Attention Is All You Need 1편
  • Posted on: 04/26/2021 –
  • Comments: 2 Comments
[ICCV 2017] Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization
  • Posted on: 04/05/2021 –
  • Comments: 1 Comment
ALADIN: All Layer Adaptive Instance Normalization for Fine-grained Style Similarity
  • Posted on: 04/05/2021 –
  • Comments: No Comments
[CVPR2019] Hue-Net: Intensity-based Image-to-Image Translation with Differentiable Histogram Loss Functions
  • Posted on: 03/22/2021 –
  • Comments: No Comments
Real-time Facial Surface Geometry from Monocular Video on Mobile GPUs
  • Posted on: 03/14/2021 –
  • Comments: 4 Comments
[CVPR2017] Densely Connected Convolutional Networks
  • Posted on: 03/07/2021 –
  • Comments: No Comments
Boosting Structure Consistency for Multispectral and Multimodal Image Registration
  • Posted on: 02/22/2021 –
  • Comments: No Comments
StarGAN : Unified GAN for Multi-Domain Image-to-Image Translation
  • Posted on: 02/08/2021 –
  • Comments: 1 Comment
Newer Posts 1 2 … 10 11 12 … 14 15 Older Posts

Conference Deadline

NEW POST

  • [CVPR2025] Masking meets Supervision: A Strong Learning Alliance
  • [CVPR 2024] PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detection
  • [ICRA 2024] Universal Visual Decomposer: Long-Horizon Manipulation Made Easy
  • [CVPR 2025] DiscoVLA: Discrepancy Reduction in Vision, Language, and Alignment for Parameter-Efficient Video-Text Retrieval
  • [WACV 2024] DTrOCR: Decoder-only Transformer for Optical Character Recognition

New Comment

  1. 홍 주영 on [CVPR 2025] DiscoVLA: Discrepancy Reduction in Vision, Language, and Alignment for Parameter-Efficient Video-Text Retrieval07/04/2025

    좋은 포인트를 지적해주신 것 같네요. 말씀하신 내용처럼, DiscoVLA는 PImgAlign 모듈에서 멀티모달 LLM인 LLaVA-NeXT를 활용해 프레임 단위의 pseudo-caption을 생성하고, 이를 통해…

  2. 홍 주영 on [CVPR 2025] DiscoVLA: Discrepancy Reduction in Vision, Language, and Alignment for Parameter-Efficient Video-Text Retrieval07/04/2025

    좋은 질문 감사합니다. 말씀해주신 대로, DiscoVLA는 멀티모달 LLM인 LLaVA-NeXT를 활용해 프레임별 pseudo-caption을 생성하고 이를 정렬 학습에 활용하였습니다. 다만, 이 pseudo-caption의…

  3. 류 지연 on [WACV 2024] DTrOCR: Decoder-only Transformer for Optical Character Recognition07/02/2025

    안녕하세요. 질문 감사합니다. 1. 본 모델에서 학습 과정은 합성 데이터셋으로 사전학습하는 과정과 real 데이터셋으로 파인튜닝 단계로 나뉘는데 논문에서는 두 학습과정에서…

  4. 류 지연 on [WACV 2024] DTrOCR: Decoder-only Transformer for Optical Character Recognition07/01/2025

    안녕하세요 질문 남겨주셔서 감사합니다 논문에서는 CTR 데이터에 대한 결과와 비교하면서 STR의 경우 이미지 내 텍스트가 갖는 특징 자체가 보다 덜…

  5. 신 인택 on [CVPR2025] Masking meets Supervision: A Strong Learning Alliance07/01/2025

    안녕하세요 정민님 깔끔한 리뷰 감사합니다. 말씀하신 것처럼 약간 지도학습기반으로 다시 회귀하는 점이 장점이자 단점이라고 생각할 수 있을 것 같습니다. 제가…

  • Sign-in
  • RCV-Calendar
  • RCV-Github
  • Paper R/W
    • Arxiv
    • Deadline
    • Overleaf
  • Coding
    • OnlineJudge
    • Kaggle

포기하지 않는 강한 집념 만이 작은 차이를 만든다.

Design by SejongRCV