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

황 유진

About Posts
Contrastive Learning of Image Representations with Cross-Video Cycle-Consistency
  • Posted on: 05/16/2021 –
  • Comments: 3 Comments
Weakly Supervised Action Selection Learning in Video
  • Posted on: 05/09/2021 –
  • Comments: 1 Comment
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks
  • Posted on: 05/02/2021 –
  • Comments: 4 Comments
Consistency-based Active Learning for Object Detection
  • Posted on: 04/05/2021 –
  • Comments: No Comments
ACTION-Net: Multipath Excitation for Action Recognition
  • Posted on: 03/22/2021 –
  • Comments: No Comments
Circle Loss: A Unified Perspective of Pair Similarity Optimization
  • Posted on: 02/28/2021 –
  • Comments: 4 Comments
Only Time Can Tell: Discovering Temporal Data for Temporal Modeling
  • Posted on: 02/08/2021 –
  • Comments: 1 Comment
FRAME ATTENTION NETWORKS FOR FACIAL EXPRESSION RECOGNITION IN VIDEOS
  • Posted on: 01/05/2021 –
  • Comments: 2 Comments
What Makes a Video a Video: Analyzing Temporal Information in Video Understanding Models and Datasets
  • Posted on: 01/03/2021 –
  • Comments: No Comments
SMART Frame Selection for Action Recognition
  • Posted on: 12/27/2020 –
  • Comments: 2 Comments
Newer Posts 1 2 … 10 11 12 13 14 Older Posts

Conference Deadline

NEW POST

  • [ICCV 2023] Dynamic Token Pruning in Plain Vision Transformers for Semantic Segmentation
  • [arXiv2025] VideoRAG: Retrieval-Augmented Generation over Video Corpus
  • 2025 상반기 회고
  • [arxiv 2025] LBAP: Improved Uncertainty Alignment of LLM Planners using Bayesian Inference
  • [ICCV 2025] SVTRv2: CTCBeats Encoder-Decoder Models in Scene Text Recognition

New Comment

  1. 류 지연 on [ICCV 2025] SVTRv2: CTCBeats Encoder-Decoder Models in Scene Text Recognition08/01/2025

    1. CTC 기반의 텍스트 인식 모델의 학습 과정에 대해 설명을 드리면 대답이 될 것 같네요! 입력된 텍스트 이미지[H x W…

  2. 류 지연 on [TPAMI 2018] SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition08/01/2025

    얘기해주신대로 두 경우 semantic module을 통해 시각 특징으로 semantic information을 생성하고 이는 LM의 워드 임베딩과 유사하도록 학습된다는 건 동일합니다. GRU라는…

  3. 류 지연 on [TPAMI 2018] SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition08/01/2025

    GRU는 순환신경망(RNN) 중 하나인데요 입력 시퀀스에 대해서 순차적으로 학습할 때 게이트란 걸 사용해 이전 정보를 얼마나 취하고 버릴지를 선택할 수…

  4. 안 우현 on Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation07/30/2025

    안녕하세요 재연님, 좋은 댓글 감사드립니다. 주신 질문이 단순한 기술 구현을 넘어서 왜 Detection 과 Segmentation을 명시적으로 분리해서 학습하고 예측하려고 하는지Perception…

  5. 안 우현 on Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation07/30/2025

    안녕하세요 지연님 댓글 감사합니다. contribution 3번에 적어놓은 부분에 대한 질문을 해주신 것 같습니다! 일단 답변을 드리자면 맞습니다. 일단 사전학습으로 사용되는…

  • 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