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

홍 주영

About Posts
[CVPR 2021] Multiple Instance Active Learning for Object Detection
  • Posted on: 04/29/2024 –
  • Comments: 3 Comments
[CVPR 2024] ImageNet-D: Benchmarking Neural Network Robustness on Diffusion Synthetic Object
  • Posted on: 03/31/2024 –
  • Comments: 5 Comments
[ICCV 2019] Active Learning for Deep Detection Neural Networks
  • Posted on: 03/03/2024 –
  • Comments: 2 Comments
2023년을 마무리하며 – 홍주영
  • Posted on: 01/08/2024 –
  • Comments: No Comments
[ICML 2023] Towards Controlled Data Augmentations for Active Learning
  • Posted on: 09/11/2023 –
  • Comments: 1 Comment
[IEEE Transactions] Cost-Effective Active Learning for Deep Image Classification
  • Posted on: 08/27/2023 –
  • Comments: 6 Comments
[CVPR 2023] MarginMatch: Improving Semi-Supervised Learning with Pseudo-Margins
  • Posted on: 07/30/2023 –
  • Comments: 4 Comments
[CVPR 2023] Coreset Sampling from Open-Set for Fine-Grained Self-Supervised Learning
  • Posted on: 07/16/2023 –
  • Comments: 6 Comments
< 2023년도 상반기를 정리한다 >
  • Posted on: 07/02/2023 –
  • Comments: 1 Comment
[CVPRW 2021] A mathematical Analysis of Learning Loss for Active Learning
  • Posted on: 06/24/2023 –
  • Comments: 8 Comments
Newer Posts 1 2 3 4 5 … 10 11 Older Posts

Conference Deadline

NEW POST

  • [CoRL 2024] 3D Diffuser Actor: Policy Diffusion with 3D Scene Representations
  • [CVPR 2025] Unbiased Video Scene Graph Generation via Visual and Semantic Dual Debiasing
  • [TPAMI 2018] SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition
  • [NeurIPS 2024] Introspective Planning: Aligning Robots’ Uncertainty with Inherent Task Ambiguity
  • [ECCV 2024]FreeZe: Training-free zero-shot 6D pose estimation with geometric and vision foundation models

New Comment

  1. 허 재연 on [CVPR 2025] Universal Scene Graph Generation07/16/2025

    1. 저도 논문을 처음 읽을 때 object associator에서 matrix에 CNN을 사용한 부분이 눈에 띄었는데요, 본문에는 'redundant noise를 효과적으로 필터링 해주면서…

  2. 허 재연 on [CVPR 2025] Universal Scene Graph Generation07/15/2025

    기존에는 image 기반 scene graph가 활발하게 연구됐는데, 최근에는 video, 3d, depth와 같은 다른 모달리티에도 확장하려는 시도가 활발합니다. 아직 성능이 제한적이기는…

  3. 허 재연 on [ICLR 2022] DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR07/15/2025

    안녕하세요, 몇달 전에 작성한 논문이라 가물가물하지만.. 다시 읽어보니 CA 모듈에서 쿼리와 키를 내적으로 계산해 query-to-feature 유사도를 구하면(내적은 유사도를 구하는 연산이므로)…

  4. 허 재연 on [CVPR 2025] Unbiased Video Scene Graph Generation via Visual and Semantic Dual Debiasing07/15/2025

    attention, spatial, contacting 카테고리의 예측이라 함은, 3가지 다른 특성을 가진 별도의 relation embedding을 병렬로 예측해서 활용한다고 생각하시면 됩니다. Figure 2에서…

  5. 안 우현 on [ICLR 2025]DEPTH PRO: Sharp Monocular Metric Depth In Less Than a Second07/15/2025

    안녕하세요 재연님 읽어주셔서 감사합니다. Depth pro의 중요한 컨트리뷰션 중 하나로 depth boundaries 를 평가하기 위한 새로운 지표(metric) 세트를 제안하는데 이를…

  • 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