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

김 형준

About Posts
[2021 ICML] What Makes for End-to-End Object Detection?
  • Posted on: 10/31/2021 –
  • Comments: 6 Comments
[2021 ICCV Workshop] TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarios
  • Posted on: 10/21/2021 –
  • Comments: 2 Comments
YOLOX: Exceeding YOLO Series in 2021
  • Posted on: 10/16/2021 –
  • Comments: 1 Comment
Protected: [2021 AAAI Under Review] Pay Attention to Spatial Alignment for RGB-Thermal Object Detection
  • Posted on: 10/10/2021 –
  • Comments: Enter your password to view comments.
YOLO 시리즈 1~3 리뷰
  • Posted on: 10/03/2021 –
  • Comments: 5 Comments
Protected: [RA-L ICRA 2022] BAANet: Learning Bi-directional Adaptive Attention Gates for Multispectral Pedestrian Detection
  • Posted on: 09/26/2021 –
  • Comments: Enter your password to view comments.
[2021 AIRE] Vision-based Robotic Grasping from Object Localization, Pose Estimation, Grasp Detection to Motion Planning: A Review
  • Posted on: 09/19/2021 –
  • Comments: No Comments
[2021 IEEE TNNLS] Weakly Aligned Feature Fusion for Multimodal Object Detection
  • Posted on: 09/12/2021 –
  • Comments: 6 Comments
[2021 ScienceDirect] Adaptive spatial pixel-level feature fusion network for multispectral pedestrian detection
  • Posted on: 09/05/2021 –
  • Comments: 2 Comments
[Sensors 2021] Attention Fusion for One-Stage Multispectral Pedestrian Detection
  • Posted on: 08/29/2021 –
  • Comments: 4 Comments
Newer Posts 1 2 3 4 5 … 7 8 Older Posts

Conference Deadline

NEW POST

  • [CoRL 2025(Oral)] SAVOR: Skill Affordance Learning from Visuo-Haptic Perception for Robot-Assisted Bite Acquisition
  • [IROS 2025] Empirical Analysis of Sim-and-Real Cotraining of Diffusion Policies for Planar Pushing from Pixels
  • [ArXiv 2025] VLA-0: Building State-of-the-Art VLAs with Zero Modification
  • [ICRA 2025] HeLiOS: Heterogeneous LiDAR Place Recognition via Overlap-based Learning and Local Spherical Transformer
  • [ICCV 2023] Progressive Spatio-Temporal Prototype Matching for Text-Video Retrieval

New Comment

  1. 김 영규 on [IROS 2025] Empirical Analysis of Sim-and-Real Cotraining of Diffusion Policies for Planar Pushing from Pixels10/20/2025

    안녕하세요 태주님 댓글 감사합니다. 답변을 드리자면, A1. 저자가 real data 수를 바꿔가며 실험을 진행할 때, Real data가 150개일땐 Real data…

  2. 김 영규 on [IROS 2025] Empirical Analysis of Sim-and-Real Cotraining of Diffusion Policies for Planar Pushing from Pixels10/20/2025

    안녕하세요 석준님 댓글 감사합니다. Ablation에는 ‘sim 데이터와 real 데이터를 이렇게 세밀하게 조합하여 학습을 하면 가장 효과적이다~’ 에 대해서도 실험을 진행해본…

  3. 홍 주영 on [ICCV 2023] Progressive Spatio-Temporal Prototype Matching for Text-Video Retrieval10/20/2025

    네, 논문에서는 “텍스트가 요구하는 세분화 수준(객체 vs 이벤트)”을 개별적으로 구분하거나 동적으로 조정하지 않습니다. 모든 텍스트 쿼리에 대해 두 수준(객체-구, 이벤트-문장)을…

  4. 김 태주 on [ArXiv 2025] VLA-0: Building State-of-the-Art VLAs with Zero Modification10/20/2025

    Q1. 액션을 텍스트로 반환하는 능력 자체는 논문에 있는 3가지 스킬로 어느정도 구현이 됐다고 생각하고, 이 논문의 핵심중에 하나인 것 같습니다.…

  5. 김 태주 on [ArXiv 2025] VLA-0: Building State-of-the-Art VLAs with Zero Modification10/20/2025

    Q1. 연속적인 행동 값을 정해진 정수 범위로 정규한다는 것이 궁금합니다. A1. 정확한 구현 방법에 대해서는 코드가 공개된 시점에서 밝혀질 것…

  • 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