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

박 성준

About Posts
[CVPR2023] Finetune like you pretrain: Improved finetuning of zero-shot vision models
  • Posted on: 04/28/2025 –
  • Comments: 10 Comments
[CVPR 2019] Learning a Unified Classifier Incrementally via Rebalancing
  • Posted on: 04/14/2025 –
  • Comments: 2 Comments
[NIPS2016] Unifying Count-Based Exploration and Intrinsic Motivation
  • Posted on: 04/07/2025 –
  • Comments: 2 Comments
[CVPR2025] Enhancing Vision-Language Compositional Understanding with Multimodal Synthetic Data
  • Posted on: 03/17/2025 –
  • Comments: 8 Comments
[CVPR2023]Exploring the Effect of Primitives for Compositional Generalization in Vision-and-Language
  • Posted on: 02/24/2025 –
  • Comments: 8 Comments
[ECCV2024]Training-free Video Temporal Grounding using Large-scale Pre-trained Models
  • Posted on: 02/16/2025 –
  • Comments: 2 Comments
[CVPR2022]Compositional Temporal Grounding with Structured Variational Cross-Graph Correspondence Learning
  • Posted on: 01/20/2025 –
  • Comments: 4 Comments
[NIPS2018] How Does Batch Normalization Help Optimization?
  • Posted on: 01/13/2025 –
  • Comments: 7 Comments
[박성준] 2024년을 마무리하며
  • Posted on: 12/29/2024 –
  • Comments: No Comments
[CVPR 2022] Incorporating Semi-Supervised and Positive-Unlabeled Learning for Boosting Full Reference Image Quality Assessment
  • Posted on: 12/09/2024 –
  • Comments: 2 Comments
Newer Posts 1 2 3 4 5 Older Posts

Conference Deadline

NEW POST

  • [arxiv 2025.02] SOFAR: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation
  • [arXiv 2024] Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG
  • [ArXiv 2025]Accurate and efficient Zero-shot 6D pose estimation with frozen foundation models
  • [NIPS2023] Self-Chained Image-Language Model for Video Localization and Question Answering
  • [CVPR 2023] Feature Aggregated Queries for Transformer-based Video Object Detectors

New Comment

  1. 박 성준 on [NIPS2023] Self-Chained Image-Language Model for Video Localization and Question Answering09/09/2025

    안녕하세요. 현우님 좋은 댓글 감사합니다. 네, 현우님이 댓글에 남겨주신 것처럼 Table 3에서 A와 B는 샘플링하는 프레임수가 32개와 4개로 sparse하게 샘플링했을…

  2. 신 인택 on [ICLR2024]CLIPSELF : VISION TRANSFORMER DISTILLS ITSELF FOR OPEN-VOCABULARY DENSE PREDICTION09/09/2025

    안녕하세요 현우님 답글 감사합니다. 질문에 대한 답변을 드리자면 1. 아래 [1] 논문기반으로 답변드리면 마지막 블록의 self-attention 을 제거하는 이유는 CLS…

  3. 박 성준 on [NIPS2023] Self-Chained Image-Language Model for Video Localization and Question Answering09/09/2025

    안녕하세요. 황유진 연구원님 좋은 댓글 감사합니다. 키프레임의 경우 저자는 단순하게 자연어 쿼리와의 유사도를 기반으로 추출하고 있습니다. 다만, BLIP-2 자체에도 이미지-텍스트…

  4. 신 인택 on [ICLR2024]CLIPSELF : VISION TRANSFORMER DISTILLS ITSELF FOR OPEN-VOCABULARY DENSE PREDICTION09/09/2025

    안녕하세요 우진님 답변 감사합니다. self-distillation 과정을 다른 논문들을 읽어본 것은 아니라 일반적인 설정 기준은 모르겠으나, 해당 논문 기준에서는 같은 구조에서…

  5. 신 인택 on [ICLR2024]CLIPSELF : VISION TRANSFORMER DISTILLS ITSELF FOR OPEN-VOCABULARY DENSE PREDICTION09/09/2025

    안녕하세요 재연님 답글 감사합니다. 1. 해당 부분은 논문에 구체적으로 설명이 없고 코드도 제공되지 않았었는데, github issue 에서 저자가 공개한 코드기반으로…

  • 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