HomeAboutMeBlogGuest
© 2025 Sejin Cha. All rights reserved.
Built with Next.js, deployed on Vercel
장지원 페이지/
DGIST CV lab (My page)
DGIST CV lab (My page)/
📒
Paper Review
📒

Paper Review

 
📌
선배님 추천 논문
  • DETR
  • Mask2Former
  • MinVIS
  • VITA
  • DVIS
 
태그
이름
요약
발표 일
subtask
AI
LoRA: Low-Rank Adaptation of Large Language Models
전이학습: LoRA
Jun 30, 2024
PEFT
AI
Explainable Conversational Question Answering over Heterogeneous Sources via Iterative Graph Neural Networks
반복 그래프 NN(GNN)을 통한 설명 가능한 QnA 대화
Jun 7, 2024
Prompting
AI
Tree of Thoughts: Deliberate Problem Solving with Large Language Models
ToT라는 Prompting 방식에 대한 설명
May 31, 2024
Prompting
AI
Transformers Learn In-Context by Gradient Descent
트랜스포머를 GD로 설명할 수 있다
Mar 31, 2024
Loss
CV
General Object Foundation Model for Images and Videos at Scale
RVOS: GLEE: 객체 기반 foundation model → referring은 주로 foundation model을 활용해서 성능을 내는 것 같다.
Dec 30, 2024
RVOS
AI
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
SSM: Mamba: 계산 효율적인 모델
Dec 31, 2024
Model
CV
Masked attention Mask Transfomer for Universial Image Segmentation
Mask2Fomer: mask attention을 이용한 모델
Jan 3, 2025
Segmentation
CV
End-to-End Object Detection with Transformers
DETR: 병렬 transformer 구조를 활용한 segmentation 아키텍쳐
Dec 30, 2024
Segmentation
CV
MinVIS: A Minimal Video Instance Segmentation Framework without Video-based Training
비디오에서의 인스턴스 세그멘테이션
Jan 3, 2025
VIS
CV
VITA: Video Instance Segmentation via Object Token Association
offline 방식 기반 VOS: video query 사용
Jan 6, 2025
VIS
CV
DVIS: Decoupled Video Instance Segmentation Framework
VIS를 segmentation, tracking, refining 세 단계로 쪼갠다.
Jan 7, 2025
VIS
CV
CTVIS: Consistent Training for Online Video Instance Segmentation
train과 test에서 일관적인 contrastive learning을 하기 위한 아키텍쳐
Jan 10, 2025
VIS
CV
MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions
‘동작’에 좀 더 초점을 맞출 수 있는 데이터 셋 제작 및 RVOS method 제안
Jan 16, 2025
RVOS
CV
Language as Queries for Referring Video Object Segmentation
RVOS task: 여기서는 text 임베딩으로 input query를 생성한다
Jan 15, 2025
RVOS
CV
A Generalized Framework for Video Instance Segmentation
GenVIS: clip을 휴릭스틱한 방법 없이 처리하는 아키텍쳐
Jan 14, 2025
RVOS
CV
Context-Aware Video Instance Segmentation
CAVIS: context aware VIS: 윤곽 정보를 통해서 맥락을 알아차리는 아키텍쳐
Jan 13, 2025
VIS
CV
SAMWISE: Infusing wisdom in SAM2 for Text-Driven Video Segmentation
RVOS를 스트리밍에서 적용할 수 있게 하는 연구: SAM2 활용
Jan 15, 2025
Segmentation
CV
SAM2: Segment Anything in Images and Videos
Segments anyting2: 비디오에서도 일반화 할 수 있는 SAM 모델
Jan 15, 2025
Segmentation
bio
Vision: A Computational Investigation into the Human Representation and Processing of Visual Information
인간의 시각 처리 방법에 관한 논문
Jan 16, 2025
Vision
CV
CLIP-Driven Universal Object Segmentation
CLIP을 활용한 segmentation
Jan 16, 2025
Segmentation
CV
O2VIS:OCCUPANCY-AWARE OBJECT ASSOCIATION FOR TEMPORALLY CONSISTENT VIDEO INSTANCE SEG MENTATION
Occupancy를 활용한 VIS
Jan 16, 2025
VIS
CV
Towards Ground-truth-free Evaluation of Any Segmentation in Medical Images∗
EvanySeg
Oct 22, 2025
RCA(reverse classification accuracy)
CV
Conformal In-Context Reverse Classification Accuracy: Efficient Estimation of Segmentation Quality with Statistical Guarantees
RCA
Oct 21, 2025
RCA(reverse classification accuracy)
CV
ReferDINO: Referring Video Object Segmentation with Visual Grounding Foundations
DINO backbone을 사용한 RVOS
Sep 30, 2025
RVOS
CV
MPG-SAM2: Adapting SAM2withMaskPriors and Global Context for Referring Video Object Segmentation
SAM2 활용한 RVOS
Sep 26, 2025
RVOS
RL
CV
Enhancing SAM with Efficient Prompting and Preference Optimization for Semi-supervised Medical Image Segmentation
DPO를 활용한 SAM 미세 조정
Sep 17, 2025
Alignment
RL
CV
SAMPO:Visual Preference Optimization for Intent-Aware Segmentation with Vision Foundation Models
VFM alignment 논문 (RLHF 활용)
Sep 15, 2025
Vision
AI
Attention is All You Need
트랜스포머
Jul 9, 2025
Model
Memo…