메뉴 건너뛰기
.. 내서재 .. 알림
소속 기관/학교 인증
인증하면 논문, 학술자료 등을  무료로 열람할 수 있어요.
한국대학교, 누리자동차, 시립도서관 등 나의 기관을 확인해보세요
(국내 대학 90% 이상 구독 중)
로그인 회원가입 고객센터 ENG
주제분류

추천
검색
질문

논문 기본 정보

자료유형
학술저널
저자정보
Mi-Gyeong Gwon (Konkuk University) Jinhee Kim (Konkuk University) Gi-Mun Um (Electronics and Telecommunications Research Institute) HeeKyung Lee (Electronics and Telecommunications Research Institute) Jeongil Seo (Electronics and Telecommunications Research Institute) Seong Yong Lim (Electronics and Telecommunications Research Institute) Seung-Jun Yang (Electronics and Telecommunications Research Institute) Wonjun Kim (Konkuk University)
저널정보
대한전자공학회 IEIE Transactions on Smart Processing & Computing IEIE Transactions on Smart Processing & Computing Vol.11 No.1
발행연도
2022.2
수록면
24 - 33 (10page)
DOI
10.5573/IEIESPC.2021.11.1.24

이용수

표지
📌
연구주제
📖
연구배경
🔬
연구방법
🏆
연구결과
AI에게 요청하기
추천
검색
질문

초록· 키워드

오류제보하기
Visual object tracking, one of the main topics in computer vision, aims to chase a target object in every frame of the video sequences. In particular, Siamese-based network architectures have been adopted widely for visual object tracking due to their correlation-based nature. On the other hand, the features encoded from the target template and the search image in Siamese branches still suffer from ambiguities, which are driven by complicated real-world environments, e.g., occlusions and rotations. This paper proposes the Siamese feedback network for robust object tracking. The key idea of the proposed method is to encode target-relevant features accurately via the feedback block, which is defined by a combination of attention and refinement modules. Specifically, interdependent features are extracted through self- and cross-attention operations. Subsequently, such re-calibrated features are refined in both spatial and channel-wise manner. Those are fed back to the input of the feedback block again via the feedback loop. This is desirable because the high-level semantic information guides the feedback block to learn more meaningful properties of the target object and its surroundings. The experimental results show that the proposed method outperforms the state-of-the-art Siamese-based methods with a gain of 0.72% and 1.69% for the expected average overlap on the VOT2016 and VOT2018 datasets, respectively. Overall, the proposed method is effective for visual object tracking, even with complicated real-world scenarios.

목차

Abstract
1. Introduction
2. Related Work
3. Proposed Method
4. Experimental Results
5. Conclusion
References

참고문헌 (28)

참고문헌 신청

함께 읽어보면 좋을 논문

논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!

이 논문의 저자 정보

이 논문과 함께 이용한 논문

최근 본 자료

전체보기

댓글(0)

0