[논문]ACP++: Action Co-Occurrence Priors for Human-Object Interaction Detection

Kim, Dong-Jin; Sun, Xiao; Choi, Jinsoo; Lin, Stephen; Kweon, In So

doi:10.1109/tip.2021.3113563

[해외논문] ACP++: Action Co-Occurrence Priors for Human-Object Interaction Detection 원문보기

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society, v.30, 2021년, pp.9150 - 9163

Kim, Dong-Jin (KAIST, School of Electrical and Computer Engineering, Daejeon, Republic of Korea) , Sun, Xiao (Visual Computing Group, Microsoft Research Asia, Beijing, China) , Choi, Jinsoo (KAIST, School of Electrical and Computer Engineering, Daejeon, Republic of Korea) , Lin, Stephen (Visual Computing Group, Microsoft Research Asia, Beijing, China) , Kweon, In So (KAIST, School of Electrical and Computer Engineering, Daejeon, Republic of Korea)

Abstract ▼ AI-Helper

A common problem in the task of human-object interaction (HOI) detection is that numerous HOI classes have only a small number of labeled examples, resulting in training sets with a long-tailed distribution. The lack of positive labels can lead to low classification accuracy for these classes. Towards addressing this issue, we observe that there exist natural correlations and anti-correlations among human-object interactions. In this paper, we model the correlations as action co-occurrence matrices and present techniques to learn these priors and leverage them for more effective training, especially on rare classes. The efficacy of our approach is demonstrated experimentally, where the performance of our approach consistently improves over the state-of-the-art methods on both of the two leading HOI detection benchmark datasets, HICO-Det and V-COCO.

참고문헌 (101)

Proc Int Conf Learn Represent (ICLR) Semi-supervised classification with graph convolutional networks kipf 2017
Proc Adv Neural Inf Process Syst (NeurIPS) Distribution aligning refinery of pseudo-label for imbalanced semi-supervised learning kim 2020
10.1109/CVPR.2019.00643
10.1007/978-3-030-58555-6_30
10.1007/978-3-030-01264-9_15
10.1109/CVPR.2017.215
10.1007/978-3-030-58589-1_43
arXiv 2010 03855 Dense relational image captioning via multi-task triple-stream networks kim 2020
10.1109/WACV.2018.00189
10.18653/v1/D19-1208
10.18653/v1/P16-1228
10.1007/978-3-030-58555-6_35
10.1109/CVPR.2011.5995543
arXiv 1505 04474 Visual semantic role labeling gupta 2015
10.1109/ICCV.2019.00977
No-Frills Pytorch Github gupta 2019
ArXiv 1503 02531 Distilling the knowledge in a neural network hinton 2015
10.1109/CVPR.2016.90
Proc AAAI Conf Artif Intell (AAAI) HCVRD: A benchmark for large-scale human-centered visual relationship detection zhuang 2018 7631
IEEE Trans Pattern Anal Mach Intell Significance of softmax-based features in comparison to distance metric learning-based features horiguchi 2020 42 1279

상세보기
10.1109/ICCV.2017.71
10.1109/CVPR.2016.96
10.1109/CVPR42600.2020.00056
Proc Eur Conf Comput Vis (ECCV) Microsoft COCO: Common objects in context lin 2014 740
10.1109/ICCV.2019.00207
10.3115/v1/D14-1162
arXiv 2106 05682 Distribution-aware semantics-oriented pseudo-label for imbalanced semi-supervised learning oh 2021
10.1109/CVPR.2014.119
Miller, George A.. WordNet : a lexical database for English. Communications of the ACM, vol.38, no.11, 39-41.

상세보기
10.1109/CVPR.2007.383272
10.1007/978-3-319-46448-0_51
10.1007/978-3-030-58568-6_15
Krishna, Ranjay, Zhu, Yuke, Groth, Oliver, Johnson, Justin, Hata, Kenji, Kravitz, Joshua, Chen, Stephanie, Kalantidis, Yannis, Li, Li-Jia, Shamma, David A., Bernstein, Michael S., Fei-Fei, Li. Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations. International journal of computer vision, vol.123, no.1, 32-73.

상세보기
10.1109/ICCV.2015.122
10.1109/WACV.2018.00048
10.1109/CVPR.2017.352
10.1109/CVPRW53098.2021.00175
10.5244/C.24.97
10.1007/978-3-319-46493-0_37
Delaitre, V., Fouhey, D.F., Laptev, I., Sivic, J., Gupta, A., Efros, A.A.. Scene Semantics from Long-Term Observation of People. Lecture notes in computer science, vol.7577, 284-298.

상세보기
Proc Adv Neural Inf Process Syst (NeurIPS) Learning person-object interactions for action recognition in still images delaitre 2011 1503
10.1109/ICCV.2017.142
10.1007/978-3-030-01246-5_21
10.1109/CVPR.2019.00370
10.1109/CVPR42600.2020.01018
Ladický, Ľubor, Russell, Chris, Kohli, Pushmeet, Torr, Philip H. S.. Inference Methods for CRFs with Co-occurrence Statistics. International journal of computer vision, vol.103, no.2, 213-225.

상세보기
Ladicky, L., Russell, C., Kohli, P., Torr, P.H.S.. Graph Cut Based Inference with Co-occurrence Statistics. Lecture notes in computer science, vol.6315, 239-253.

상세보기
Proc IEEE Conf Comput Vis Pattern Recognit (CVPR) ViP-CNN: A visual phrase reasoning convolutional neural network for visual relationship detection li 2017
10.1109/ICASSP.2011.5946600
10.1109/ICCV.2019.00956
10.1109/ICIP.2014.7026189
10.1109/CVPR42600.2020.01363
10.1109/CVPR42600.2020.00377
10.1109/CVPR42600.2020.00417
10.1109/CVPR.2019.00838
10.1007/978-3-030-58520-4_15
10.1109/ICCV.2019.00579
10.1109/CVPR.2018.00813
Proc Adv Neural Inf Process Syst (NeurIPS) LinkNet: Relational embedding for scene graph woo 2018 560
10.1109/ICCV.2017.213
10.1007/978-3-030-01240-3_25
10.1109/CVPR.2019.00408
Proc Adv Neural Inf Process Syst (NeurIPS) Faster R-CNN: Towards real-time object detection with region proposal networks ren 2015 1
10.1109/WACV.2018.00181
Stark, L., Bowyer, K.. Achieving generalized object recognition through reasoning about association of function to structure. IEEE transactions on pattern analysis and machine intelligence, vol.13, no.10, 1097-1104.

상세보기
10.1109/ICIP.2018.8451218
10.1109/ICCVW.2019.00344
10.1109/CVPR.2015.7298683
10.1007/978-3-030-01261-8_7
Introduction to Statistical Relational Learning An introduction to conditional random fields for relational learning sutton 2006 2 93
Bansal, Ankan, Rambhatla, Sai Saketh, Shrivastava, Abhinav, Chellappa, Rama. Detecting Human-Object Interactions via Functional Generalization. Proceedings of the ... aaai conference on artificial intelligence, vol.34, no.7, 10460-10469.

상세보기
10.1109/CVPR.2017.331
10.1109/CVPR.2019.00527
10.1109/CVPR.2018.00611
10.1109/ICCV.2017.121
10.1007/978-3-030-01219-9_20
10.1007/978-3-030-01264-9_42
10.1007/978-3-030-58565-5_5
10.1109/ICCV.2019.00093
10.1109/CVPR.2019.00064
10.1109/CVPR.2017.555
Deng, J., Ding, N., Jia, Y., Frome, A., Murphy, K., Bengio, S., Li, Y., Neven, H., Adam, H.. Large-Scale Object Classification Using Label Relation Graphs. Lecture notes in computer science, vol.8689, 48-64.

상세보기
10.1109/CVPR.2017.476
10.1109/CVPR.2008.4587799
10.1007/978-3-030-58610-2_41
Proc Brit Mach Vis Conf (BMVC) iCAN: Instance-centric attention network for human-object interaction detection gao 2018
10.4324/9781315740218
10.1109/CVPR.2018.00872
10.1109/CVPR.2017.330
10.1109/CVPR.2011.5995327
10.1109/CVPR.2019.00212
10.1109/CVPR.2019.00207
10.1007/978-3-030-01246-5_41
10.1109/CVPR.2007.383331
10.1109/ICCV.2015.314
Xu, Bingjie, Li, Junnan, Wong, Yongkang, Zhao, Qi, Kankanhalli, Mohan S.. Interact as You Intend: Intention-Driven Human-Object Interaction Detection. IEEE transactions on multimedia, vol.22, no.6, 1423-1432.

상세보기
Proc IEEE Conf Comput Vis Pattern Recognit (CVPR) Describing the scene as a whole: Joint object detection, scene classification and semantic segmentation yao 2012 702
10.1007/978-3-030-01258-8_3
10.1109/CVPR.2010.5540234
10.1109/CVPR.2010.5540235
10.1109/ICCV.2011.6126386

LOADING...

활용도 분석정보

상세보기

다운로드

내보내기

활용도 Top5 논문

해당 논문의 주제분야에서 활용도가 높은 상위 5개 콘텐츠를 보여줍니다.
더보기 버튼을 클릭하시면 더 많은 관련자료를 살펴볼 수 있습니다.

원문 보기

AccessON 원문보기

원문 URL 링크

DOI : 10.1109/TIP.2021.3113563
IEEE : 저널 > 논문
AccessON : 저널

*원문 PDF 파일 및 링크정보가 존재하지 않을 경우 KISTI DDS 시스템에서 제공하는 원문복사서비스를 사용할 수 있습니다.

오픈액세스(OA) 유형

GREEN

저자가 공개 리포지터리에 출판본, post-print, 또는 pre-print를 셀프 아카이빙 하여 자유로운 이용이 가능한 논문

저작권 관리 안내

내보내기 메뉴

내보내기 구분

파일저장
인쇄
메일전송

구성항목

기본정보
상세정보

관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관

저장형식

Text(ASCII format)
Excel format
RefWorks Direct Export
RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley

메일정보

받는사람 (필수): @
보내는사람 (선택): @
제목
내용: KISTI 검색결과 이메일 서비스

안내

총 건의 자료가 검색되었습니다.

다운받으실 자료의 인덱스를 입력하세요. (1-10,000)

검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다.

데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요)

다운로드 파일은 UTF-8 형태로 저장됩니다.
파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오.

Text(ASCII format)
Excel format

표제어: PCR

동의어: Packet Collision Rate

용어 설명 출처 목록 (6)

용어 설명: PCR은 세균 특이성이 있는 primer를 이용하여 적은 수의 세균이 있을지라도 쉽게 검출할 수 있는 유용한 방법이며, 이를 이용하여 구강 내 치면세균막이나 타액에서 직접 세균을 검출할 수 있게 되었다[8].

AI-Helper ※ AI-Helper는 을 사용합니다.

AI-Helper

안녕하세요, AI-Helper입니다. 좌측 "선택된 텍스트"에서 텍스트를 선택하여 요약, 번역, 용어설명을 실행하세요.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.

연합인증