Human object interaction detection based on feature optimization and key human-object enhancement
Aiming at the problem of unclear or missing human object interaction behavior objects in complex background, we propose a human object interaction detection algorithm based on feature optimization and key human-object enhancement. In order to solve the problem of missing human behavior objects, we p...
Saved in:
| Published in | Journal of visual communication and image representation Vol. 93; p. 103824 |
|---|---|
| Main Authors | , , , |
| Format | Journal Article |
| Language | English |
| Published |
Elsevier Inc
01.05.2023
|
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | Aiming at the problem of unclear or missing human object interaction behavior objects in complex background, we propose a human object interaction detection algorithm based on feature optimization and key human-object enhancement. In order to solve the problem of missing human behavior objects, we propose Feature Optimized Faster Region Convolutional Neural Network (FOFR-CNN). FOFR-CNN is an object detection network optimized by multi-scale feature optimization algorithm, taking into account both image semantics and image structure. In order to reduce the interference of complex background, we propose a Key Human-Object Enhancement Network. The network uses an instance-based method to enhance the features of interactive objects. In order to enrich the interaction information, we use the graph convolutional network. Experimental results on HICO-DET, V-COCO and HOI-A datasets show that the proposed algorithm has significantly improved accuracy and multi-scale object detection ability compared with other human object interaction algorithms. |
|---|---|
| AbstractList | Aiming at the problem of unclear or missing human object interaction behavior objects in complex background, we propose a human object interaction detection algorithm based on feature optimization and key human-object enhancement. In order to solve the problem of missing human behavior objects, we propose Feature Optimized Faster Region Convolutional Neural Network (FOFR-CNN). FOFR-CNN is an object detection network optimized by multi-scale feature optimization algorithm, taking into account both image semantics and image structure. In order to reduce the interference of complex background, we propose a Key Human-Object Enhancement Network. The network uses an instance-based method to enhance the features of interactive objects. In order to enrich the interaction information, we use the graph convolutional network. Experimental results on HICO-DET, V-COCO and HOI-A datasets show that the proposed algorithm has significantly improved accuracy and multi-scale object detection ability compared with other human object interaction algorithms. |
| ArticleNumber | 103824 |
| Author | Wang, Xikun Zhang, Yongmei Ye, Qing Li, Rui |
| Author_xml | – sequence: 1 givenname: Qing surname: Ye fullname: Ye, Qing email: yeqing@ncut.edu.cn – sequence: 2 givenname: Xikun surname: Wang fullname: Wang, Xikun – sequence: 3 givenname: Rui surname: Li fullname: Li, Rui – sequence: 4 givenname: Yongmei surname: Zhang fullname: Zhang, Yongmei email: zhangym@ncut.edu.cn |
| BookMark | eNp9kM1OwzAQhC1UJNrCE3DJC6T4J3GSAwdUAUWqxAXO1sZeqw7EqRy3Unl6kqbnnna0qxnNfgsy851HQh4ZXTHK5FOzao7ahRWnXAwbUfLshswZrfK0ooWcjTorUsGpuCOLvm8opaIS2ZzA5tCCT7q6QR0T5yMG0NF1PjEYcVI19GiSQViEeAiYdPvoWvcH5yt4k_zgKdmNQeklCP0OvMYWfbwntxZ-e3y4zCX5fnv9Wm_S7ef7x_plm2pBRUxBcFlrU5Uyz_MCKsnAcl2KvNYMtBUZSoZFVRpdl9bmHMDaUiLNJBaQCyOWREy5OnR9H9CqfXAthJNiVI2UVKPOlNRISU2UBtfz5MKh2tFhUL12OFQ3LgyPKNO5q_5_8kl1-A |
| CitedBy_id | crossref_primary_10_1134_S036176882308008X crossref_primary_10_1007_s10489_024_05324_1 |
| Cites_doi | 10.1109/CVPR.2010.5540234 10.1109/CVPR.2017.634 10.1109/TBIOM.2020.2973504 10.1109/ISACV.2017.8054899 10.1109/CVPR42600.2020.00417 10.1007/978-3-030-58555-6_30 10.1109/TCYB.2021.3049537 10.1109/ICCV.2011.6126386 10.1145/3065386 10.1109/TPAMI.2009.83 10.5244/C.24.97 10.1109/ICCV.2015.169 10.1109/ROBIO54168.2021.9739429 10.1109/TPAMI.2016.2577031 10.1007/s41095-020-0188-2 10.1109/ICCV.2019.00956 10.23919/MVA51890.2021.9511361 10.1109/CVPR.2016.308 10.1023/B:VISI.0000029664.99615.94 10.1109/CVPR46437.2021.00889 10.1109/IJCNN52387.2021.9534440 10.1109/CVPR.2017.106 10.1109/5.726791 10.1109/CVPR.2015.7298594 10.1145/3463944.3469097 10.1109/CVPR.2016.90 10.1109/ICIP.2019.8803786 10.1109/CVPR42600.2020.01363 10.1109/CVPR.2014.81 10.1109/CVPR.2019.00796 10.1109/CVPR.2018.00872 10.1109/CVPR42600.2020.00056 10.1142/S0218001422550023 10.1109/CVPR.2007.383331 10.1109/DCC.2019.00072 10.1109/CVPR.2010.5540235 10.1145/3412846 10.1109/WACV.2018.00048 |
| ContentType | Journal Article |
| Copyright | 2023 Elsevier Inc. |
| Copyright_xml | – notice: 2023 Elsevier Inc. |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.jvcir.2023.103824 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Journalism & Communications Engineering |
| EISSN | 1095-9076 |
| ExternalDocumentID | 10_1016_j_jvcir_2023_103824 S1047320323000743 |
| GroupedDBID | --K --M .DC .~1 0R~ 1B1 1~. 1~5 29L 4.4 457 4G. 53G 5GY 5VS 7-5 71M 8P~ 9JN AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXUO AAYFN ABBOA ABFNM ABJNI ABMAC ABXDB ABYKQ ACDAQ ACGFS ACNNM ACRLP ACZNC ADBBV ADEZE ADFGL ADJOM ADMHC ADMUD ADTZH AEBSH AECPX AEKER AENEX AFKWA AFTJW AGHFR AGUBO AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CAG COF CS3 DM4 DU5 EBS EFBJH EFLBG EJD EO8 EO9 EP2 EP3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q GBLVA GBOLZ HLZ HVGLF HZ~ IHE J1W JJJVA KOM LG5 LX9 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG ROL RPZ SBC SDF SDG SDP SES SEW SPC SPCBC SST SSV SSZ T5K WH7 WUQ XPP YQT ZMT ZU3 ~G- AAXKI AAYXX AFJKZ AKRWK CITATION |
| ID | FETCH-LOGICAL-c303t-a326bcd9865557a961af2c835bc1acf34e61e798dcb8ff52aaff86e046e7a53d3 |
| IEDL.DBID | AIKHN |
| ISSN | 1047-3203 |
| IngestDate | Thu Sep 26 17:50:23 EDT 2024 Fri Feb 23 02:39:39 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Human object interaction detection FOFR-CNN Graph convolutional network Key human-object enhancement |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c303t-a326bcd9865557a961af2c835bc1acf34e61e798dcb8ff52aaff86e046e7a53d3 |
| ParticipantIDs | crossref_primary_10_1016_j_jvcir_2023_103824 elsevier_sciencedirect_doi_10_1016_j_jvcir_2023_103824 |
| PublicationCentury | 2000 |
| PublicationDate | May 2023 2023-05-00 |
| PublicationDateYYYYMMDD | 2023-05-01 |
| PublicationDate_xml | – month: 05 year: 2023 text: May 2023 |
| PublicationDecade | 2020 |
| PublicationTitle | Journal of visual communication and image representation |
| PublicationYear | 2023 |
| Publisher | Elsevier Inc |
| Publisher_xml | – name: Elsevier Inc |
| References | G. Moon, J.Y. Chang, K.M. Lee, PoseFix: Model-agnostic general human pose refinement network, in: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 7773–7781. S. Ioffe, C. Szegedy, Batch Normalization: accelerating deep network training by reducing internal covariate shift, arXiv [cs.LG], 2015. K. Simonyan, A. Zisserman, Very deep convolutional networks for large-scale image recognition, arXiv [cs.CV], 2014. J. Tong, X. Wu, D. Ding, Z. Zhu, Z. Liu, Learning-based multi-frame video quality enhancement, in: 2019 IEEE International Conference on Image Processing (ICIP), 2019. Liu, Ji, Pang, Han, Li (b0015) 2022; 52 G. Gkioxari, R. Girshick, P. Dollar, K. He, Detecting and recognizing human-object interactions, in: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018. C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, Z. Wojna, Rethinking the inception architecture for computer vision, in: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 2818–2826. Gao, Xu, Zou, Huang (b0245) 2020 Ren, He, Girshick, Sun (b0105) 2017; 39 C. Gao, Y. Zou, J.-B. Huang, ICAN: Instance-centric attention network for human-object interaction detection, arXiv [cs.CV], 2018. S. Chen, Q. Liu, Y. Yang, Multi-view multi-modality priors residual network of depth video enhancement for bandwidth limited asymmetric coding framework, in: 2019 Data Compression Conference (DCC), 2019. Liu, Mu, Huang (b0250) 2021; 7 Fu, Liu, Guan, Zhou, Tao, Xu (b0220) 2021; 17 B. Yao, L. Fei-Fei, Grouplet: a structured image representation for recognizing human and object interactions, in: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2010. Z. Liang, J. Liu, Y. Guan, J. Rojas, Visual-semantic graph attention networks for human-object interaction detection, in: 2021 IEEE International Conference on Robotics and Biomimetics (ROBIO), 2021. R. Girshick, J. Donahue, T. Darrell, J. Malik, Rich feature hierarchies for accurate object detection and semantic segmentation, in: 2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014. V. Delaitre, I. Laptev, J. Sivic, Recognizing human actions in still images: a study of bag-of-features and part-based representations, in: Procedings of the British Machine Vision Conference 2010, 2010. Z. Liang, J. Liu, Y. Guan, J. Rojas, Pose-based Modular Network for human-object interaction detection, arXiv [cs.CV], 2020. Wang, Zheng, Yingbiao (b0240) 2020 O. Ulutan, A.S.M. Iftekhar, B.S. Manjunath, VSGNet: Spatial attention network for detecting human object interactions using graph convolutions, in: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020. Pic leaderboard. Available from: <http://www.picdataset.com/challenge/leaderboard/hoi2019>, 2019. Y. Liao, S. Liu, F. Wang, Y. Chen, C. Qian, J. Feng, PPDM: Parallel point detection and matching for real-time human-object interaction detection, in: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020. Y.-W. Chao, Y. Liu, X. Liu, H. Zeng, J. Deng, Learning to detect human-object interactions, in: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), 2018. B. KimT. ChoiJ. KangH.J. KimUnionDet: Union-Level detector towards real-time human-object interaction detectionComputer Vision – ECCV 2020Springer International PublishingCham2020498514. Asad, Jiang, Yang, Tu, Malik (b0215) 2022; 36 T. Wang, T. Yang, M. Danelljan, F.S. Khan, X. Zhang, J. Sun, Learning human-object interaction detection using interaction points, in: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020. M.-J. Chiou, C.-Y. Liao, L.-W. Wang, R. Zimmermann, J. Feng, ST-HOI: a spatial-temporal baseline for human-object interaction detection in videos, in: Proceedings of the 2021 Workshop on Intelligent Cross-Data Analysis and Retrieval, 2021, pp. 9–17. S. Xie, R. Girshick, P. Dollar, Z. Tu, K. He, Aggregated residual transformations for deep neural networks, in: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. S. Gupta, J. Malik, Visual Semantic Role Labeling, arXiv [cs.CV], 2015. Wang, Zhou, Yan (b0025) 2022; 39 Le, Zou, Yeung, Ng (b0030) 2011; 2011 Zhou, Wang, Qi, Ling, Shen (b0270) 2020 R. Girshick, Fast R-CNN, in: 2015 IEEE International Conference on Computer Vision (ICCV), 2015. B. Yao, X. Jiang, A. Khosla, A. L. Lin, L. Guibas, L. Fei-Fei, Human action recognition by learning bases of action attributes and parts, in: 2011 International Conference on Computer Vision, 2011. N. Dalal, B. Triggs, Histograms of oriented gradients for human detection, in: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), 2005. Li, Liu, Wu, Huang, Xu, Lu (b0115) 2022; 44 Gupta, Kembhavi, Davis (b0140) 2009; 31 Lecun, Bottou, Bengio, Haffner (b0055) 1998; 86 T. Lin, P. Dollár, R.B. Girshick, K. He, B. Hariharan, S.J. Belongie, Feature pyramid networks for object detection, in: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 936–944. A. Gupta, L.S. Davis, Objects in action: an approach for combining action understanding and object perception, in: 2007 IEEE Conference on Computer Vision and Pattern Recognition, 2007. Lowe (b0130) 2004; 60 M. Chen, Y. Liao, S. Liu, Z. Chen, F. Wang, C. Qian, Reformulating HOI detection as adaptive set prediction, in: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021. Zheng, Ranjan, Chen, Chen, Castillo, Chellappa (b0040) 2020; 2 Fang, Cao, Tai, Lu (b0190) 2018 K. Kogashi, Y. Wu, S. Nobuhara, K. Nishino, Human-object interaction detection with missing objects, in: 2021 17th International Conference on Machine Vision and Applications (MVA), 2021. C. Szegedy et al., Going deeper with convolutions, in: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015. Krizhevsky, Sutskever, Hinton (b0060) 2017; 60 Zeng (b0050) 2022; 37 B. Wan, D. Zhou, Y. Liu, R. Li, X. He, Pose-aware multi-level feature network for human object interaction detection, in: 2019 IEEE/CVF International Conference on Computer Vision (ICCV), 2019. N. Heidari, A. Iosifidis, On the spatial attention in spatio-temporal graph convolutional networks for skeleton-based human action recognition, in: 2021 International Joint Conference on Neural Networks (IJCNN), 2021, pp. 1–7. Qi, Wang, Jia, Shen, Zhu (b0180) 2018 K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. K. Ahmed, I.M. El-Henawy, H.A. Mahmoud, Action recognition technique based on fast HOG3D of integral foreground snippets and random forest, in: 2017 Intelligent Systems and Computer Vision (ISCV), 2017. B. Yao, L. Fei-Fei, Modeling mutual context of object and human pose in human-object interaction activities, in: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2010. Wang (10.1016/j.jvcir.2023.103824_b0025) 2022; 39 Gao (10.1016/j.jvcir.2023.103824_b0245) 2020 Li (10.1016/j.jvcir.2023.103824_b0115) 2022; 44 Fang (10.1016/j.jvcir.2023.103824_b0190) 2018 10.1016/j.jvcir.2023.103824_b0260 Lecun (10.1016/j.jvcir.2023.103824_b0055) 1998; 86 10.1016/j.jvcir.2023.103824_b0225 10.1016/j.jvcir.2023.103824_b0145 10.1016/j.jvcir.2023.103824_b0100 10.1016/j.jvcir.2023.103824_b0265 10.1016/j.jvcir.2023.103824_b0020 10.1016/j.jvcir.2023.103824_b0185 10.1016/j.jvcir.2023.103824_b0065 Lowe (10.1016/j.jvcir.2023.103824_b0130) 2004; 60 10.1016/j.jvcir.2023.103824_b0095 10.1016/j.jvcir.2023.103824_b0170 10.1016/j.jvcir.2023.103824_b0090 10.1016/j.jvcir.2023.103824_b0255 10.1016/j.jvcir.2023.103824_b0135 10.1016/j.jvcir.2023.103824_b0210 10.1016/j.jvcir.2023.103824_b0010 10.1016/j.jvcir.2023.103824_b0175 Ren (10.1016/j.jvcir.2023.103824_b0105) 2017; 39 Zheng (10.1016/j.jvcir.2023.103824_b0040) 2020; 2 Fu (10.1016/j.jvcir.2023.103824_b0220) 2021; 17 10.1016/j.jvcir.2023.103824_b0205 Wang (10.1016/j.jvcir.2023.103824_b0240) 2020 Le (10.1016/j.jvcir.2023.103824_b0030) 2011; 2011 10.1016/j.jvcir.2023.103824_b0085 10.1016/j.jvcir.2023.103824_b0160 10.1016/j.jvcir.2023.103824_b0080 Krizhevsky (10.1016/j.jvcir.2023.103824_b0060) 2017; 60 10.1016/j.jvcir.2023.103824_b0125 10.1016/j.jvcir.2023.103824_b0005 10.1016/j.jvcir.2023.103824_b0200 10.1016/j.jvcir.2023.103824_b0165 10.1016/j.jvcir.2023.103824_b0045 Gupta (10.1016/j.jvcir.2023.103824_b0140) 2009; 31 10.1016/j.jvcir.2023.103824_b0120 Asad (10.1016/j.jvcir.2023.103824_b0215) 2022; 36 Zhou (10.1016/j.jvcir.2023.103824_b0270) 2020 Zeng (10.1016/j.jvcir.2023.103824_b0050) 2022; 37 10.1016/j.jvcir.2023.103824_b0150 10.1016/j.jvcir.2023.103824_b0195 10.1016/j.jvcir.2023.103824_b0070 10.1016/j.jvcir.2023.103824_b0235 10.1016/j.jvcir.2023.103824_b0035 Liu (10.1016/j.jvcir.2023.103824_b0250) 2021; 7 Liu (10.1016/j.jvcir.2023.103824_b0015) 2022; 52 10.1016/j.jvcir.2023.103824_b0110 10.1016/j.jvcir.2023.103824_b0155 Qi (10.1016/j.jvcir.2023.103824_b0180) 2018 10.1016/j.jvcir.2023.103824_b0075 10.1016/j.jvcir.2023.103824_b0230 |
| References_xml | – volume: 52 start-page: 7852 year: 2022 end-page: 7864 ident: b0015 article-title: DGIG-Net: Dynamic graph-in-graph networks for few-shot human-object interaction publication-title: IEEE Trans. Cybern. contributor: fullname: Li – volume: 39 start-page: 6 year: 2022 ident: b0025 article-title: Abnormal behavior detection model based on dual-flow structure publication-title: Comput. Appl. Software contributor: fullname: Yan – volume: 60 start-page: 84 year: 2017 end-page: 90 ident: b0060 article-title: ImageNet classification with deep convolutional neural networks publication-title: Commun. ACM contributor: fullname: Hinton – volume: 36 start-page: pp year: 2022 ident: b0215 article-title: Multi-level two-stream fusion-based spatio-temporal attention model for violence detection and localization publication-title: Intern. J. Pattern Recognit. Artif. Intell. contributor: fullname: Malik – volume: 7 start-page: 229 year: 2021 end-page: 239 ident: b0250 article-title: Detecting human-object interaction with multi-level pairwise feature network publication-title: Comput. Vis. Media (Beijing) contributor: fullname: Huang – start-page: 4262 year: 2020 end-page: 4271 ident: b0270 article-title: Cascaded human-object interaction recognition publication-title: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) contributor: fullname: Shen – start-page: 696 year: 2020 end-page: 712 ident: b0245 article-title: DRG: dual relation graph for human-object interaction detection publication-title: Computer Vision – ECCV 2020 contributor: fullname: Huang – volume: 39 start-page: 1137 year: 2017 end-page: 1149 ident: b0105 article-title: Faster R-CNN: Towards real-time object detection with region proposal networks publication-title: IEEE Trans. Pattern Anal. Mach. Intell. contributor: fullname: Sun – start-page: 407 year: 2018 end-page: 423 ident: b0180 article-title: Learning human-object interactions by graph parsing neural networks publication-title: Computer Vision – ECCV 2018 contributor: fullname: Zhu – volume: 37 start-page: 6 year: 2022 ident: b0050 article-title: Human behavior recognition based on ResNext-GRU and clustering sampling publication-title: J. Chengdu Univ. Information Technol. contributor: fullname: Zeng – volume: 86 start-page: 2278 year: 1998 end-page: 2324 ident: b0055 article-title: Gradient-based learning applied to document recognition publication-title: Proc. IEEE Inst. Electr. Electron. Eng. contributor: fullname: Haffner – volume: 44 start-page: 3870 year: 2022 end-page: 3882 ident: b0115 article-title: Transferable Interactiveness Knowledge for human-object interaction detection publication-title: IEEE Trans. Pattern Anal. Mach. Intell. contributor: fullname: Lu – start-page: 52 year: 2018 end-page: 68 ident: b0190 article-title: Pairwise body-part attention for recognizing human-object interactions publication-title: Computer Vision – ECCV 2018 contributor: fullname: Lu – volume: 31 start-page: 1775 year: 2009 end-page: 1789 ident: b0140 article-title: Observing human-object interactions: using spatial and functional compatibility for recognition publication-title: IEEE Trans. Pattern Anal. Mach. Intell. contributor: fullname: Davis – start-page: 248 year: 2020 end-page: 264 ident: b0240 article-title: Contextual heterogeneous graph network for human-object interaction detection publication-title: Computer Vision – ECCV 2020 contributor: fullname: Yingbiao – volume: 2 start-page: 194 year: 2020 end-page: 209 ident: b0040 article-title: An automatic system for unconstrained video-based face recognition publication-title: IEEE Trans. Biom. Behav. Identity Sci. contributor: fullname: Chellappa – volume: 60 start-page: 91 year: 2004 end-page: 110 ident: b0130 article-title: Distinctive image features from scale-invariant keypoints publication-title: Int. J. Comput. Vis. contributor: fullname: Lowe – volume: 2011 start-page: 3361 year: 2011 end-page: 3368 ident: b0030 article-title: Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis publication-title: CVPR contributor: fullname: Ng – volume: 17 start-page: 1 year: 2021 end-page: 13 ident: b0220 article-title: Dynamic graph learning convolutional networks for semi-supervised classification publication-title: ACM trans. multimed. comput. commun. appl. contributor: fullname: Xu – ident: 10.1016/j.jvcir.2023.103824_b0145 doi: 10.1109/CVPR.2010.5540234 – start-page: 407 year: 2018 ident: 10.1016/j.jvcir.2023.103824_b0180 article-title: Learning human-object interactions by graph parsing neural networks contributor: fullname: Qi – ident: 10.1016/j.jvcir.2023.103824_b0090 doi: 10.1109/CVPR.2017.634 – volume: 2 start-page: 194 issue: 3 year: 2020 ident: 10.1016/j.jvcir.2023.103824_b0040 article-title: An automatic system for unconstrained video-based face recognition publication-title: IEEE Trans. Biom. Behav. Identity Sci. doi: 10.1109/TBIOM.2020.2973504 contributor: fullname: Zheng – ident: 10.1016/j.jvcir.2023.103824_b0045 doi: 10.1109/ISACV.2017.8054899 – ident: 10.1016/j.jvcir.2023.103824_b0255 doi: 10.1109/CVPR42600.2020.00417 – ident: 10.1016/j.jvcir.2023.103824_b0260 doi: 10.1007/978-3-030-58555-6_30 – volume: 52 start-page: 7852 issue: 8 year: 2022 ident: 10.1016/j.jvcir.2023.103824_b0015 article-title: DGIG-Net: Dynamic graph-in-graph networks for few-shot human-object interaction publication-title: IEEE Trans. Cybern. doi: 10.1109/TCYB.2021.3049537 contributor: fullname: Liu – ident: 10.1016/j.jvcir.2023.103824_b0155 doi: 10.1109/ICCV.2011.6126386 – volume: 60 start-page: 84 issue: 6 year: 2017 ident: 10.1016/j.jvcir.2023.103824_b0060 article-title: ImageNet classification with deep convolutional neural networks publication-title: Commun. ACM doi: 10.1145/3065386 contributor: fullname: Krizhevsky – ident: 10.1016/j.jvcir.2023.103824_b0125 – volume: 31 start-page: 1775 issue: 10 year: 2009 ident: 10.1016/j.jvcir.2023.103824_b0140 article-title: Observing human-object interactions: using spatial and functional compatibility for recognition publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2009.83 contributor: fullname: Gupta – ident: 10.1016/j.jvcir.2023.103824_b0160 doi: 10.5244/C.24.97 – ident: 10.1016/j.jvcir.2023.103824_b0100 doi: 10.1109/ICCV.2015.169 – volume: 2011 start-page: 3361 year: 2011 ident: 10.1016/j.jvcir.2023.103824_b0030 article-title: Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis publication-title: CVPR contributor: fullname: Le – volume: 39 start-page: 6 issue: 2 year: 2022 ident: 10.1016/j.jvcir.2023.103824_b0025 article-title: Abnormal behavior detection model based on dual-flow structure publication-title: Comput. Appl. Software contributor: fullname: Wang – ident: 10.1016/j.jvcir.2023.103824_b0200 doi: 10.1109/ROBIO54168.2021.9739429 – start-page: 248 year: 2020 ident: 10.1016/j.jvcir.2023.103824_b0240 article-title: Contextual heterogeneous graph network for human-object interaction detection contributor: fullname: Wang – volume: 39 start-page: 1137 issue: 6 year: 2017 ident: 10.1016/j.jvcir.2023.103824_b0105 article-title: Faster R-CNN: Towards real-time object detection with region proposal networks publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2016.2577031 contributor: fullname: Ren – ident: 10.1016/j.jvcir.2023.103824_b0265 – volume: 7 start-page: 229 issue: 2 year: 2021 ident: 10.1016/j.jvcir.2023.103824_b0250 article-title: Detecting human-object interaction with multi-level pairwise feature network publication-title: Comput. Vis. Media (Beijing) doi: 10.1007/s41095-020-0188-2 contributor: fullname: Liu – ident: 10.1016/j.jvcir.2023.103824_b0195 doi: 10.1109/ICCV.2019.00956 – start-page: 4262 year: 2020 ident: 10.1016/j.jvcir.2023.103824_b0270 article-title: Cascaded human-object interaction recognition contributor: fullname: Zhou – ident: 10.1016/j.jvcir.2023.103824_b0020 doi: 10.23919/MVA51890.2021.9511361 – ident: 10.1016/j.jvcir.2023.103824_b0080 doi: 10.1109/CVPR.2016.308 – volume: 60 start-page: 91 issue: 2 year: 2004 ident: 10.1016/j.jvcir.2023.103824_b0130 article-title: Distinctive image features from scale-invariant keypoints publication-title: Int. J. Comput. Vis. doi: 10.1023/B:VISI.0000029664.99615.94 contributor: fullname: Lowe – ident: 10.1016/j.jvcir.2023.103824_b0065 – ident: 10.1016/j.jvcir.2023.103824_b0210 doi: 10.1109/CVPR46437.2021.00889 – ident: 10.1016/j.jvcir.2023.103824_b0005 doi: 10.1109/IJCNN52387.2021.9534440 – ident: 10.1016/j.jvcir.2023.103824_b0120 doi: 10.1109/CVPR.2017.106 – volume: 86 start-page: 2278 issue: 11 year: 1998 ident: 10.1016/j.jvcir.2023.103824_b0055 article-title: Gradient-based learning applied to document recognition publication-title: Proc. IEEE Inst. Electr. Electron. Eng. doi: 10.1109/5.726791 contributor: fullname: Lecun – ident: 10.1016/j.jvcir.2023.103824_b0070 doi: 10.1109/CVPR.2015.7298594 – start-page: 696 year: 2020 ident: 10.1016/j.jvcir.2023.103824_b0245 article-title: DRG: dual relation graph for human-object interaction detection contributor: fullname: Gao – ident: 10.1016/j.jvcir.2023.103824_b0165 – ident: 10.1016/j.jvcir.2023.103824_b0185 doi: 10.1109/ROBIO54168.2021.9739429 – ident: 10.1016/j.jvcir.2023.103824_b0010 doi: 10.1145/3463944.3469097 – ident: 10.1016/j.jvcir.2023.103824_b0075 – ident: 10.1016/j.jvcir.2023.103824_b0085 doi: 10.1109/CVPR.2016.90 – volume: 44 start-page: 3870 issue: 7 year: 2022 ident: 10.1016/j.jvcir.2023.103824_b0115 article-title: Transferable Interactiveness Knowledge for human-object interaction detection publication-title: IEEE Trans. Pattern Anal. Mach. Intell. contributor: fullname: Li – ident: 10.1016/j.jvcir.2023.103824_b0235 doi: 10.1109/ICIP.2019.8803786 – ident: 10.1016/j.jvcir.2023.103824_b0225 doi: 10.1109/CVPR42600.2020.01363 – ident: 10.1016/j.jvcir.2023.103824_b0095 doi: 10.1109/CVPR.2014.81 – volume: 37 start-page: 6 issue: 1 year: 2022 ident: 10.1016/j.jvcir.2023.103824_b0050 article-title: Human behavior recognition based on ResNext-GRU and clustering sampling publication-title: J. Chengdu Univ. Information Technol. contributor: fullname: Zeng – ident: 10.1016/j.jvcir.2023.103824_b0175 – ident: 10.1016/j.jvcir.2023.103824_b0035 doi: 10.1109/CVPR.2019.00796 – ident: 10.1016/j.jvcir.2023.103824_b0110 doi: 10.1109/CVPR.2018.00872 – start-page: 52 year: 2018 ident: 10.1016/j.jvcir.2023.103824_b0190 article-title: Pairwise body-part attention for recognizing human-object interactions contributor: fullname: Fang – ident: 10.1016/j.jvcir.2023.103824_b0205 doi: 10.1109/CVPR42600.2020.00056 – volume: 36 start-page: pp issue: 01 year: 2022 ident: 10.1016/j.jvcir.2023.103824_b0215 article-title: Multi-level two-stream fusion-based spatio-temporal attention model for violence detection and localization publication-title: Intern. J. Pattern Recognit. Artif. Intell. doi: 10.1142/S0218001422550023 contributor: fullname: Asad – ident: 10.1016/j.jvcir.2023.103824_b0135 doi: 10.1109/CVPR.2007.383331 – ident: 10.1016/j.jvcir.2023.103824_b0230 doi: 10.1109/DCC.2019.00072 – ident: 10.1016/j.jvcir.2023.103824_b0150 doi: 10.1109/CVPR.2010.5540235 – volume: 17 start-page: 1 issue: 1s year: 2021 ident: 10.1016/j.jvcir.2023.103824_b0220 article-title: Dynamic graph learning convolutional networks for semi-supervised classification publication-title: ACM trans. multimed. comput. commun. appl. doi: 10.1145/3412846 contributor: fullname: Fu – ident: 10.1016/j.jvcir.2023.103824_b0170 doi: 10.1109/WACV.2018.00048 |
| SSID | ssj0003934 |
| Score | 2.3934925 |
| Snippet | Aiming at the problem of unclear or missing human object interaction behavior objects in complex background, we propose a human object interaction detection... |
| SourceID | crossref elsevier |
| SourceType | Aggregation Database Publisher |
| StartPage | 103824 |
| SubjectTerms | FOFR-CNN Graph convolutional network Human object interaction detection Key human-object enhancement |
| Title | Human object interaction detection based on feature optimization and key human-object enhancement |
| URI | https://dx.doi.org/10.1016/j.jvcir.2023.103824 |
| Volume | 93 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LS8NAEB60XvQgPlGrZQ_iydhmN0mTYylKfSJqobewT0yhqbTVo7_dnexGLIgHb5uQCWEymW92MvMNwGmkkddLiyC14BREkrIg4zaQU0rEERWJYAa7ke8fksEwuhnFoxXo170wWFbpfb_z6ZW39mfaXpvtt6JoPyPJAMMB4MwB4SqsWTiiaQPWete3g4dvh8wy93MZSQlQoCYfqsq8xh-yQF5QyiqucBr9DlA_QOdqCzZ9tEh67oG2YUWXO7Dxg0NwB5r-omI-IWdkqd9jvgu8StKTqcB0C0FuiJnrZCBKL7RbIZApYhdGVyyfZGrdyMT3ZxJeKmI_dFIN8wv8jXT5itaCmcU9GF5dvvQHgZ-qEEgLV4uA24BNSJVhR2rc5VkSckOlDcSEDLk0LNJJqLtZqqRIjYkp58akibb7aN3lMVNsHxrltNQHQBJFlVKhiTXuExkXWSdVkX3znUxqmiaHcF6rMn9z5Bl5XVU2zivN56j53Gn-EJJa3fmSDeTWvf8lePRfwSas45ErYDyGxmL2rk9skLEQLVi9-Axb1pT6T3ePLW9SX2kC1Ro |
| link.rule.ids | 315,783,787,4509,24128,27936,27937,45597,45691 |
| linkProvider | Elsevier |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LS8NAEB5qe1APolWx1scexJOhNpukybEUJbWPixZ6C_vECqbSRn-_O9mNtCAevC1JJoTJ7Mzs7HzfAtwECnm9FPdiE5y8QPjUS5hJ5KTkYeDziFONaOTJNEpnwdM8nNdgUGFhsK3S-X7r00tv7a50nDY7H4tF5xlJBigeAE5tINyBhskGEjM7G_3hKJ3-OGSa2M1lJCVAgYp8qGzzevsSC-QF9WnJFe4HvweojaDzeAgHLlskfftBR1BTeRP2NzgEm9B2Dy3W7-SWbOE91sfAyiI9WXIstxDkhlhZJAORqlB2hIFMEjPQqmT5JEvjRt4dPpOwXBIz0Ul5mJ_nXqTyV7QWrCyewOzx4WWQeu5UBU-YcFV4zCRsXMgEEalhjyVRl2lfmESMiy4TmgYq6qpeEkvBY61DnzGt40iZdbTqsZBKegr1fJmrMyCR9KWUXR0qXCdSxpP7WAbmz98nQvlx1IK7SpXZhyXPyKqusres1HyGms-s5lsQVerOtmwgM-79L8Hz_wpew276Mhln4-F01IY9vGObGS-gXqw-1aVJOAp-5QzqG-hI1Xk |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Human+object+interaction+detection+based+on+feature+optimization+and+key+human-object+enhancement&rft.jtitle=Journal+of+visual+communication+and+image+representation&rft.au=Ye%2C+Qing&rft.au=Wang%2C+Xikun&rft.au=Li%2C+Rui&rft.au=Zhang%2C+Yongmei&rft.date=2023-05-01&rft.pub=Elsevier+Inc&rft.issn=1047-3203&rft.eissn=1095-9076&rft.volume=93&rft_id=info:doi/10.1016%2Fj.jvcir.2023.103824&rft.externalDocID=S1047320323000743 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1047-3203&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1047-3203&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1047-3203&client=summon |