請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/76471完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 陳銘憲(Ming-Syan Chen) | |
| dc.contributor.author | Yu-Chi Chen | en |
| dc.contributor.author | 陳郁棋 | zh_TW |
| dc.date.accessioned | 2021-07-09T15:52:51Z | - |
| dc.date.available | 2025-08-21 | |
| dc.date.copyright | 2020-08-21 | |
| dc.date.issued | 2020 | |
| dc.date.submitted | 2020-08-14 | |
| dc.identifier.citation | [1] M. Al-Dhelaan and H. Alhawasi. Graph summarization for hashtag recommendation. In 2015 3rd International Conference on Future Internet of Things and Cloud, pages 698–702. IEEE, 2015. [2] L. Bail, Y. Jiao, L. Cui, and E. R. Hancock. Learning aligned-spatial graph convolutional networks for graph classification. arXiv preprint arXiv:1904.04238, 2019. [3] F. M. Belém, J. M. Almeida, and M. A. Gonçalves. A survey on tag recommendation methods. Journal of the Association for Information Science and Technology, 68(4):830–844, 2017. [4] N. Ben-Lhachemi et al. Hashtag recommendation using word sequences’ embeddings. In International Conference on Big Data, Cloud and Applications, pages 131–143. Springer, 2018. [5] B. Berendt and C. Hanser. Tags are not metadata, but” just more content”-to some people. In ICWSM, 2007. [6] M. J. Carman, M. Baillie, and F. Crestani. Tag data and personalized information retrieval. In Proceedings of the 2008 ACM workshop on Search in social media, pages 27–34, 2008. [7] Z.-M. Chen, X.-S. Wei, P. Wang, and Y. Guo. Multi-label image recognition with graph convolutional networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 5177–5186, 2019. [8] K. C. Cheung and T. K. Y. Cheung. Recommendation of hashtags in social twitter network. International Journal of Data Analysis Techniques and Strategies, 9(3):222–236, 2017. [9] C. Chunseong Park, B. Kim, and G. Kim. Attend to you: Personalized image captioning with context sequence memory networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pages 895–903, 2017. [10] E. Denton, J. Weston, M. Paluri, L. Bourdev, and R. Fergus. User conditional hashtag prediction for images. In Proceedings of the 21th ACM SIGKDD international conference on knowledge discovery and data mining, pages 1731–1740, 2015. [11] K. Dey, R. Shrivastava, S. Kaushik, and L. V. Subramaniam. Emtagger: a word embedding based novel method for hashtag recommendation on twitter. In 2017 IEEE International Conference on Data Mining Workshops (ICDMW), pages 1025–1032. IEEE, 2017. [12] Z. Ding, X. Qiu, Q. Zhang, and X. Huang. Learning topical translation model for microblog hashtag suggestion. In Twenty-Third International Joint Conference on Artificial Intelligence, 2013. [13] Z. Ding, Q. Zhang, and X.-J. Huang. Automatic hashtag recommendation for microblogs using topic-specific translation model. In Proceedings of COLING 2012:Posters, pages 265–274, 2012. [14] M. Efron. Hashtag retrieval in a microblogging environment. In Proceedings of the 33rd international ACM SIGIR conference on Research and development in information retrieval, pages 787–788. ACM, 2010. [15] A. Frome, G. S. Corrado, J. Shlens, S. Bengio, J. Dean, M. Ranzato, and T. Mikolov. Devise: A deep visual-semantic embedding model. In Advances in neural information processing systems (NIPS), pages 2121–2129, 2013. [16] Y. Gong, Q. Ke, M. Isard, and S. Lazebnik. A multi-view embedding space for modeling internet images, tags, and their semantics. International journal of computer vision (IJCV), 106(2):210–233, 2014. [17] Y. Gong and Q. Zhang. Hashtag recommendation using attention-based convolutional neural network. In International Joint Conference on Artificial Intelligence (IJCAI), pages 2782–2788, 2016. [18] W. Hamilton, Z. Ying, and J. Leskovec. Inductive representation learning on large graphs. In Advances in neural information processing systems (NIPS), pages 1024–1034, 2017. [19] S. Hochreiter and J. Schmidhuber. Long short-term memory. Neural computation, 9(8):1735–1780, 1997. [20] H. Huang, Q. Zhang, Y. Gong, and X.-J. Huang. Hashtag recommendation using endto-end memory networks with hierarchical attention. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 943–952, 2016. [21] M. Jeon, S. Jun, and E. Hwang. Hashtag recommendation based on user tweet and hashtag classification on twitter. In International Conference on Web-Age Information Management, pages 325–336. Springer, 2014. [22] M. Jocic, D. Obradovic, V. Malbasa, and Z. Konjo. Image tagging with an ensemble of deep convolutional neural networks. In 2017 International Conference on Information Society and Technology, ICIST Workshops, pages 13–17, 2017. [23] D. Kao, K.-T. Lai, and M.-S. Chen. An efficient and resource-aware hashtag recommendation using deep neural networks. In Pacific-Asia Conference on Knowledge Discovery and Data Mining, pages 150–162. Springer, 2019. [24] M. R. Khan and J. E. Blumenstock. Multi-gcn: Graph convolutional networks for multi-view networks, with applications to global poverty. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, pages 606–613, 2019. [25] T. N. Kipf and M. Welling. Semi-supervised classification with graph convolutional networks. In International Conference on Learning Representations (ICLR), 2017. [26] K. Knautz, S. Soubusta, and W. G. Stock. Tag clusters as information retrieval interfaces. In 2010 43rd Hawaii International Conference on System Sciences, pages 1–10. IEEE, 2010. [27] F.-F. Kou, J.-P. Du, C.-X. Yang, Y.-S. Shi, W.-Q. Cui, M.-Y. Liang, and Y. Geng. Hashtag recommendation based on multi-features of microblogs. Journal of Computer Science and Technology, 33(4):711–726, 2018. [28] J. Li, H. Xu, X. He, J. Deng, and X. Sun. Tweet modeling with lstm recurrent neural networks for hashtag recommendation. In 2016 International Joint Conference on Neural Networks (IJCNN), pages 1570–1577. IEEE, 2016. [29] M. Li, T. Gan, M. Liu, Z. Cheng, J. Yin, and L. Nie. Long-tail hashtag recommendation for micro-videos with graph convolutional network. In Proceedings of the 28th ACM International Conference on Information and Knowledge Management, pages 509–518, 2019. [30] Q. Li, Z. Han, and X.-M. Wu. Deeper insights into graph convolutional networks for semi-supervised learning. In Thirty-Second AAAI Conference on Artificial Intelligence, 2018. [31] Y. Li, T. Liu, J. Hu, and J. Jiang. Topical co-attention networks for hashtag recommendation on microblogs. Neurocomputing, 331:356–365, 2019. [32] Y. Li, T. Liu, J. Jiang, and L. Zhang. Hashtag recommendation with topical attentionbased lstm. Coling, 2016. [33] Z. Li, Z. Liu, J. Huang, G. Tang, Y. Duan, Z. Zhang, and Y. Yang. Mv-gcn: Multiview graph convolutional networks for link prediction. IEEE Access, 7:176317-176328, 2019. [34] D. Liu, X.-S. Hua, L. Yang, M. Wang, and H.-J. Zhang. Tag ranking. In Proceedings of the 18th international conference on World wide web (WWW), pages 351–360, 2009. [35] J. Liu, Z. He, and Y. Huang. Hashtag2vec: Learning hashtag representation with relational hierarchical embedding model. In IJCAI, pages 3456–3462, 2018. [36] J. Lu, J. Yang, D. Batra, and D. Parikh. Hierarchical question-image co-attention for visual question answering. In Advances in neural information processing systems (NIPS), pages 289–297, 2016. [37] J. Ma, C. Feng, G. Shi, X. Shi, and H. Huang. Temporal enhanced sentence-level attention model for hashtag recommendation. CAAI Transactions on Intelligence Technology, 3(2):95–100, 2018. [38] Z. Ma, A. Sun, and G. Cong. Will this# hashtag be popular tomorrow? In Proceedings of the 35th international ACM SIGIR conference on Research and development in information retrieval, pages 1173–1174. ACM, 2012. [39] S. K. Maity, A. Panigrahi, S. Ghosh, A. Banerjee, P. Goyal, and A. Mukherjee. Deeptagrec: A content-cum-user based tag recommendation framework for stack overflow. In European Conference on Information Retrieval, pages 125–131. Springer, 2019. [40] V. Mnih, N. Heess, A. Graves, et al. Recurrent models of visual attention. In Advances in neural information processing systems, pages 2204–2212, 2014. [41] V. Nair and G. E. Hinton. Rectified linear units improve restricted boltzmann machines. In Proceedings of the 27th international conference on machine learning (ICML-10), pages 807–814, 2010. [42] H. T. Nguyen, M. Wistuba, and L. Schmidt-Thieme. Personalized tag recommendation for images using deep transfer learning. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases (ECML/PKDD), pages 705–720. Springer, 2017. [43] T. H. H. Nguyen. Recommending tags for images: Deep learning approaches for personalized tag recommendation. 2018. [44] M. Norouzi, T. Mikolov, S. Bengio, Y. Singer, J. Shlens, A. Frome, G. S. Corrado, and J. Dean. Zero-shot learning by convex combination of semantic embeddings. arXiv preprint arXiv:1312.5650, 2013. [45] M. Park, H. Li, and J. Kim. Harrison: A benchmark on hashtag recommendation for real-world images in social networks. arXiv preprint arXiv:1605.05054, 2016. [46] M. Peng, Q. Bian, Q. Zhang, T. Gui, J. Fu, L. Zeng, and X. Huang. Model the longterm post history for hashtag recommendation. In CCF International Conference on Natural Language Processing and Chinese Computing, pages 596–608. Springer, 2019. [47] Y. S. Rawat and M. S. Kankanhalli. Contagnet: Exploiting user context for image tag recommendation. In Proceedings of the 24th ACM international conference on Multimedia, pages 1102–1106, 2016. [48] S. Ruder. An overview of gradient descent optimization algorithms. arXiv preprint arXiv:1609.04747, 2016. [49] S. Sedhai and A. Sun. Hashtag recommendation for hyperlinked tweets. In Proceedings of the 37th international ACM SIGIR conference on Research development in information retrieval, pages 831–834, 2014. [50] Y. Shen, H. Li, S. Yi, D. Chen, and X. Wang. Person re-identification with deep similarity-guided graph neural network. In Proceedings of the European conference on computer vision (ECCV), pages 486–504, 2018. [51] X. Shi, H. Huang, S. Zhao, P. Jian, and Y.-K. Tang. Tag recommendation by wordlevel tag sequence modeling. In International Conference on Database Systems for Advanced Applications, pages 420–424. Springer, 2019. [52] K. Simonyan and A. Zisserman. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014. [53] A. Singh, S. Saini, R. Shah, and P. Narayanan. Learning to hash-tag videos with tag2vec. In Proceedings of the Tenth Indian Conference on Computer Vision, Graphics and Image Processing, pages 1–8, 2016. [54] S. Social. How to grow your audience with hashtags for instagram, 2018. [55] N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov. Dropout: a simple way to prevent neural networks from overfitting. The journal of machine learning research, 15(1):1929–1958, 2014. [56] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin. Attention is all you need. In Advances in neural information processing systems (NIPS), pages 5998–6008, 2017. [57] H. Wang, X. Shi, and D.-Y. Yeung. Relational stacked denoising autoencoder for tag recommendation. In Twenty-ninth AAAI conference on artificial intelligence, 2015. [58] J. Wang, Y. Yang, J. Mao, Z. Huang, C. Huang, and W. Xu. Cnn-rnn: A unified framework for multi-label image classification. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pages 2285–2294, 2016. [59] X. Wang, R. Girshick, A. Gupta, and K. He. Non-local neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pages 7794–7803, 2018. [60] X. Wang and A. Gupta. Videos as space-time region graphs. In Proceedings of the European conference on computer vision (ECCV), pages 399–417, 2018. [61] Y. Wang, J. Qu, J. Liu, J. Chen, and Y. Huang. What to tag your microblog: Hashtag recommendation based on topic analysis and collaborative filtering. In Asia-pacific Web Conference, pages 610–618. Springer, 2014. [62] Y. Wang, S. Wang, J. Tang, G. Qi, H. Liu, and B. Li. Clare: A joint approach to label classification and tag recommendation. In Thirty-First AAAI Conference on Artificial Intelligence, 2017. [63] Y. Wei, Z. Cheng, X. Yu, Z. Zhao, L. Zhu, and L. Nie. Personalized hashtag recommendation for micro-videos. In Proceedings of the 27th ACM International Conference on Multimedia, pages 1446–1454, 2019. [64] Y. Wei, W. Xia, J. Huang, B. Ni, J. Dong, Y. Zhao, and S. Yan. Cnn: Single-label to multi-label. arXiv preprint arXiv:1406.5726, 2014. [65] J. Weston, S. Chopra, and K. Adams. # tagspace: Semantic embeddings from hashtags. In Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), pages 1822–1827, 2014. [66] G. Wu, Y. Li, W. Yan, R. Li, X. Gu, and Q. Yang. Hashtag recommendation with attention-based neural image hashtagging network. In International Conference on Neural Information Processing, pages 52–63. Springer, 2018. [67] Y. Wu, Y. Yao, F. Xu, H. Tong, and J. Lu. Tag2word: Using tags to generate words for content based tag recommendation. In Proceedings of the 25th ACM international on conference on information and knowledge management, pages 2287–2292, 2016. [68] C. Xiong, V. Zhong, and R. Socher. Dynamic coattention networks for question answering. arXiv preprint arXiv:1611.01604, 2016. [69] B. Xu, N. Wang, T. Chen, and M. Li. Empirical evaluation of rectified activations in convolutional network. arXiv preprint arXiv:1505.00853, 2015. [70] K. Xu, J. Ba, R. Kiros, K. Cho, A. Courville, R. Salakhudinov, R. Zemel, and Y. Bengio. Show, attend and tell: Neural image caption generation with visual attention. In International conference on machine learning, pages 2048–2057, 2015. [71] Y. Yan, Q. Zhang, B. Ni, W. Zhang, M. Xu, and X. Yang. Learning context graph for person search. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 2158–2167, 2019. [72] C. Yang, Z. Liu, D. Zhao, M. Sun, and E. Chang. Network representation learning with rich text information. In Twenty-Fourth International Joint Conference on Artificial Intelligence (IJCAI), 2015. [73] Z. Yang, X. He, J. Gao, L. Deng, and A. Smola. Stacked attention networks for image question answering. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 21–29, 2016. [74] R. Ying, R. He, K. Chen, P. Eksombatchai, W. L. Hamilton, and J. Leskovec. Graph convolutional neural networks for web-scale recommender systems. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery Data Mining, pages 974–983, 2018. [75] Q. You, H. Jin, and J. Luo. Visual sentiment analysis by attending on local image regions. In Thirty-First AAAI Conference on Artificial Intelligence, 2017. [76] Q. You, H. Jin, Z. Wang, C. Fang, and J. Luo. Image captioning with semantic attention. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pages 4651–4659, 2016. [77] Q. Zhang, J. Wang, H. Huang, X. Huang, and Y. Gong. Hashtag recommendation for multimodal microblog using co-attention network. In International Joint Conference on Artificial Intelligence (IJCAI), pages 3420–3426, 2017. [78] S. Zhang, Y. Yao, F. Xu, H. Tong, X. Yan, and J. Lu. Hashtag recommendation for photo sharing services. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, pages 5805–5812, 2019. [79] Y. Zhang, B. Gong, and M. Shah. Fast zero-shot image tagging. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 5985–5994. IEEE, 2016. [80] F. Zhao, Y. Zhu, H. Jin, and L. T. Yang. A personalized hashtag recommendation approach using lda-based topic model in microblog environment. Future Generation Computer Systems, 65:196–206, 2016. [81] R. Zhu, D. Yang, and Y. Li. Learning improved semantic representations with treestructured lstm for hashtag recommendation: An experimental study. Information, 10(4):127, 2019. [82] S. Zhu, S. Aloufi, and A. El Saddik. Utilizing image social clues for automated image tagging. In 2015 IEEE International Conference on Multimedia and Expo (ICME), pages 1–6. IEEE, 2015. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/76471 | - |
| dc.description.abstract | 主題標籤對於現代社群軟體來說佔有一個重要的角色,它可以用來當作增加曝光率的工具,也可以當作分類的依據。過去曾有不少人分別提出從照片、文字、使用者角度出發的標籤推薦方法,然而多數方法只考慮單一資訊對推薦系統所造成的影響,而忽略了不同種資訊間相互作用所帶來的加成效果。在這次的研究中,我們提出了一個創新的TAGNet模型,利用圖卷機網路搭配三重注意力機制,來預測出符合內文及使用者偏好的主題標籤。我們的切入點為相似照片的內文會分享相似的主題標籤,因此我們以照片相似度來建立一個照片圖,並提出一個有別於原始圖卷機網路的傳播方式來傳遞圖中的各種資訊。相對於傳統單一輸入輸出的推薦系統,我們是以一個集體的方式並結合具有相似資訊的內文來達到推薦的目的。此外,人們發文除了照片的資訊之外,文字與使用者習慣也是一個很有用的資訊。因此,我們設計了一個三重注意力機制來抽取並融合照片、文字與使用者資訊交互產生的影響,將所學習到的特徵當作照片圖中的節點特徵。實驗測試在一個大型的Instagram真實資料集上,而其結果顯示我們的TAGNet模型相較於之前最新的方法,在Precision、Recall以及F1-score皆有著顯著的進步,並超越之前方法的表現。 | zh_TW |
| dc.description.abstract | Hashtag is an important advertising tool and a must-have feature for social media nowadays. In the past, many hashtag recommendation methods have been proposed from different perspectives of images, texts, and users. However, most previous works consider neither the mutual influence between multi-modalities, nor the visual similarity between images. In this thesis, we devise a novel model, named Triplet-Attention Graph Network (TAGNet). The rationale behind our method is that visually similar images share some common hashtags. Therefore, we build an image graph, and apply a new Aggregated Graph Convolution (AGC) module to propagate information in a collective way. Furthermore, it is noted that text and user also have rich content information within posts, and we hence propose a Triplet Attention (TA) module to incorporate multi-modalities into node features. Experiments on the large-scale dataset collected from Instagram show that TAGNet achieved significant improvement in recall rate over the best state-of-the-art method. | en |
| dc.description.provenance | Made available in DSpace on 2021-07-09T15:52:51Z (GMT). No. of bitstreams: 1 U0001-0308202023583500.pdf: 4243519 bytes, checksum: d23508fc4b6462b5f5cc275fc926383c (MD5) Previous issue date: 2020 | en |
| dc.description.tableofcontents | 口試委員會審定書 iii 誌謝 v Acknowledgements vii 摘要 ix Abstract xi 1 Introduction 1 2 Related Work 5 2.1 Hashtag Recommendation . . . . . . . . . . . . . . . . . . . . . . . . . 5 2.2 Graph Convolutional Network . . . . . . . . . . . . . . . . . . . . . . . 6 2.3 Attention Mechanism . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6 3 TAGNet Framework 9 3.1 Graph Construction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10 3.1.1 Image Feature Extraction . . . . . . . . . . . . . . . . . . . . . . 10 3.1.2 Text Feature Extraction . . . . . . . . . . . . . . . . . . . . . . . 11 3.1.3 User Feature Extraction . . . . . . . . . . . . . . . . . . . . . . 11 3.1.4 Edge Generation . . . . . . . . . . . . . . . . . . . . . . . . . . 11 3.2 Information Fusion via Triplet Attention . . . . . . . . . . . . . . . . . . 12 3.2.1 User-Image Co-attention . . . . . . . . . . . . . . . . . . . . . . 12 3.2.2 Image-Text Co-attention . . . . . . . . . . . . . . . . . . . . . . 14 3.2.3 Text-User Co-attention . . . . . . . . . . . . . . . . . . . . . . . 15 3.2.4 Post Information Fusion . . . . . . . . . . . . . . . . . . . . . . 15 3.3 Aggregated Graph Convolution . . . . . . . . . . . . . . . . . . . . . . . 15 3.4 Training . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16 4 Experiments 19 4.1 Dataset and Evaluation Metrics . . . . . . . . . . . . . . . . . . . . . . . 19 4.2 Implementation Details . . . . . . . . . . . . . . . . . . . . . . . . . . . 19 4.3 Comparison to Other Methods . . . . . . . . . . . . . . . . . . . . . . . 20 4.4 Ablation Studies . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21 4.5 Sensitivity Analysis for Parameters . . . . . . . . . . . . . . . . . . . . . 23 4.5.1 Effects of Threshold γ for Relation Matrix A . . . . . . . . . . . 23 4.5.2 Sensitivity Study of Embedding Dimension . . . . . . . . . . . . 23 4.5.3 Effects of the Dropout Rate in the Training Process . . . . . . . . 24 4.6 Heterogeneous Graph Networks . . . . . . . . . . . . . . . . . . . . . . 24 4.7 Hashtag Recommendation Examples . . . . . . . . . . . . . . . . . . . . 25 5 Conclusion and Future Work 29 Bibliography 31 | |
| dc.language.iso | en | |
| dc.subject | 圖卷積網路 | zh_TW |
| dc.subject | 注意力機制 | zh_TW |
| dc.subject | 主題標籤推薦系統 | zh_TW |
| dc.subject | Graph Convolutional Networks | en |
| dc.subject | Attention Mechanism | en |
| dc.subject | Hashtag Recommendation | en |
| dc.title | 圖卷積網路搭配三重注意力機制之主題標籤推薦系統 | zh_TW |
| dc.title | TAGNet: Triplet-Attention Graph Networks for Hashtag Recommendation | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 108-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 楊得年(De-Nian Yang),王鈺強(Yu-Chiang Wang),陳怡伶(Yi-Ling Chen),賴冠廷(Kuan-Ting Lai) | |
| dc.subject.keyword | 主題標籤推薦系統,圖卷積網路,注意力機制, | zh_TW |
| dc.subject.keyword | Hashtag Recommendation,Graph Convolutional Networks,Attention Mechanism, | en |
| dc.relation.page | 40 | |
| dc.identifier.doi | 10.6342/NTU202002334 | |
| dc.rights.note | 同意授權(全球公開) | |
| dc.date.accepted | 2020-08-16 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 電信工程學研究所 | zh_TW |
| dc.date.embargo-lift | 2025-08-21 | - |
| 顯示於系所單位： | 電信工程學研究所 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| U0001-0308202023583500.pdf | 4.14 MB | Adobe PDF | 檢視/開啟 |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。