影片物件切割(Video Object Segmentation)被廣泛地應用在電腦視覺，像是影像物件編輯、物件追蹤、自駕車等。近年來隨著深度學習的發展，越來越多的方法都是使用卷神經網路(CNN)的方式解決影像物件切割的問題。在這篇論文，我們就提出了基於記憶體的方式來產生影像物件的標記(mask)，我們設計了模型並取名為「全域和區域匹配影像切割網路(Global and Local Matcher for Video Object Segmentation)」。主要是分別對參考影格和前一張影格做匹配並產生出該張影格的標記(mask)。另外，為了獲得更好的效能，我們還加了區域調整模塊。這可以解決邊界區域的爭議問題，也可以讓模型判斷物體更加清晰。加上了區域調整模型，不管在雅卡爾指數和輪廓邊界準確度都有有效的提升。

Video Object Segmentation(VOS) is widely used in computer vision, such as video editing, object tracking, self-driving and so on. With the development of deep learning in recent years, more and more methods solved problems of video object segmentation based on convolution neural network. In this thesis, we proposed a memory-based method to generate masks of objects in video. We designed the model called “Global and Local Matcher for Video Object Segmentation”. The main target is matching and generating the mask of the object in the current frame with the information of a reference frame and its previous frame. Besides, we also add the local adjustment module for better performance. It can not only solve the ambiguous problems of the object boundary, but also makes our model recognize objects more clearly. With local adjustment module, we increase our performance efficiently in Jaccard similarity or boundary accuracy.

[1] Seoung Wug Oh, Joon-Young Lee, Ning Xu, and Seon Joo Kim. Video Object Segmentation Using Space-Time Memory Networks. In ICCV 2019.
[2] Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. Attention is all you need. In Advances in Neural Information Processing Systems, pages 5998–6008, 2017.
[3] Xiaolong Wang, Ross Girshick, Abhinav Gupta, and Kaiming He. Non-local neural networks. In CVPR, 2018.
[4] Anna Khoreva, Rodrigo Benenson, Eddy Ilg, Thomas Brox, and Bernt Schiele. Lucid Data Dreaming for Video Object Segmentation. In The 2017 DAVIS Challenge on Video Object Segmentation - CVPR Workshops, 2017.
[5] Ning Xu, Linjie Yang, Yuchen Fan, Dingcheng Yue, Yuchen Liang, Jianchao Yang, and Thomas Huang. Youtube-vos: A large-scale video object segmentation benchmark. In ECCV, 2018
[6] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. In CVPR, pages 770–778, 2016.
[7] Yongqing Liang, Xin Li, Navid Jafari, and Qin Chen. Video Object Segmentation with Adaptive Feature Bank and Uncertain-Region Refinement. In NIPS, 2020.
[8] Seoung Wug Oh, Joon-Young Lee, Kalyan Sunkavalli, and Seon Joo Kim. Fast video object segmentation by reference guided mask propagation. In CVPR, 2018.
[9] Linjie Yang, Yanran Wang, Xuehan Xiong, Jianchao Yang, and Aggelos K Katsaggelos. Efficient video object segmentation via network modulation. In CVPR, 2018.
[10] Sergi Caelles, Kevis-Kokitsi Maninis, Jordi Pont-Tuset, Laura Leal-Taixe, Daniel Cremers, and Luc Van Gool. One-shot video object segmentation. In CVPR, 2017.
[11] Ziqin Wang, Jun Xu, Li Liu, Fan Zhu, and Ling Shao. RANet: Ranking attention network for fast video object segmentation. In ICCV, 2019.
[12] Jingchun Cheng, Yi-Hsuan Tsai, Wei-Chih Hung, Shengjin Wang, and Ming-Hsuan Yang. Fast and accurate online video object segmentation via tracking parts. In CVPR, 2018.
[13] Paul Voigtlaender and Bastian Leibe. Online adaptation of convolutional neural networks for video object segmentation. In British Machine Vision Conference, 2017.
[14] Carles Ventura, Miriam Bellver, Andreu Girbau, Amaia Salvador, Ferran Marques, and Xavier Giro-i Nieto. Rvos: Endto-end recurrent network for video object segmentation. In CVPR, 2019.
[15] Qiang Wang, Li Zhang, Luca Bertinetto, Weiming Hu, and Philip H.S. Torr. Fast online object tracking and segmentation: A unifying approach. In Proc. CVPR, 2019.
[16] Mark Sandler, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, and Liang-Chieh Chen. MobileNetV2: Inverted Residuals and Linear Bottlenecks. In CVPR, 2018.
[17] Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton. Imagenet classification with deep convolutional neural networks. In NIPS, pages 1097–1105. 2012.
[18] Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollar, and C Lawrence Zitnick. Microsoft coco: Common objects in context. In ECCV, 2014.
[19] Mark Everingham, Luc Van Gool, Christopher K. Williams, John Winn, and Andrew Zisserman. The Pascal Visual Object Classes (VOC) Challenge. In IJCV, 2010.
[20] Olga Russakovsky, Jia Deng, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, Michael Bernstein, Alexander C. Berg, and Li Fei-Fei. ImageNet Large Scale Visual Recognition Challenge. In IJCV, 2015.
[21] Olaf Ronneberger, Philipp Fischer, and Thomas Brox. U-Net: Convolutional Networks for Biomedical Image Segmentation. In MICCAI, 2015.
[22] Ilya Loshchilov, and Frank Hutter. Decoupled Weight Decay Regularization. In ICLR, 2019.
[23] Yuan-Ting Hu, Jia-Bin Huang, and Alexander Schwing. Maskrnn: Instance level video object segmentation. In NIPS, 2017.
[24] Federico Perazzi, Anna Khoreva, Rodrigo Benenson, Bernt Schiele, and Alexander Sorkine-Hornung. Learning video object segmentation from static images. In CVPR, 2017.