{"title":"The comparison of different graph convolutional neural networks for image recognition","authors":"Sichao Fu, Xinghao Yang, Weifeng Liu","doi":"10.1145/3240876.3240915","DOIUrl":"https://doi.org/10.1145/3240876.3240915","url":null,"abstract":"During the past decade, deep learning (DL) has been proven an effective way for image recognition. Various kinds of DL models such as, graph neural network (GNN), gated graph neural networks (GG-NNs) and graph convolutional neural networks (GCN) have been proposed. The latest GCN algorithm has achieved prominent performance for knowledge graph classification and molecular recognition. However, it only calculates the simple zero-one adjacency matrix, which is powerless to distinguish the self-node and other nodes. In this paper, we propose a novel negative one-zero-one graph to tackle this problem. Particularly, the negative one-zero-one graph employs zero to identify the node itself. To further explore the distance structure of inner-class samples, we develop the negative one-zero-one graph to a Euclidean distance version. Based on the ordinary graph, we also propose three kinds of hypergraph construction methods, such as hypergraph label method, hypergraph Euclidean distance method and the improvement method of hypergraph Euclidean distance. Additionally, we extend GCN to image recognition tasks in this paper. Extensive experiments are conducted on PASCAL VOC 2007 dataset to validate the proposed algorithms. The experiments results prove that the proposed methods is superior to the some methods for image recognition.","PeriodicalId":143744,"journal":{"name":"International Conference on Internet Multimedia Computing and Service","volume":"102 20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115264364","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Xingyan Guo, Yi Jin, Yidong Li, Junliang Xing, Congyan Lang
{"title":"Stabilizing video facial landmark detection and tracking via global and local filtering","authors":"Xingyan Guo, Yi Jin, Yidong Li, Junliang Xing, Congyan Lang","doi":"10.1145/3240876.3240913","DOIUrl":"https://doi.org/10.1145/3240876.3240913","url":null,"abstract":"Video facial landmark detection and tracking are important computer vision tasks with many applications such as face anti-spoofing, animation and recognition. Most of existing facial landmark detection and tracking methods, however, often suffer from the instability issue which will affect their effectiveness in real world applications. In this work we present a novel solution for stabilized facial landmark detection and tracking in video frames. The proposed solution addresses various kinds of challenging situations and provides effective remedies to solve them. The main contribution within our solution is a novel global and local filtering strategy, which guarantees the robustness of global whole facial shape tracking and the adaptivity of local facial parts tracking. The proposed solution does not depend on specific face detection and alignment algorithms, thus can be easily deployed into existing systems. Extensive experimental evaluations and analyses on different benchmark datasets verify the effectiveness of the proposed approach.","PeriodicalId":143744,"journal":{"name":"International Conference on Internet Multimedia Computing and Service","volume":"209 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123387209","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"One-shot learning for RGB-D hand-held object recognition","authors":"Jian Sun, Yaohui Zhu, Shuqiang Jiang","doi":"10.1145/3240876.3240920","DOIUrl":"https://doi.org/10.1145/3240876.3240920","url":null,"abstract":"With the advance of computer technology and smart device, many applications, such as face recognition and object recognition, have been developed to facilitate human-computer interaction (HCI) efficiently. In this respect, the hand-held object recognition plays an important role in HCI. It can be used not only to help computer understand useros intentions but also to meet useros requirements. In recent years the appearance of convolutional neural networks (CNNs) greatly enhances the performance of object recognition and this technology has been applied to hand-held object recognition in some works. However, these supervised learning models need large number of labelled data and many iterations to train their large number of parameters. This is a huge challenge for HCI, because HCI need to deal with in-time and itos difficult to collect enough labeled data. Especially when a new category need to be learnt, it will spend a lot of time to update the model. In this work, we adopt the one-shot learning method to solve this problem. This method does not need to update the model when a new category need to be learnt. Moreover, depth image is robust to light and color variation. We fuse depth image information to harness the complementary relationship between the two modalities to improve the performance of hand-held object recognition. Experimental results on our handheld object dataset demonstrate that our method for hand-held object recognition achieves an improvement of performance.","PeriodicalId":143744,"journal":{"name":"International Conference on Internet Multimedia Computing and Service","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125721226","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Illustrate your travel notes: web-based story visualization","authors":"Junlei Zhang, H. Yao, JiaLing He, Xiaoshuai Sun","doi":"10.1145/3240876.3240911","DOIUrl":"https://doi.org/10.1145/3240876.3240911","url":null,"abstract":"In this paper, we present an automatic web-based framework to insert images to the proper location of travel notes without restrictions on pre-defined vocabulary and training process. Instead of learning region-entity correspondences from explicitly human labelling, we collected weakly labeled Web images and proposed a method based on clustering to further discover image regions whose visual contents are highly correlated with the corresponding weak labels, from the original whole images. Then an adaptive visual representation is constructed from the discovered image regions which can automatically link phrase-image pairs. We also release a new dataset TVN25 targeting at Web-based travel notes visualization task which consists of 25 travel notes and over 22k weakly labeled Web images about the lingual phrases in travel notes. Experiments results on travel notes visualization not only demonstrated the effectiveness of our proposed framework, but also show the potential for more real-world applications.","PeriodicalId":143744,"journal":{"name":"International Conference on Internet Multimedia Computing and Service","volume":" 7","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132158682","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Automatic makeup based on generative adversarial nets","authors":"Renda Bao, Han Yu, Si Liu, Bo Li","doi":"10.1145/3240876.3240903","DOIUrl":"https://doi.org/10.1145/3240876.3240903","url":null,"abstract":"Automatic makeup aims to compose and synthesize makeup on human face through computer algorithm, which belongs to the field of face image analysis. It plays an important role in interactive entertainment applications, image and video editing and face recognition assistance. However, as a face editing task, automatic makeup has several challenges as following: 1) It is usually difficult to meet the editing requirements while ensuring that makeup results are naturally looking without obvious artifacts. 2) Designed network should preserve the content (human identity) of input images but only edits the makeup-related parts of input images such as lip gloss and eye shadow. 3) Number of face makeup dataset is limited. To address these difficulties, we propose an automatic makeup generative adversarial network, a novel approach that can perform makeup attribute editing for multiple makeup styles. The network is an end-to-end model with several specially designed skip layers in generator network and allows simultaneous training of multiple datasets in addition to makeup datasets. Finally, the performance of proposed method was compared with state-of-art method qualitatively and quantitatively.","PeriodicalId":143744,"journal":{"name":"International Conference on Internet Multimedia Computing and Service","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130989163","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Xuming Wang, Jin Huang, Jia Zhu, Min Yang, Fen Yang
{"title":"Facial expression recognition with deep learning","authors":"Xuming Wang, Jin Huang, Jia Zhu, Min Yang, Fen Yang","doi":"10.1145/3240876.3240908","DOIUrl":"https://doi.org/10.1145/3240876.3240908","url":null,"abstract":"Automatic recognition of facial expression images is a challenge for computer due to variation of expression, background, position and label noise. The paper propose a new method for static facial expression recognition. Main process is to perform experiments by FER-2013 dataset, the primary mission is using our CNN model to classify a set of static images into 7 basic emotions and then achieve effective classification automatically. The two preprocessing of the faces picture have enhanced the effect of the picture for recognition. First, FER datasets are preprocessed with standard histogram eqialization. Then we employ ImageDataGenerator to deviate and rotate the facial image to enhance model robustness. Finally, the result of softmax activation function (also known as multinomial logistic regression) is stacked by SVM. The result of softmax activation function + SVM is better than softmax activation function. The accuracy of facial expression recognition achieve 68.79% on the test set.","PeriodicalId":143744,"journal":{"name":"International Conference on Internet Multimedia Computing and Service","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121342840","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Na Cheng, Tongtong Zhao, Zhengyu Chen, Xianping Fu
{"title":"Enhancement of underwater images by super-resolution generative adversarial networks","authors":"Na Cheng, Tongtong Zhao, Zhengyu Chen, Xianping Fu","doi":"10.1145/3240876.3240881","DOIUrl":"https://doi.org/10.1145/3240876.3240881","url":null,"abstract":"Underwater image enhancement plays an important role in oceanic engineering, while the research is far from enough. The problems like color casts, low contrast brought out by the properties of water and its impurities, make it a challenging task. This paper proposes a novel framework for enhancing underwater image. It includes two parts, that is, pre-processing and de-blurring with improved Super-resolution Generative Adversarial Networks. First, in the process of pre-processing, we use the color correction approach and the contrast enhancement method to compensate color casts and produce natural color images. Second, an improved Super-resolution Generative Adversarial Networks is applied to pre-processed images in order to remove blurring and boost detail. Based on the network, the loss net is modified, so that the pre-processed images will be de-blurred and sharpened. The experimental results show that the proposed strategy improves the quality of underwater images efficiently.","PeriodicalId":143744,"journal":{"name":"International Conference on Internet Multimedia Computing and Service","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116233375","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Shaoning Xiao, Yimeng Li, Yunan Ye, Zhou Zhao, Jun Xiao, Fei Wu, Jiang Zhu, Yueting Zhuang
{"title":"Video question answering via multi-granularity temporal attention network learning","authors":"Shaoning Xiao, Yimeng Li, Yunan Ye, Zhou Zhao, Jun Xiao, Fei Wu, Jiang Zhu, Yueting Zhuang","doi":"10.1145/3240876.3240885","DOIUrl":"https://doi.org/10.1145/3240876.3240885","url":null,"abstract":"This work aims to address the problem of video question answering (VideoQA) with a novel model and a new open-ended VideoQA dataset. VideoQA is a challenging field in visual information retrieval, which generates the answer according to video content and question. The existing works mostly focus on overall frame-level visual understanding to tackle the problem, which neglects finer-grained and temporal information inside the video, or just combines the multi-grained representations simply by concatenation or addition. Thus, we propose the multi-granularity temporal attention network (MGTA-Net) that enables to search for the specific frames in a video that are holistically and locally related to the answer. We first learn the mutual attention representations of multi-grained visual content and question. Then the mutually attended features are combined hierarchically using a double layer LSTM to generate the answer. The effectiveness of our model is demonstrated on the large scale dataset.","PeriodicalId":143744,"journal":{"name":"International Conference on Internet Multimedia Computing and Service","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133853788","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Domain separation network for cross-modal retrieval","authors":"Chenlu Liu, Huimin Lu, Hao Wei, Xing Xu, Yanli Ji","doi":"10.1145/3240876.3240878","DOIUrl":"https://doi.org/10.1145/3240876.3240878","url":null,"abstract":"Recent years, cross-modal retrieval has drawn much attention due to the explosion of multi-media data. Existing approaches always map representations from one modality to the other, or extract invariant features. However, those method ignore the individual characteristics of each modality. In this paper, we explicitly extract representations from two subspace, one is private to each modality and the other is shared across modalities. Moreover, Our model use the partitioned representation to reconstruct the feature of both image and text. Comprehensive experimental results on two widely used benchmark datasets show that the proposed method is superior in learning effective subspace representation.","PeriodicalId":143744,"journal":{"name":"International Conference on Internet Multimedia Computing and Service","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132600737","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ting Rui, Fei Zhou, Fukai Zhang, Dong Wang, Chengsong Yang
{"title":"Research on road semantic segmentation based on hybrid auto-encoder","authors":"Ting Rui, Fei Zhou, Fukai Zhang, Dong Wang, Chengsong Yang","doi":"10.1145/3240876.3240918","DOIUrl":"https://doi.org/10.1145/3240876.3240918","url":null,"abstract":"Road detection is an important part of the environment perception technology of unmanned vehicles. Using computer vision technology to achieve the semantic segmentation of environmental scenes is one of the key technology to ensure the safe driving of unmanned vehicles. In this paper, a hybrid autoencoder semantic segmentation model combining sparse autoencoder and denoising autoencoder is proposed. The model uses sparse autoencoder to conduct sparse semantic encoding and use denoising autoencoder to conduct robust semantic encoding. In this way, the features learned by the model are more conducive for semantic segmentation. Through the deep rich structure semantic segmentation model, an optimized selection of image semantics can be achieved, and further improve the semantic segmentation performance. Experiments show that this model is simpler, with less training time, and better comprehensive segmentation performance.","PeriodicalId":143744,"journal":{"name":"International Conference on Internet Multimedia Computing and Service","volume":"95 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116697974","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}