Pub Date : 2019-10-01DOI: 10.1109/SIBGRAPI-T.2019.00007
M. Pias, S. Botelho, Paulo L. J. Drews-Jr
This paper explores Domain-Specific Deep Learning Architectures for GPU Computer Vision through a "brainstorming" approach on selected hands-on topics in the area. We intend to discuss Deep Neural Networks (DNNs) to image classification problems through tools, frameworks and data pipelines commonly used to train and deploy DNNs in GPUs and Domain-Specific Architectures (DSAs).
{"title":"Perfect Storm: DSAs Embrace Deep Learning for GPU-Based Computer Vision","authors":"M. Pias, S. Botelho, Paulo L. J. Drews-Jr","doi":"10.1109/SIBGRAPI-T.2019.00007","DOIUrl":"https://doi.org/10.1109/SIBGRAPI-T.2019.00007","url":null,"abstract":"This paper explores Domain-Specific Deep Learning Architectures for GPU Computer Vision through a \"brainstorming\" approach on selected hands-on topics in the area. We intend to discuss Deep Neural Networks (DNNs) to image classification problems through tools, frameworks and data pipelines commonly used to train and deploy DNNs in GPUs and Domain-Specific Architectures (DSAs).","PeriodicalId":371584,"journal":{"name":"2019 32nd SIBGRAPI Conference on Graphics, Patterns and Images Tutorials (SIBGRAPI-T)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126463755","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}
Pub Date : 2019-10-01DOI: 10.1109/sibgrapi-t.2019.00005
{"title":"Message from the Tutorial Program Chairs","authors":"","doi":"10.1109/sibgrapi-t.2019.00005","DOIUrl":"https://doi.org/10.1109/sibgrapi-t.2019.00005","url":null,"abstract":"","PeriodicalId":371584,"journal":{"name":"2019 32nd SIBGRAPI Conference on Graphics, Patterns and Images Tutorials (SIBGRAPI-T)","volume":"131 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122655978","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}
Pub Date : 2019-10-01DOI: 10.1109/SIBGRAPI-T.2019.00009
M. Silva, W. Ramos, Alan C. Neves, Edson Roteia Araujo Junior, M. Campos, E. R. Nascimento
The emergence of low-cost, high-quality personal wearable cameras combined with a large and increasing storage capacity of video-sharing websites have evoked a growing interest in first-person videos. A First-Person Video is usually composed of monotonous long-running unedited streams captured by a device attached to the user body, which makes it visually unpleasant and tedious to watch. Thus, there is a rise in the need to provide quick access to the information therein. In the last few years, a popular approach to retrieve the information from videos is to produce a short version of the input video by creating a video summary; however, this approach disrupts the temporal context of the recording. Fast-Forward is another approach that creates a shorter version of the video preserving the video context by increasing its playback speed. Although Fast-Forward methods keep the recording story, they do not consider the semantic load of the input video. The Semantic Fast-Forward approach creates a shorter version of First-Person Videos dealing with both video context and emphasis of the relevant portions to keep the semantic load of the input video. In this paper, we present a review of the representative methods in both fast-forward and semantic fast-forward methods and discuss the future directions of the area.
{"title":"Fast-Forward Methods for Egocentric Videos: A Review","authors":"M. Silva, W. Ramos, Alan C. Neves, Edson Roteia Araujo Junior, M. Campos, E. R. Nascimento","doi":"10.1109/SIBGRAPI-T.2019.00009","DOIUrl":"https://doi.org/10.1109/SIBGRAPI-T.2019.00009","url":null,"abstract":"The emergence of low-cost, high-quality personal wearable cameras combined with a large and increasing storage capacity of video-sharing websites have evoked a growing interest in first-person videos. A First-Person Video is usually composed of monotonous long-running unedited streams captured by a device attached to the user body, which makes it visually unpleasant and tedious to watch. Thus, there is a rise in the need to provide quick access to the information therein. In the last few years, a popular approach to retrieve the information from videos is to produce a short version of the input video by creating a video summary; however, this approach disrupts the temporal context of the recording. Fast-Forward is another approach that creates a shorter version of the video preserving the video context by increasing its playback speed. Although Fast-Forward methods keep the recording story, they do not consider the semantic load of the input video. The Semantic Fast-Forward approach creates a shorter version of First-Person Videos dealing with both video context and emphasis of the relevant portions to keep the semantic load of the input video. In this paper, we present a review of the representative methods in both fast-forward and semantic fast-forward methods and discuss the future directions of the area.","PeriodicalId":371584,"journal":{"name":"2019 32nd SIBGRAPI Conference on Graphics, Patterns and Images Tutorials (SIBGRAPI-T)","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126237397","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}
Pub Date : 2019-10-01DOI: 10.1109/SIBGRAPI-T.2019.00010
R. Ribani, M. Marengoni
Transfer learning is an emerging topic that may drive the success of machine learning in research and industry. The lack of data on specific tasks is one of the main reasons to use it, since collecting and labeling data can be very expensive and can take time, and recent concerns with privacy make difficult to use real data from users. The use of transfer learning helps to fast prototype new machine learning models using pre-trained models from a source task since training on millions of images can take time and requires expensive GPUs. In this survey, we review the concepts and definitions related to transfer learning and we list the different terms used in the literature. We bring the point of view from different authors of prior surveys, adding some more recent findings in order to give a clear vision of directions for future work in this field of research.
{"title":"A Survey of Transfer Learning for Convolutional Neural Networks","authors":"R. Ribani, M. Marengoni","doi":"10.1109/SIBGRAPI-T.2019.00010","DOIUrl":"https://doi.org/10.1109/SIBGRAPI-T.2019.00010","url":null,"abstract":"Transfer learning is an emerging topic that may drive the success of machine learning in research and industry. The lack of data on specific tasks is one of the main reasons to use it, since collecting and labeling data can be very expensive and can take time, and recent concerns with privacy make difficult to use real data from users. The use of transfer learning helps to fast prototype new machine learning models using pre-trained models from a source task since training on millions of images can take time and requires expensive GPUs. In this survey, we review the concepts and definitions related to transfer learning and we list the different terms used in the literature. We bring the point of view from different authors of prior surveys, adding some more recent findings in order to give a clear vision of directions for future work in this field of research.","PeriodicalId":371584,"journal":{"name":"2019 32nd SIBGRAPI Conference on Graphics, Patterns and Images Tutorials (SIBGRAPI-T)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123825625","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：