面向bilibili短视频评论数据的情感分析,旨在挖掘视频观看者对短视频的看法,使视频作者也可以快速得到自己想要的评价,进而对后续作品做出改进。针对短视频评论更新快、词汇新颖、评论过长、一词多义等因素造成的短视频评论情感分析准...面向bilibili短视频评论数据的情感分析,旨在挖掘视频观看者对短视频的看法,使视频作者也可以快速得到自己想要的评价,进而对后续作品做出改进。针对短视频评论更新快、词汇新颖、评论过长、一词多义等因素造成的短视频评论情感分析准确率低的问题,文章构建了bilibili短视频评论数据集,并提出了ELMO(Embedding From Language Model)用以构建动态词向量解决一词多义及新词的问题,通过构建TextCNN和Reformer双通道神经网络结构来提取局部、全局特征。由于Reformer采用了局部敏感哈希的特殊注意力机制,更能联系全局特征,之后将两者得到的结果拼接送入分类器得出情感分析的结果,并将得出的结果与多个深度学习模型进行对比。展开更多
To achieve an optimal trade-off between video quality and energy efficiency in the uplink streaming of multi-user Scalable Video Coding (SVC) videos in relay-based Orthogonal Frequency Division Multiple Access (OFDMA)...To achieve an optimal trade-off between video quality and energy efficiency in the uplink streaming of multi-user Scalable Video Coding (SVC) videos in relay-based Orthogonal Frequency Division Multiple Access (OFDMA) cellular networks, a cross-layer design framework that jointly selects the Transmission Policy (TP) for SVC video frames, assigns OFDMA subcarriers, and allocates power for each subcarrier is proposed. We apply the dual decomposition method to the problem, and obtain a TP selection subproblem for each SVC video adaptation and a resource allocation subproblem of Joint Subcarrier, Relay and Power Allocation (JSRPA). A second level of dual decomposition is used to divide the JSRPA problem into independent subcarrier subproblems. The proposed Crosslayer Trade-off Optimization (CTO) algorithm is sub-distributed with significantly low complexity. A performance evaluation with typical SVC video traces demonstrates that the proposed algorithm is able to converge and efficiently achieve the optimal trade-off between the video quality and energy consumption at the MSs for uplink SVC streaming.展开更多
文摘面向bilibili短视频评论数据的情感分析,旨在挖掘视频观看者对短视频的看法,使视频作者也可以快速得到自己想要的评价,进而对后续作品做出改进。针对短视频评论更新快、词汇新颖、评论过长、一词多义等因素造成的短视频评论情感分析准确率低的问题,文章构建了bilibili短视频评论数据集,并提出了ELMO(Embedding From Language Model)用以构建动态词向量解决一词多义及新词的问题,通过构建TextCNN和Reformer双通道神经网络结构来提取局部、全局特征。由于Reformer采用了局部敏感哈希的特殊注意力机制,更能联系全局特征,之后将两者得到的结果拼接送入分类器得出情感分析的结果,并将得出的结果与多个深度学习模型进行对比。
基金Shanghai Science and Technology Commission (21511101200)National Natural Science Foundation of China (72192821)+3 种基金Shanghai Sailing Program (22YF1420300)CCF-Tencent Open Research Fund (RAGR20220121)Young Elite Scientists Sponsorship Program by CAST (2022QNRC001)National Natural Science Foundation of China (62302297)。
基金partially supported by the National Natural Science Foundation of China under Grants No. 610202380, No. 60932007Major Program of National Natural Science Foundation of China under Grant No. 60932007+2 种基金Tianjin Research Program of Application Foundation and Advanced Technology under Grant No. 12JCQNJC00300Research Fund for the Doctoral Program of Higher Education of China under Grant No. 20110032120029the Innovation Foundation of Tianjin University
文摘To achieve an optimal trade-off between video quality and energy efficiency in the uplink streaming of multi-user Scalable Video Coding (SVC) videos in relay-based Orthogonal Frequency Division Multiple Access (OFDMA) cellular networks, a cross-layer design framework that jointly selects the Transmission Policy (TP) for SVC video frames, assigns OFDMA subcarriers, and allocates power for each subcarrier is proposed. We apply the dual decomposition method to the problem, and obtain a TP selection subproblem for each SVC video adaptation and a resource allocation subproblem of Joint Subcarrier, Relay and Power Allocation (JSRPA). A second level of dual decomposition is used to divide the JSRPA problem into independent subcarrier subproblems. The proposed Crosslayer Trade-off Optimization (CTO) algorithm is sub-distributed with significantly low complexity. A performance evaluation with typical SVC video traces demonstrates that the proposed algorithm is able to converge and efficiently achieve the optimal trade-off between the video quality and energy consumption at the MSs for uplink SVC streaming.