An empirical study of pre-trained language models in simple knowledge graph question answeringSpringer Science and Business Media LLC - Tập 26 - Trang 2855-2886 - 2023
Nan Hu, Yike Wu, Guilin Qi, Dehai Min, Jiaoyan Chen, Jeff Z Pan, Zafar Ali
Large-scale pre-trained language models (PLMs) such as BERT have recently achieved great success and become a milestone in natural language processing (NLP). It is now the consensus of the NLP community to adopt PLMs as the backbone for downstream tasks. In recent works on knowledge graph question answering (KGQA), BERT or its variants have become necessary in their KGQA models. However, there is ...... hiện toàn bộ
From constrained to unconstrained datasets: an evaluation of local action descriptors and fusion strategies for interaction recognitionSpringer Science and Business Media LLC - Tập 19 - Trang 265-276 - 2015
Chenqiang Gao, Luyu Yang, Yinhe Du, Zeming Feng, Jiang Liu
As an important task in computer vision, the interaction recognition has attracted extensive attention due to its widely potential applications. The existing methods mainly focus on the interaction recognition problem on constrained datasets with few variations of scenes, viewpoints, background clutter for the experimental purpose. The performance of the recently proposed methods on the available ...... hiện toàn bộ
Distributed Context Monitoring for the Adaptation of Continuous ServicesSpringer Science and Business Media LLC - Tập 10 - Trang 503-528 - 2007
Claudio Bettini, Dario Maggiorini, Daniele Riboni
This paper describes a middleware designed for distributed context acquisition and reconciliation intended to support the adaptation of continuous Internet services, like e.g., multimedia streaming. These services persist in time, and are characterized by multiple transmissions of data by the service provider, as a result of a single request from the user. Adapting these services to the current co...... hiện toàn bộ
Spatiotemporal contrastive modeling for video moment retrievalSpringer Science and Business Media LLC - Tập 26 - Trang 1525-1544 - 2022
Yi Wang, Kun Li, Guoliang Chen, Yan Zhang, Dan Guo, Meng Wang
With the rapid development of social networks, video data has been growing explosively. As one of the important social mediums, spatiotemporal characteristics of videos have attracted considerable attention in recommendation system and video understanding. In this paper, we discuss the video moment retrieval (VMR) task, which locates moments in a video based on different textual queries. Existing ...... hiện toàn bộ
A study of homophily on social mediaSpringer Science and Business Media LLC - Tập 15 - Trang 213-232 - 2011
Halil Bisgin, Nitin Agarwal, Xiaowei Xu
The fact that similarity breeds connections, the principle of homophily, has been well-studied in existing sociology literature. Several studies have observed this phenomenon by conducting surveys on human subjects. These studies have concluded that new ties are formed between similar individuals. This phenomenon has been used to explain several socio-psychological concepts such as, segregation, c...... hiện toàn bộ
Trustworthy service composition with secure data transmission in sensor networksSpringer Science and Business Media LLC - Tập 21 - Trang 185-200 - 2017
Tao Zhang, Lele Zheng, Yongzhi Wang, Yulong Shen, Ning Xi, Jianfeng Ma, Jianming Yong
As the basis of the Internet of Things (IoT), sensor networks have materialized its computation and communication capability into anything in our modern lives. Service composition provides us a promising way to cooperate various sensors to build more powerful IoT applications over sensor networks. However, the limited capability of sensor node poses great challenges not only to trustworthy service...... hiện toàn bộ
FedAda: Fast-convergent adaptive federated learning in heterogeneous mobile edge computing environmentSpringer Science and Business Media LLC - Tập 25 - Trang 1971-1998 - 2022
Jinghui Zhang, Xinyu Cheng, Cheng Wang, Yuchen Wang, Zhan Shi, Jiahui Jin, Aibo Song, Wei Zhao, Liangsheng Wen, Tingting Zhang
With rapid advancement of Internet of Things (IoT) and social networking applications generating large amounts of data at or close to the network edge, Mobile Edge Computing (MEC) has naturally been proposed to bring model training closer to where data is produced. However, there still exists privacy concern since typical MEC frameworks need to transfer sensitive data resources from data collectio...... hiện toàn bộ
What have we learned from OpenReview?Springer Science and Business Media LLC - Tập 26 - Trang 683-708 - 2022
Gang Wang, Qi Peng, Yanfeng Zhang, Mingyang Zhang
Anonymous peer review is used by the great majority of computer science conferences. OpenReview is such a platform that aims to promote openness in peer review process. The paper, (meta) reviews, rebuttals, and final decisions are all released to public. We collect 11,915 submissions and their 41,276 reviews from the OpenReview platform. We also collect these submissions’ citation data from Google...... hiện toàn bộ
Attention based hierarchical LSTM network for context-aware microblog sentiment classificationSpringer Science and Business Media LLC - Tập 22 - Trang 59-81 - 2018
Shi Feng, Yang Wang, Liran Liu, Daling Wang, Ge Yu
Analyzing sentiment polarities of microblog has become a hot research topic for both academic and industrial communities. Most of the existing algorithms regard each microblog as an independent training instance. However, the sentiments embedded in short tweets are usually ambiguous and context-aware. Even a non-sentiment word might convey a clear emotional tendency in certain microblog conversati...... hiện toàn bộ