Results 271 to 280 of about 90,690 (297)
Some of the next articles are maybe not open access.
International Journal of Grid and High Performance Computing, 2020
The volume of data in diverse data formats from various data sources has led the way for a new drift in the digital world, Big Data. This article proposes sl-LSTM (sequence labelling LSTM), a neural network architecture that combines the effectiveness of typical LSTM models to perform sequence labeling tasks.
Nancy Victor, Daphne Lopez
openaire +1 more source
The volume of data in diverse data formats from various data sources has led the way for a new drift in the digital world, Big Data. This article proposes sl-LSTM (sequence labelling LSTM), a neural network architecture that combines the effectiveness of typical LSTM models to perform sequence labeling tasks.
Nancy Victor, Daphne Lopez
openaire +1 more source
Host–Parasite: Graph LSTM-in-LSTM for Group Activity Recognition
IEEE Transactions on Neural Networks and Learning Systems, 2021This article aims to tackle the problem of group activity recognition in the multiple-person scene. To model the group activity with multiple persons, most long short-term memory (LSTM)-based methods first learn the person-level action representations by several LSTMs and then integrate all the person-level action representations into the following ...
Xiangbo Shu +3 more
openaire +2 more sources
Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2020
Misinformation in social media - such as fake news, rumors, or other forms of deceptive content - poses a significant threat to society and, hence, scalable strategies for an early detection of online cascades with misinformation are in dire need. The prominent approach in detecting online cascades with misinformation builds upon neural networks based ...
Francesco Ducci +2 more
openaire +1 more source
Misinformation in social media - such as fake news, rumors, or other forms of deceptive content - poses a significant threat to society and, hence, scalable strategies for an early detection of online cascades with misinformation are in dire need. The prominent approach in detecting online cascades with misinformation builds upon neural networks based ...
Francesco Ducci +2 more
openaire +1 more source
The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, 2018
Search task identification aims to understand a user's information needs to improve search quality for applications such as query suggestion, personalized search, and advertisement retrieval. To properly identify the search task within long query sessions, it is important to partition these sessions into segments before further processing.
Cong Du, Peng Shu, Yong Li
openaire +1 more source
Search task identification aims to understand a user's information needs to improve search quality for applications such as query suggestion, personalized search, and advertisement retrieval. To properly identify the search task within long query sessions, it is important to partition these sessions into segments before further processing.
Cong Du, Peng Shu, Yong Li
openaire +1 more source
ACM Transactions on Multimedia Computing, Communications, and Applications, 2019
Detection of scene text in arbitrary shapes is a challenging task in the field of computer vision. Most existing scene text detection methods exploit the rectangle/quadrangular bounding box to denote the detected text, which fails to accurately fit text with arbitrary shapes, such as curved text. In addition, recent progress on scene text detection has
Zhandong Liu, Wengang Zhou, Houqiang Li
openaire +1 more source
Detection of scene text in arbitrary shapes is a challenging task in the field of computer vision. Most existing scene text detection methods exploit the rectangle/quadrangular bounding box to denote the detected text, which fails to accurately fit text with arbitrary shapes, such as curved text. In addition, recent progress on scene text detection has
Zhandong Liu, Wengang Zhou, Houqiang Li
openaire +1 more source
2023
The world wide web (WWW) is an advanced system with an unmatched amount of digital data. Today's internet usage is accessible through common search engines like Google and Yahoo. Cybercriminals have become more assertive on social media. As a result, numerous commercial and trade websites are hacked, leading to forced trafficking of women and children ...
Anil Kumar +3 more
openaire +1 more source
The world wide web (WWW) is an advanced system with an unmatched amount of digital data. Today's internet usage is accessible through common search engines like Google and Yahoo. Cybercriminals have become more assertive on social media. As a result, numerous commercial and trade websites are hacked, leading to forced trafficking of women and children ...
Anil Kumar +3 more
openaire +1 more source
Proceedings of the 7th International Conference on Human-Agent Interaction, 2019
While many works involving human-agent interactions have focused on individuals or crowds, modelling interactions on the group scale has not been considered in depth. Simulation of interactions with groups of agents is vital in many applications, enabling more comprehensive and realistic behavior encompassing all possibilities between crowd and ...
Fangkai Yang, Christopher Peters
openaire +1 more source
While many works involving human-agent interactions have focused on individuals or crowds, modelling interactions on the group scale has not been considered in depth. Simulation of interactions with groups of agents is vital in many applications, enabling more comprehensive and realistic behavior encompassing all possibilities between crowd and ...
Fangkai Yang, Christopher Peters
openaire +1 more source
Proceedings of the 56th Annual Design Automation Conference 2019, 2019
Various models with Long Short-Term Memory (LSTM) network have demonstrated prior art performances in sequential information processing. Previous LSTM-specific architectures set large on-chip memory for weight storage to alleviate the memory-bound issue and facilitate the LSTM inference in cloud computing. In this paper, E-LSTM is proposed for embedded
Runbin Shi +4 more
openaire +1 more source
Various models with Long Short-Term Memory (LSTM) network have demonstrated prior art performances in sequential information processing. Previous LSTM-specific architectures set large on-chip memory for weight storage to alleviate the memory-bound issue and facilitate the LSTM inference in cloud computing. In this paper, E-LSTM is proposed for embedded
Runbin Shi +4 more
openaire +1 more source
IA-LSTM: Interaction-Aware LSTM for Pedestrian Trajectory Prediction
IEEE Transactions on CyberneticsPredicting the trajectory of pedestrians in crowd scenarios is indispensable in self-driving or autonomous mobile robot field because estimating the future locations of pedestrians around is beneficial for policy decision to avoid collision. It is a challenging issue because humans have different walking motions, and the interactions between humans and
Jing Yang +4 more
openaire +2 more sources