Laycock, Robin Cross, Alana J Lourenco, Tomas Crewther, Sheila G
Published in
Behavioral and Brain Functions
BackgroundAlthough the ventral visual stream is understood to be responsible for object recognition, it has been proposed that the dorsal stream may contribute to object recognition by rapidly activating parietal attention mechanisms, prior to ventral stream object processing.MethodsTo investigate the relative contribution of the dorsal visual stre...
Simonnet, Edwin
This article explores the use of neural networks, a supervised classification method, to perform a task of spoken language understanding in order to treat automatically user requests over the phone. First the spoken language understanding is defined inside the process chain of automatically treating a user request going from recording the request t...
Ostmeyer, Jared Cowell, Lindsay
Published in
Neurocomputing
Recurrent Neural Networks (RNN) are a type of statistical model designed to handle sequential data. The model reads a sequence one symbol at a time. Each symbol is processed based on information collected from the previous symbols. With existing RNN architectures, each symbol is processed using only information from the previous processing step. To...
Sun, Zhu (author) Yang, J. (author) Zhang, J. (author) Bozzon, A. (author) Huang, Long Kai (author) Xu, Chi (author)
Knowledge graphs (KGs) have proven to be effective to improve recommendation. Existing methods mainly rely on hand-engineered features from KGs (e.g., meta paths), which requires domain knowledge. This paper presents RKGE, a KG embedding approach that automatically learns semantic representations of both entities and paths between entities for char...
Gu, Yue Li, Xinyu Huang, Kaixiang Fu, Shiyu Yang, Kangning Chen, Shuhong Zhou, Moliang Marsic, Ivan
Published in
Proceedings of the ... ACM International Conference on Multimedia, with co-located Symposium & Workshops. ACM International Conference on Multimedia
Human conversation analysis is challenging because the meaning can be expressed through words, intonation, or even body language and facial expression. We introduce a hierarchical encoder-decoder structure with attention mechanism for conversation analysis. The hierarchical encoder learns word-level features from video, audio, and text data that ar...
Zhang, Weiting Yang, Dong Wang, Hongchao Zhang, Jun Gidlund, Mikael
Accurate and real-time perception of the operating status of rolling bearings, which constitute a key component of rotating machinery, is of vital significance. However, most existing solutions not only require substantial expertise to conduct feature engineering, but also seldom consider the temporal correlation of sensor sequences, ultimately lea...
Guo, Siwen Höhn, Sviatlana Schommer, Christoph
This paper concerns personalized sentiment analysis, which aims at improving the prediction of the sentiment expressed in a piece of text by considering individualities. Mostly, this is done by relating to a person’s past expressions (or opinions), however the time gaps between the messages are not considered in the existing works. We argue that th...
Li, Jiahui (author)
A cross-domain visual place recognition (VPR) task is proposed in this work, i.e., matching images of the same architectures depicted in different domains. VPR is commonly treated as an image retrieval task, where a query image from an unknown location is matched with relevant instances from geo-tagged gallery database. Different from conventional ...
Gu, Yue Lyu, Xinyu Sun, Weijia Li, Weitian Chen, Shuhong Li, Xinyu Ivan, Marsic
Published in
Proceedings of the ... ACM International Conference on Multimedia, with co-located Symposium & Workshops. ACM International Conference on Multimedia
Emotion recognition in dyadic communication is challenging because: 1. Extracting informative modality-specific representations requires disparate feature extractor designs due to the heterogenous input data formats. 2. How to effectively and efficiently fuse unimodal features and learn associations between dyadic utterances are critical to the mod...
Isunza Navarro, Abgeiba Yaroslava
Just-In-Time Software Defect Prediction (JIT-DP) focuses on predicting errors in software at change-level with the objective of helping developers identify defects while the development process is still ongoing, and improving the quality of software applications. This work studies deep learning techniques by applying attention mechanisms that have ...
