W
Wei Xu
Researcher at Baidu
Publications - 133
Citations - 28642
Wei Xu is an academic researcher from Baidu. The author has contributed to research in topics: Convolutional neural network & Recurrent neural network. The author has an hindex of 58, co-authored 133 publications receiving 24351 citations. Previous affiliations of Wei Xu include Carnegie Mellon University & Princeton University.
Papers
More filters
Journal ArticleDOI
3D Convolutional Neural Networks for Human Action Recognition
TL;DR: Wang et al. as mentioned in this paper developed a novel 3D CNN model for action recognition, which extracts features from both the spatial and the temporal dimensions by performing 3D convolutions, thereby capturing the motion information encoded in multiple adjacent frames.
Proceedings Article
3D Convolutional Neural Networks for Human Action Recognition
TL;DR: A novel 3D CNN model for action recognition that extracts features from both the spatial and the temporal dimensions by performing 3D convolutions, thereby capturing the motion information encoded in multiple adjacent frames.
Posted Content
Bidirectional LSTM-CRF Models for Sequence Tagging
Zhiheng Huang,Wei Xu,Kai Yu +2 more
TL;DR: This work is the first to apply a bidirectional LSTM CRF model to NLP benchmark sequence tagging data sets and it is shown that the BI-LSTM-CRF model can efficiently use both past and future input features thanks to a biddirectional L STM component.
Proceedings ArticleDOI
Document clustering based on non-negative matrix factorization
Wei Xu,Xin Liu,Yihong Gong +2 more
TL;DR: This paper proposes a novel document clustering method based on the non-negative factorization of the term-document matrix of the given document corpus that surpasses the latent semantic indexing and the spectral clustering methods not only in the easy and reliable derivation of document clustered results, but also in document clusters accuracies.
Proceedings Article
Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN)
TL;DR: The m-RNN model directly models the probability distribution of generating a word given previous words and an image, and achieves significant performance improvement over the state-of-the-art methods which directly optimize the ranking objective function for retrieval.