W
Wei Xu
Researcher at Beijing Normal University
Publications - 8
Citations - 84
Wei Xu is an academic researcher from Beijing Normal University. The author has contributed to research in topics: Computer science & Deep learning. The author has an hindex of 2, co-authored 3 publications receiving 11 citations.
Papers
More filters
Journal ArticleDOI
TransCrowd: weakly-supervised crowd counting with transformers
TL;DR: TransChen et al. as mentioned in this paper reformulated the weakly-supervised crowd counting problem from the perspective of sequence-to-count based on transformers and observed that the proposed TransCrowd can effectively extract the semantic crowd information by using the self-attention mechanism of transformer.
Book ChapterDOI
An End-to-End Transformer Model for Crowd Localization
Dingkang Liang,Wei Xu,Xiang Bai +2 more
TL;DR: Zhang et al. as mentioned in this paper proposed an end-to-end transformer-decoder for crowd localization, which views the crowd localization as a direct set prediction problem, taking extracted features and trainable embeddings as input of the transformerdecoder.
Journal ArticleDOI
DNNBrain: A Unifying Toolbox for Mapping Deep Neural Networks and Brains
TL;DR: DNNBrain is presented, a Python-based toolbox designed for exploring the internal representations of DNNs as well as brains, and it is expected that this toolbox will accelerate scientific research by both applying DNN's to model biological neural systems and utilizing paradigms of cognitive neuroscience to unveil the black box of Dnns.
Posted ContentDOI
DNNBrain: a unifying toolbox for mapping deep neural networks and brains
TL;DR: DNNBrain is presented, a Python-based toolbox designed for exploring internal representations in both DNNs and the brain and expects that this toolbox will accelerate scientific research in applying DNN’s to model biological neural systems and utilizing paradigms of cognitive neuroscience to unveil the black box of Dnns.
Journal ArticleDOI
Numerosity representation in a deep convolutional neural network
TL;DR: This work examined whether the numerosity underestimation effect, a phenomenon indicating that numerosity perception acts upon the perceptual number rather than the physical number, can be observed in deep convolutional neural networks (DCNNs), and found that number-selective units at late layers operated on the perceived number, like humans do.