Moreover, the proposed point cloud quality metric exploits the best performing 2D quality metrics in the literature to assess the quality of the projected images.
Ranked #1 on Point Cloud Quality Assessment on M-PCCD
We validate the performance of our proposed architecture in the context of two multi-perspective visual recognition tasks namely lip reading and face recognition.
A subset of the in the wild dataset contains facial images with different expressions, annotated for usage in the context of face expression recognition tests.
We address this problem with a novel QE method that is more faithful to deductive reasoning, and show that this leads to better performance on complex queries to incomplete KBs.
In this context, this paper proposes two novel LSTM cell architectures that are able to jointly learn from multiple sequences simultaneously acquired, targeting to create richer and more effective models for recognition tasks.
In a world where security issues have been gaining growing importance, face recognition systems have attracted increasing attention in multiple application areas, ranging from forensics and surveillance to commerce and entertainment.
This paper proposes a double-deep spatio-angular learning framework for light field based face recognition, which is able to learn both texture and angular dynamics in sequence using convolutional representations; this is a novel recognition framework that has never been proposed before for either face recognition or any other visual recognition task.
In experiments on the one billion words language modeling benchmark, we are able to slightly improve on our previous results which use a different loss function, and employ leave-one-out training on a subset of the main training set.
We apply this new method to learn ﬁrst-order HMMs for unsupervised part-of-speech (POS) tagging, and show that HMMs learned this way consistently and signiﬁcantly out-performs both EM-trained HMMs, and HMMs with a sparsity-inducing Dirichlet prior trained by variational EM.
Confidence-weighted (CW) learning , an online learning method for linear classifiers, maintains a Gaussian distributions over weight vectors, with a covariance matrix that represents uncertainty about weights and correlations.
Automatic sentiment classification has been extensively studied and applied in recent years.