arXiv subjects

Jian Xue

Publications and source records attributed to Jian Xue.

41 records · Page 3Linked to original sources

arXiv2021

FEAFA+: An Extended Well-Annotated Dataset for Facial Expression Analysis and 3D Facial Animation

Nearly all existing Facial Action Coding System-based datasets that include facial action unit (AU) intensity information annotate the intensity values hierarchically using A--E levels. However, facial expressions change continuously and shift smoothly from one state to another. Therefore, it is more effective to regress the intensity value of local facial AUs to represent whole facial expression changes, particularly in the fields of expression transfer and facial animation. We introduce an extension of FEAFA in combination with the relabeled DISFA database, which is available at https://www.iiplab.net/feafa+/ now. Extended FEAFA (FEAFA+) includes 150 video sequences from FEAFA and DISFA, with a total of 230,184 frames being manually annotated on floating-point intensity value of 24 redefined AUs using the Expression Quantitative Tool. We also list crude numerical results for posed and spontaneous subsets and provide a baseline comparison for the AU intensity regression task.

cs.CV↗

arXiv2021

On Addressing Practical Challenges for RNN-Transducer

In this paper, several works are proposed to address practical challenges for deploying RNN Transducer (RNN-T) based speech recognition system. These challenges are adapting a well-trained RNN-T model to a new domain without collecting the audio data, obtaining time stamps and confidence scores at word level. The first challenge is solved with a splicing data method which concatenates the speech segments extracted from the source domain data. To get the time stamp, a phone prediction branch is added to the RNN-T model by sharing the encoder for the purpose of force alignment. Finally, we obtain word-level confidence scores by utilizing several types of features calculated during decoding and from confusion network. Evaluated with Microsoft production data, the splicing data adaptation method improves the baseline and adaptation with the text to speech method by 58.03% and 15.25% relative word error rate reduction, respectively. The proposed time stamping method can get less than 50ms word timing difference from the ground truth alignment on average while maintaining the recognition accuracy of the RNN-T model. We also obtain high confidence annotation performance with limited computation cost.

eess.AS↗

arXiv2021

Speedup of the Quantum Adiabatic Algorithm using Delocalization Catalysis

We propose a method to speed up the quantum adiabatic algorithm using catalysis by many-body delocalization. This is applied to random-field antiferromagnetic Ising spin models. The algorithm is catalyzed in such a way that the evolution approximates a Heisenberg model in the middle of its course, and the model is in a delocalized phase. We show numerically that we can speed up the standard algorithm for finding the ground state of the random-field Ising model using this idea. We also demonstrate that the speedup is due to gap amplification, even though the underlying model is not frustration-free. The crossover to speedup occurs at roughly the value of the interaction which is known to be the critical one for the delocalization transition. We also calculate the participation ratio and entanglement entropy as a function of time: their time dependencies indicate that the system is exploring more states and that they are more entangled than when there is no catalyst. Together, all these pieces of evidence demonstrate that the speedup is related to delocalization. Even though only relatively small systems can be investigated, the evidence suggests that the scaling of the method with system size is favorable. Our method is illustrated by experimental results from a small online IBM quantum computer, showing how to verify the method in future as such machines improve. The cost of the catalytic method compared to the standard algorithm is only a constant factor.

quant-ph↗

arXiv2019

FEAFA: A Well-Annotated Dataset for Facial Expression Analysis and 3D Facial Animation

Facial expression analysis based on machine learning requires large number of well-annotated data to reflect different changes in facial motion. Publicly available datasets truly help to accelerate research in this area by providing a benchmark resource, but all of these datasets, to the best of our knowledge, are limited to rough annotations for action units, including only their absence, presence, or a five-level intensity according to the Facial Action Coding System. To meet the need for videos labeled in great detail, we present a well-annotated dataset named FEAFA for Facial Expression Analysis and 3D Facial Animation. One hundred and twenty-two participants, including children, young adults and elderly people, were recorded in real-world conditions. In addition, 99,356 frames were manually labeled using Expression Quantitative Tool developed by us to quantify 9 symmetrical FACS action units, 10 asymmetrical (unilateral) FACS action units, 2 symmetrical FACS action descriptors and 2 asymmetrical FACS action descriptors, and each action unit or action descriptor is well-annotated with a floating point number between 0 and 1. To provide a baseline for use in future research, a benchmark for the regression of action unit values based on Convolutional Neural Networks are presented. We also demonstrate the potential of our FEAFA dataset for 3D facial animation. Almost all state-of-the-art algorithms for facial animation are achieved based on 3D face reconstruction. We hence propose a novel method that drives virtual characters only based on action unit value regression of the 2D video frames of source actors.

cs.LG↗

arXiv2017

Quantum phase transition in a multiconnected Jaynes-Cummings lattice

The rapid progress in quantum technology enables the implementation of artificial many-body systems with correlated photons and polaritons. A multiconnected Jaynes-Cummings (MCJC) lattice can be constructed by connecting qubits and cavities alternatively. Such kind of models can be realized with superconducting qubits coupled to superconducting microwave resonators or with quantum dots coupled to optical nanocavities. We study physical properties of the one-dimensional MCJC lattice using the density-matrix renormalization group method. This model has an intrinsic symmetry between the left and right qubit-cavity couplings. The competition between these couplings may drive the ground state either to a Mott-insulating or to a superfluid phase at an integer filling. We calculate the single-particle and density-density correlation functions, the correlation lengths in the Mott-insulating phase and the Luttinger parameters in the superfluid phase, and determine accurately the critical points that separate these two phases.

quant-ph↗