5 citations · 12 across the 14 of their papers we have counts for
14 papers
Scalpel: Fine-Grained Alignment of Attention Activation Manifolds via Mixture Gaussian Bridges to Mitigate Multimodal Hallucination
Ziqiang Shi, Rujie Liu, Shanshan Yu +2
Rapid progress in large vision-language models (LVLMs) has achieved unprecedented performance in vision-language tasks. However, due to the strong prior of large language models (L…
SchröMind: Mitigating Hallucinations in Multimodal Large Language Models via Solving the Schrödinger Bridge Problem
Ziqiang Shi, Rujie Liu, Shanshan Yu +2
Recent advancements in Multimodal Large Language Models (MLLMs) have achieved significant success across various domains. However, their use in high-stakes fields like healthcare r…
Generative Modelling with High-Order Langevin Dynamics
Ziqiang Shi, Rujie Liu
Diffusion generative modelling (DGM) based on stochastic differential equations (SDEs) with score matching has achieved unprecedented results in data generation. In this paper, we…
Multi-modal Affect Analysis using standardized data within subjects in the Wild
Sachihiro Youoku, Takahisa Yamamoto, Junya Saito +7
Human affective recognition is an important factor in human-computer interaction. However, the method development with in-the-wild data is not yet accurate enough for practical usa…
HiCOMEX: Facial Action Unit Recognition Based on Hierarchy Intensity Distribution and COMEX Relation Learning
Ziqiang Shi, Liu Liu, Zhongling Liu +3
The detection of facial action units (AUs) has been studied as it has the competition due to the wide-ranging applications thereof. In this paper, we propose a novel framework for…
SingCubic: Cyclic Incremental Newton-type Gradient Descent with Cubic Regularization for Non-Convex Optimization
Ziqiang Shi
In this work, we generalized and unified two recent completely different works of~\cite{shi2015large} and~\cite{cartis2012adaptive} respectively into one by proposing the cyclic in…
Hodge and Podge: Hybrid Supervised Sound Event Detection with Multi-Hot MixMatch and Composition Consistence Training
Ziqiang Shi, Liu Liu, Huibin Lin +1
In this paper, we propose a method called Hodge and Podge for sound event detection. We demonstrate Hodge and Podge on the dataset of Detection and Classification of Acoustic Scene…
HODGEPODGE: Sound event detection based on ensemble of semi-supervised learning methods
Ziqiang Shi, Liu Liu, Huibin Lin +2
In this paper, we present a method called HODGEPODGE\footnotemark[1] for large-scale detection of sound events using weakly labeled, synthetic, and unlabeled data proposed in the D…
A Double Joint Bayesian Approach for J-Vector Based Text-dependent Speaker Verification
Ziqiang Shi, Mengjiao Wang, Liu Liu +2
J-vector has been proved to be very effective in text-dependent speaker verification with short-duration speech. However, the current state-of-the-art back-end classifiers, e.g. jo…
Multi-view (Joint) Probability Linear Discrimination Analysis for Multi-view Feature Verification
Ziqiang Shi, Liu Liu, Mengjiao Wang +1
Multi-view feature has been proved to be very effective in many multimedia applications. However, the current back-end classifiers cannot make full use of such features. In this pa…
A better convergence analysis of the block coordinate descent method for large scale machine learning
Ziqiang Shi, Rujie Liu
This paper considers the problems of unconstrained minimization of large scale smooth convex functions having block-coordinate-wise Lipschitz continuous gradients. The block coordi…
Empirical study of PROXTONE and PROXTONE for Fast Learning of Large Scale Sparse Models
Ziqiang Shi, Rujie Liu
PROXTONE is a novel and fast method for optimization of large scale non-smooth convex problem \cite{shi2015large}. In this work, we try to use PROXTONE method in solving large scal…
Proximal Stochastic Newton-type Gradient Descent Methods for Minimizing Regularized Finite Sums
Ziqiang Shi
In this work, we generalized and unified recent two completely different works of Jascha \cite{sohl2014fast} and Lee \cite{lee2012proximal} respectively into one by proposing the \…
Online and Stochastic Universal Gradient Methods for Minimizing Regularized Hölder Continuous Finite Sums
Ziqiang Shi, Rujie Liu
Online and stochastic gradient methods have emerged as potent tools in large scale optimization with both smooth convex and nonsmooth convex problems from the classes $C^{1,1}(\rea…