15 citations · 52 across the 24 of their papers we have counts for
24 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…
Attention to details, logits to truth: visual-aware attention and logits enhancement to mitigate hallucinations in LVLMs
Jingyi Wang, Fei Li, Rujie Liu
Existing Large Vision-Language Models (LVLMs) exhibit insufficient visual attention, leading to hallucinations. To alleviate this problem, some previous studies adjust and amplify…
Human Identification at a Distance: Challenges, Methods and Results on the Competition HID 2025
Jingzhe Ma, Meng Zhang, Jianlong Yu +34
Human identification at a distance (HID) is challenging because traditional biometric modalities such as face and fingerprints are often difficult to acquire in real-world scenario…
RTAT: A Robust Two-stage Association Tracker for Multi-Object Tracking
Song Guo, Rujie Liu, Narishige Abe
Data association is an essential part in the tracking-by-detection based Multi-Object Tracking (MOT). Most trackers focus on how to design a better data association strategy to imp…
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…
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…
Speech Separation Based on Multi-Stage Elaborated Dual-Path Deep BiLSTM with Auxiliary Identity Loss
Ziqiang Shi, Rujie Liu, Jiqing Han
Deep neural network with dual-path bi-directional long short-term memory (BiLSTM) block has been proved to be very effective in sequence modeling, especially in speech separation.…
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…
LaFurca: Iterative Refined Speech Separation Based on Context-Aware Dual-Path Parallel Bi-LSTM
Ziqiang Shi, Rujie Liu, Jiqing Han
Deep neural network with dual-path bi-directional long short-term memory (BiLSTM) block has been proved to be very effective in sequence modeling, especially in speech separation,…
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…
Learning to Find Correlated Features by Maximizing Information Flow in Convolutional Neural Networks
Wei Shen, Fei Li, Rujie Liu
Training convolutional neural networks for image classification tasks usually causes information loss. Although most of the time the information lost is redundant with respect to t…
FurcaNet: An end-to-end deep gated convolutional, long short-term memory, deep neural networks for single channel speech separation
Ziqiang Shi, Huibin Lin, Liu Liu +4
Deep gated convolutional networks have been proved to be very effective in single channel speech separation. However current state-of-the-art framework often considers training the…
Is CQT more suitable for monaural speech separation than STFT? an empirical study
Ziqiang Shi, Huibin Lin, Liu Liu +2
Short-time Fourier transform (STFT) is used as the front end of many popular successful monaural speech separation methods, such as deep clustering (DPCL), permutation invariant tr…
Learning to generate filters for convolutional neural networks
Wei Shen, Rujie Liu
Conventionally, convolutional neural networks (CNNs) process different images with the same set of filters. However, the variations in images pose a challenge to this fashion. In t…
Tackling Early Sparse Gradients in Softmax Activation Using Leaky Squared Euclidean Distance
Wei Shen, Rujie Liu
Softmax activation is commonly used to output the probability distribution over categories based on certain distance metric. In scenarios like one-shot learning, the distance metri…
Generating Attention from Classifier Activations for Fine-grained Recognition
Wei Shen, Rujie Liu
Recent advances in fine-grained recognition utilize attention maps to localize objects of interest. Although there are many ways to generate attention maps, most of them rely on so…
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…
Learning Residual Images for Face Attribute Manipulation
Wei Shen, Rujie Liu
Face attributes are interesting due to their detailed description of human faces. Unlike prior researches working on attribute prediction, we address an inverse and more challengin…
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…
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…
Online and stochastic Douglas-Rachford splitting method for large scale machine learning
Ziqiang Shi, Rujie Liu
Online and stochastic learning has emerged as powerful tool in large scale optimization. In this work, we generalize the Douglas-Rachford splitting (DRs) method for minimizing comp…