Qiang Ji

UAI Conference 2024 Conference Paper

Beyond Dirichlet-based Models: When Bayesian Neural Networks Meet Evidential Deep Learning

• Hanjing Wang
• Qiang Ji

Bayesian neural networks (BNNs) excel in uncertainty quantification (UQ) by estimating the posterior distribution of model parameters, yet face challenges due to the high computational demands of Bayesian inference. Evidential deep learning methods address this by treating target distribution parameters as random variables with a learnable conjugate distribution, enabling efficient UQ. However, there’s debate over whether these methods can accurately estimate epistemic uncertainty due to their single-network, sampling-free nature. In this paper, we combine the strengths of both approaches by distilling BNN knowledge into a Dirichlet-based model, endowing it with a Bayesian perspective and theoretical guarantees. Additionally, we introduce two enhancements to further improve the integration of Bayesian UQ with Dirichlet-based models. To relax the heavy computational load with BNNs, we introduce a self-regularized training strategy using Laplacian approximation (LA) for self-distillation. To alleviate the conjugate prior assumption, we employ an expressive normalizing flow for refining the model in a post-processing manner, where a few training iterations can enhance model performance. The experimental results have demonstrated the effectiveness of our proposed methods in both UQ accuracy and robustness.

AAAI Conference 2024 Conference Paper

Effective Causal Discovery under Identifiable Heteroscedastic Noise Model

• Naiyu Yin
• Tian Gao
• Yue Yu
• Qiang Ji

Capturing the underlying structural causal relations represented by Directed Acyclic Graphs (DAGs) has been a fundamental task in various AI disciplines. Causal DAG learning via the continuous optimization framework has recently achieved promising performance in terms of accuracy and efficiency. However, most methods make strong assumptions of homoscedastic noise, i.e., exogenous noises have equal variances across variables, observations, or even both. The noises in real data usually violate both assumptions due to the biases introduced by different data collection processes. To address the heteroscedastic noise issue, we introduce relaxed implementable sufficient conditions and prove the identifiability of a general class of SEM subject to those conditions. Based on the identifiable general SEM, we propose a novel formulation for DAG learning which accounts for the noise variance variation across variables and observations. We then propose an effective two-phase iterative DAG learning algorithm to address the increasing optimization difficulties and learn a causal DAG from data with heteroscedastic variables noise under varying variance. We show significant empirical gains of the proposed approaches over state-of-the-art methods on both synthetic data and real data.

UAI Conference 2023 Conference Paper

Diversity-enhanced probabilistic ensemble for uncertainty estimation

• Hanjing Wang
• Qiang Ji

Ensemble methods combine multiple individual models for prediction, which have demonstrated their effectiveness in accurate uncertainty quantification (UQ) and strong robustness. Obtaining a diverse ensemble set of model parameters results in better model averaging performance and better approximation of the true posterior distribution of these parameters. In this paper, we propose the diversity-enhanced probabilistic ensemble method with the adaptive uncertainty-guided ensemble learning strategy for better quantifying uncertainty and further improving the model robustness. Specifically, we construct the probabilistic ensemble model by building a Gaussian distribution of the model parameters for each ensemble component using Laplacian approximation in a post-processing manner. Then a mixture of Gaussian model is established with learnable and refinable parameters in an EM-like algorithm. During ensemble training, we leverage the uncertainty estimated from previous models as guidance when training the next one such that the new model will focus more on the less explored regions by previous models. Various experiments including out-of-distribution detection and image classification under distributional shifts have demonstrated better uncertainty estimation and improved model generalization ability of our proposed method.

IJCAI Conference 2022 Conference Paper

Empirical Bayesian Approaches for Robust Constraint-based Causal Discovery under Insufficient Data

• Zijun Cui
• Naiyu Yin
• Yuru Wang
• Qiang Ji

Causal discovery is to learn cause-effect relationships among variables given observational data and is important for many applications. Existing causal discovery methods assume data sufficiency, which may not be the case in many real world datasets. As a result, many existing causal discovery methods can fail under limited data. In this work, we propose Bayesian-augmented frequentist independence tests to improve the performance of constraint-based causal discovery methods under insufficient data: 1) We firstly introduce a Bayesian method to estimate mutual information (MI), based on which we propose a robust MI based independence test; 2) Secondly, we consider the Bayesian estimation of hypothesis likelihood and incorporate it into a well-defined statistical test, resulting in a robust statistical testing based independence test. We apply proposed independence tests to constraint-based causal discovery methods and evaluate the performance on benchmark datasets with insufficient samples. Experiments show significant performance improvement in terms of both accuracy and efficiency over SOTA methods.

UAI Conference 2022 Conference Paper

Variational message passing neural network for Maximum-A-Posteriori (MAP) inference

• Zijun Cui
• Hanjing Wang
• Tian Gao
• Kartik Talamadupula
• Qiang Ji

Maximum-A-Posteriori (MAP) inference is a fundamental task in probabilistic inference and belief propagation (BP) is a widely used algorithm for MAP inference. Though BP has been applied successfully to many different fields, it offers no performance guarantee and often performs poorly on loopy graphs. To improve the performance on loopy graphs and to scale up to large graphs, we propose a variational message passing neural network (V-MPNN), where we leverage both the power of neural networks in modeling complex functions and the well-established algorithmic theories on variational belief propagation. Instead of relying on a hand-crafted variational assumption, we propose a neural-augmented free energy where a general variational distribution is parameterized through a neural network. A message passing neural network is utilized for the minimization of neural-augmented free energy. Training of the MPNN is thus guided by neural-augmented free energy, without requiring exact MAP configurations as annotations. We empirically demonstrate the effectiveness of the proposed V-MPNN by comparing against both state-of-the-art training-free methods and training-based methods.

ICML Conference 2021 Conference Paper

DAGs with No Curl: An Efficient DAG Structure Learning Approach

• Yue Yu 0011
• Tian Gao 0007
• Naiyu Yin
• Qiang Ji

Recently directed acyclic graph (DAG) structure learning is formulated as a constrained continuous optimization problem with continuous acyclicity constraints and was solved iteratively through subproblem optimization. To further improve efficiency, we propose a novel learning framework to model and learn the weighted adjacency matrices in the DAG space directly. Specifically, we first show that the set of weighted adjacency matrices of DAGs are equivalent to the set of weighted gradients of graph potential functions, and one may perform structure learning by searching in this equivalent set of DAGs. To instantiate this idea, we propose a new algorithm, DAG-NoCurl, which solves the optimization problem efficiently with a two-step procedure: $1)$ first we find an initial non-acyclic solution to the optimization problem, and $2)$ then we employ the Hodge decomposition of graphs and learn an acyclic graph by projecting the non-acyclic graph to the gradient of a potential function. Experimental studies on benchmark datasets demonstrate that our method provides comparable accuracy but better efficiency than baseline DAG structure learning methods on both linear and generalized structural equation models, often by more than one order of magnitude.

AAAI Conference 2021 Conference Paper

Type-augmented Relation Prediction in Knowledge Graphs

• Zijun Cui
• Pavan Kapanipathi
• Kartik Talamadupula
• Tian Gao
• Qiang Ji

Knowledge graphs (KGs) are of great importance to many real world applications, but they generally suffer from incomplete information in the form of missing relations between entities. Knowledge graph completion (also known as relation prediction) is the task of inferring missing facts given existing ones. Most of the existing work is proposed by maximizing the likelihood of observed instance-level triples. Not much attention, however, is paid to the ontological information, such as type information of entities and relations. In this work, we propose a type-augmented relation prediction (TaRP) method, where we apply both the type information and instance-level information for relation prediction. In particular, type information and instance-level information are encoded as prior probabilities and likelihoods of relations respectively, and are combined by following Bayes’ rule. Our proposed TaRP method achieves significantly better performance than state-of-the-art methods on four benchmark datasets: FB15K, FB15K-237, YAGO26K-906, and DB111K-174. In addition, we show that TaRP achieves significantly improved data efficiency. More importantly, the type information extracted from a specific dataset can generalize well to other datasets through the proposed TaRP model.

AAAI Conference 2021 Conference Paper

Uncertain Graph Neural Networks for Facial Action Unit Detection

• Tengfei Song
• Lisha Chen
• Wenming Zheng
• Qiang Ji

Capturing the dependencies among different facial action units (AU) is extremely important for the AU detection task. Many studies have employed graph-based deep learning methods to exploit the dependencies among AUs. However, the dependencies among AUs in real world data are often noisy and the uncertainty is essential to be taken into consideration. Rather than employing a deterministic mode, we propose an uncertain graph neural network (UGN) to learn the probabilistic mask that simultaneously captures both the individual dependencies among AUs and the uncertainties. Further, we propose an adaptive weighted loss function based on the epistemic uncertainties to adaptively vary the weights of the training samples during the training process to account for unbalanced data distributions among AUs. We also provide an insightful analysis on how the uncertainties are related to the performance of AU detection. Extensive experiments, conducted on two benchmark datasets, i. e. , BP4D and DISFA, demonstrate our method achieves the state-of-the-art performance.

NeurIPS Conference 2020 Conference Paper

Knowledge Augmented Deep Neural Networks for Joint Facial Expression and Action Unit Recognition

• Zijun Cui
• Tengfei Song
• Yuru Wang
• Qiang Ji

Facial expression and action units (AUs) represent two levels of descriptions of the facial behavior. Due to the underlying facial anatomy and the need to form a meaningful coherent expression, they are strongly correlated. This paper proposes to systematically capture their dependencies and incorporate them into a deep learning framework for joint facial expression recognition and action unit detection. Specifically, we first propose a constraint optimization method to encode the generic knowledge on expression-AUs probabilistic dependencies into a Bayesian Network (BN). The BN is then integrated into a deep learning framework as a weak supervision for an AU detection model. A data-driven facial expression recognition(FER) model is then constructed from data. Finally, the FER model and AU detection model are trained jointly to refine their learning. Evaluations on benchmark datasets demonstrate the effectiveness of the proposed knowledge integration in improving the performance of both the FER model and the AU detection model. The proposed AU detection model is demonstrated to be able to achieve competitive performance without AU annotations. Furthermore, the proposed Bayesian Network capturing the generic knowledge is demonstrated to generalize well to different datasets.

AAAI Conference 2020 Conference Paper

Label Error Correction and Generation through Label Relationships

• Zijun Cui
• Yong Zhang
• Qiang Ji

For multi-label supervised learning, the quality of the label annotation is important. However, for many real world multilabel classification applications, label annotations often lack quality, in particular when label annotation requires special expertise, such as annotating fine-grained labels. The relationships among labels, on other hand, are usually stable and robust to errors. For this reason, we propose to capture and leverage label relationships at different levels to improve finegrained label annotation quality and to generate labels. Two levels of labels, including object-level labels and propertylevel labels, are considered. The object-level labels characterize object category based on its overall appearance, while the property-level labels describe specific local object properties. A Bayesian network (BN) is learned to capture the relationships among the multiple labels at the two levels. A MAP inference is then performed to identify the most stable and consistent label relationships and they are then used to improve data annotations for the same dataset and to generate labels for a new dataset. Experimental evaluations on six benchmark databases for two different tasks (facial action unit and object attribute classification) demonstrate the effectiveness of the proposed method in improving data annotation and in generating effective new labels.

NeurIPS Conference 2019 Conference Paper

Deep Structured Prediction for Facial Landmark Detection

• Lisha Chen
• Hui Su
• Qiang Ji

Existing deep learning based facial landmark detection methods have achieved excellent performance. These methods, however, do not explicitly embed the structural dependencies among landmark points. They hence cannot preserve the geometric relationships between landmark points or generalize well to challenging conditions or unseen data. This paper proposes a method for deep structured facial landmark detection based on combining a deep Convolutional Network with a Conditional Random Field. We demonstrate its superior performance to existing state-of-the-art techniques in facial landmark detection, especially a better generalization ability on challenging datasets that include large pose and occlusion.

AAAI Conference 2018 Conference Paper

An Adversarial Hierarchical Hidden Markov Model for Human Pose Modeling and Generation

• Rui Zhao
• Qiang Ji

We propose a hierarchical extension to hidden Markov model (HMM) under the Bayesian framework to overcome its limited model capacity. The model parameters are treated as random variables whose distributions are governed by hyperparameters. Therefore the variation in data can be modeled at both instance level and distribution level. We derive a novel learning method for estimating the parameters and hyperparameters of our model based on adversarial learning framework, which has shown promising results in generating photorealistic images and videos. We demonstrate the benefit of the proposed method on human motion capture data through comparison with both state-of-the-art methods and the same model that is learned by maximizing likelihood. The first experiment on reconstruction shows the model’s capability of generalizing to novel testing data. The second experiment on synthesis shows the model’s capability of generating realistic and diverse data.

AAAI Conference 2017 Conference Paper

Capturing Dependencies among Labels and Features for Multiple Emotion Tagging of Multimedia Data

• Shan Wu
• Shangfei Wang
• Qiang Ji

In this paper, we tackle the problem of emotion tagging of multimedia data by modeling the dependencies among multiple emotions in both the feature and label spaces. These dependencies, which carry crucial top-down and bottom-up evidence for improving multimedia affective content analysis, have not been thoroughly exploited yet. To this end, we propose two hierarchical models that independently and dependently learn the shared features and global semantic relationships among emotion labels to jointly tag multiple emotion labels of multimedia data. Efficient learning and inference algorithms of the proposed models are also developed. Experiments on three benchmark emotion databases demonstrate the superior performance of our methods to existing methods.

AAAI Conference 2017 Conference Paper

Differentiating Between Posed and Spontaneous Expressions with Latent Regression Bayesian Network

• Quan Gan
• Siqi Nie
• Shangfei Wang
• Qiang Ji

Spatial patterns embedded in human faces are crucial for differentiating posed expressions from spontaneous ones, yet they have not been thoroughly exploited in the literature. To tackle this problem, we present a generative model, i. e. , Latent Regression Bayesian Network (LRBN), to effectively capture the spatial patterns embedded in facial landmark points to differentiate between posed and spontaneous facial expressions. The LRBN is a directed graphical model consisting of one latent layer and one visible layer. Due to the “explaining away” effect in Bayesian networks, LRBN is able to capture both the dependencies among the latent variables given the observation and the dependencies among visible variables. We believe that such dependencies are crucial for faithful data representation. Specifically, during training, we construct two LRBNs to capture spatial patterns inherent in displacements of landmark points from spontaneous facial expressions and posed facial expressions respectively. During testing, the samples are classified into posed or spontaneous expressions according to their likelihoods on two models. Ef- ficient learning and inference algorithms are proposed. Experimental results on two benchmark databases demonstrate the advantages of the proposed approach in modeling spatial patterns as well as its superior performance to the existing methods in differentiating between posed and spontaneous expressions.

IJCAI Conference 2016 Conference Paper

Constrained Local Latent Variable Discovery

• Tian Gao
• Qiang Ji

For many applications, the observed data may be incomplete and there often exist variables that are unobserved but play an important role in capturing the underlying relationships. In this work, we propose a method to identify local latent variables and to determine their structural relations with the observed variables. We formulate the local latent variable discovery as discovering the Markov Blanket (MB) of a target variable. To efficiently search the latent variable space, we exploit MB topology to divide the latent space into different subspaces. Within each subspace, we employ a constrained structure expectation-maximization algorithm to greedily learn the MB with latent variables. We evaluate the performance of our method on synthetic data to demonstrate its effectiveness in identifying the correct latent variables. We further apply our algorithm to feature discovery and selection problem, and show that the latent variables learned through the proposed method can improve the classification accuracy in benchmark feature selection and discovery datasets.

AAAI Conference 2016 Conference Paper

Learning Bayesian Networks with Bounded Tree-width via Guided Search

• Siqi Nie
• Cassio de Campos
• Qiang Ji

Bounding the tree-width of a Bayesian network can reduce the chance of overfitting, and allows exact inference to be performed efficiently. Several existing algorithms tackle the problem of learning bounded tree-width Bayesian networks by learning from k-trees as super-structures, but they do not scale to large domains and/or large tree-width. We propose a guided search algorithm to find k-trees with maximum Informative scores, which is a measure of quality for the k-tree in yielding good Bayesian networks. The algorithm achieves close to optimal performance compared to exact solutions in small domains, and can discover better networks than existing approximate methods can in large domains. It also provides an optimal elimination order of variables that guarantees small complexity for later runs of exact inference. Comparisons with well-known approaches in terms of learning and inference accuracy illustrate its capabilities.

IJCAI Conference 2016 Conference Paper

Object Recognition with Hidden Attributes

• Xiaoyang Wang
• Qiang Ji

Attribute based object recognition performs object recognition using the semantic properties of the object. Unlike the existing approaches that treat attributes as a middle level representation and require to estimate the attributes during testing, we propose to incorporate the hidden attributes, which are the attributes used only during training to improve model learning and are not needed during testing. To achieve this goal, we develop two different approaches to incorporate hidden attributes. The first approach utilizes hidden attributes as additional information to improve the object classification model. The second approach further exploits the semantic relationships between the objects and the hidden attributes. Experiments on benchmark data sets demonstrate that both approaches can effectively improve the learning of the object classifiers over the baseline models that do not use attributes, and their combination reaches the best performance. Experiments also show that the proposed approaches outperform both state of the art methods that use attributes as middle level representation and the approaches that learn the classifiers with hidden information.

NeurIPS Conference 2015 Conference Paper

Local Causal Discovery of Direct Causes and Effects

• Tian Gao
• Qiang Ji

We focus on the discovery and identification of direct causes and effects of a target variable in a causal network. State-of-the-art algorithms generally need to find the global causal structures in the form of complete partial directed acyclic graphs in order to identify the direct causes and effects of a target variable. While these algorithms are effective, it is often unnecessary and wasteful to find the global structures when we are only interested in one target variable (such as class labels). We propose a new local causal discovery algorithm, called Causal Markov Blanket (CMB), to identify the direct causes and effects of a target variable based on Markov Blanket Discovery. CMB is designed to conduct causal discovery among multiple variables, but focuses only on finding causal relationships between a specific target variable and other variables. Under standard assumptions, we show both theoretically and experimentally that the proposed local causal discovery algorithm can obtain the comparable identification accuracy as global methods but significantly improve their efficiency, often by more than one order of magnitude.

NeurIPS Conference 2014 Conference Paper

Advances in Learning Bayesian Networks of Bounded Treewidth

• Siqi Nie
• Denis Maua
• Cassio de Campos
• Qiang Ji

This work presents novel algorithms for learning Bayesian networks of bounded treewidth. Both exact and approximate methods are developed. The exact method combines mixed integer linear programming formulations for structure learning and treewidth computation. The approximate method consists in sampling k-trees (maximal graphs of treewidth k), and subsequently selecting, exactly or approximately, the best structure whose moral graph is a subgraph of that k-tree. The approaches are empirically compared to each other and to state-of-the-art methods on a collection of public data sets with up to 100 variables.

IJCAI Conference 2013 Conference Paper

Deep Feature Learning Using Target Priors with Applications in ECoG Signal Decoding for BCI

• Zuoguan Wang
• Siwei Lyu
• Gerwin Schalk
• Qiang Ji

Recent years have seen a great interest in using deep architectures for feature learning from data. One drawback of the commonly used unsupervised deep feature learning methods is that for supervised or semi-supervised learning tasks, the information in the target variables are not used until the final stage when the classifier or regressor is trained on the learned features. This could lead to over-generalized features that are not competitive on the specific supervised or semi-supervised learning tasks. In this work, we describe a new learning method that combines deep feature learning on mixed labeled and unlabeled data sets. Specifically, we describe a weakly supervised learning method of a prior supervised convolutional stacked auto-encoders (PCSA), of which information in the target variables is represented probabilistically using a Gaussian Bernoulli restricted Boltzmann machine (RBM). We apply this method to the decoding problem of an ECoG based Brain Computer Interface (BCI) system. Our experimental results show that PCSA achieves significant improvement in decoding performance on benchmark data sets compared to the unsupervised feature learning as well as to the current state-of-the-art algorithms that are based on manually crafted features.

YNIMG Journal 2012 Journal Article

Cross-subject workload classification with a hierarchical Bayes model

• Ziheng Wang
• Ryan M. Hope
• Zuoguan Wang
• Qiang Ji
• Wayne D. Gray

Most of the current EEG-based workload classifiers are subject-specific; that is, a new classifier is built and trained for each human subject. In this paper we introduce a cross-subject workload classifier based on a hierarchical Bayes model. The cross-subject classifier is trained and tested with data from a group of subjects. In our work, it was trained and tested on EEG data collected from 8 subjects as they performed the Multi-Attribute Task Battery across three levels of difficulty. The accuracy of this cross-subject classifier is stable across the three levels of workload and comparable to a benchmark subject-specific neural network classifier.

NeurIPS Conference 2012 Conference Paper

Learning with Target Prior

• Zuoguan Wang
• Siwei Lyu
• Gerwin Schalk
• Qiang Ji

In the conventional approaches for supervised parametric learning, relations between data and target variables are provided through training sets consisting of pairs of corresponded data and target variables. In this work, we describe a new learning scheme for parametric learning, in which the target variables $\y$ can be modeled with a prior model $p(\y)$ and the relations between data and target variables are estimated through $p(\y)$ and a set of uncorresponded data $\x$ in training. We term this method as learning with target priors (LTP). Specifically, LTP learning seeks parameter $\t$ that maximizes the log likelihood of $f_\t(\x)$ on a uncorresponded training set with regards to $p(\y)$. Compared to the conventional (semi)supervised learning approach, LTP can make efficient use of prior knowledge of the target variables in the form of probabilistic distributions, and thus removes/reduces the reliance on training data in learning. Compared to the Bayesian approach, the learned parametric regressor in LTP can be more efficiently implemented and deployed in tasks where running efficiency is critical, such as on-line BCI signal decoding. We demonstrate the effectiveness of the proposed approach on parametric regression tasks for BCI signal decoding and pose estimation from video.

NeurIPS Conference 2011 Conference Paper

Anatomically Constrained Decoding of Finger Flexion from Electrocorticographic Signals

• Zuoguan Wang
• Gerwin Schalk
• Qiang Ji

Brain-computer interfaces (BCIs) use brain signals to convey a user's intent. Some BCI approaches begin by decoding kinematic parameters of movements from brain signals, and then proceed to using these signals, in absence of movements, to allow a user to control an output. Recent results have shown that electrocorticographic (ECoG) recordings from the surface of the brain in humans can give information about kinematic parameters (e. g. , hand velocity or finger flexion). The decoding approaches in these demonstrations usually employed classical classification/regression algorithms that derive a linear mapping between brain signals and outputs. However, they typically only incorporate little prior information about the target kinematic parameter. In this paper, we show that different types of anatomical constraints that govern finger flexion can be exploited in this context. Specifically, we incorporate these constraints in the construction, structure, and the probabilistic functions of a switched non-parametric dynamic system (SNDS) model. We then apply the resulting SNDS decoder to infer the flexion of individual fingers from the same ECoG dataset used in a recent study. Our results show that the application of the proposed model, which incorporates anatomical constraints, improves decoding performance compared to the results in the previous work. Thus, the results presented in this paper may ultimately lead to neurally controlled hand prostheses with full fine-grained finger articulation.

JMLR Journal 2011 Journal Article

Efficient Structure Learning of Bayesian Networks using Constraints

• Cassio P. de Campos
• Qiang Ji

This paper addresses the problem of learning Bayesian network structures from data based on score functions that are decomposable. It describes properties that strongly reduce the time and memory costs of many known methods without losing global optimality guarantees. These properties are derived for different score criteria such as Minimum Description Length (or Bayesian Information Criterion), Akaike Information Criterion and Bayesian Dirichlet Criterion. Then a branch-and-bound algorithm is presented that integrates structural constraints with data in a way to guarantee global optimality. As an example, structural constraints are used to map the problem of structure learning in Dynamic Bayesian networks into a corresponding augmented Bayesian network. Finally, we show empirically the benefits of using the properties with state-of-the-art methods and with the new algorithm, which is able to handle larger data sets than before. [abs] [ pdf ][ bib ] &copy JMLR 2011. ( edit, beta )

AAAI Conference 2010 Conference Paper

Properties of Bayesian Dirichlet Scores to Learn Bayesian Network Structures

• Cassio de Campos
• Qiang Ji

This paper addresses exact learning of Bayesian network structure from data based on the Bayesian Dirichlet score function and its derivations. We describe useful properties that strongly reduce the computational costs of many known methods without losing global optimality guarantees. We show empirically the advantages of the properties in terms of time and memory consumptions, demonstrating that state-ofthe-art methods, with the use of such properties, might handle larger data sets than those currently possible.

ICML Conference 2009 Conference Paper

Structure learning of Bayesian networks using constraints

• Cassio de Campos
• Zhi Zeng
• Qiang Ji

This paper addresses exact learning of Bayesian network structure from data and expert's knowledge based on score functions that are decomposable. First, it describes useful properties that strongly reduce the time and memory costs of many known methods such as hill-climbing, dynamic programming and sampling variable orderings. Secondly, a branch and bound algorithm is presented that integrates parameter and structural constraints with data in a way to guarantee global optimality with respect to the score function. It is an any-time procedure because, if stopped, it provides the best current solution and an estimation about how far it is from the global solution. We show empirically the advantages of the properties and the constraints, and the applicability of the algorithm to large data sets (up to one hundred variables) that cannot be handled by other current methods (limited to around 30 variables).

UAI Conference 2008 Conference Paper

Strategy Selection in Influence Diagrams using Imprecise Probabilities

• Cassio de Campos
• Qiang Ji

This paper describes a new algorithm to solve the decision making problem in Influence Diagrams based on algorithms for credal networks. Decision nodes are associated to imprecise probability distributions and a reformulation is introduced that finds the global maximum strategy with respect to the expected utility. We work with Limited Memory Influence Diagrams, which generalize most Influence Diagram proposals and handle simultaneous decisions. Besides the global optimum method, we explore an anytime approximate solution with a guaranteed maximum error and show that imprecise probabilities are handled in a straightforward way. Complexity issues and experiments with random diagrams and an effects-based military planning problem are discussed.

IJCAI Conference 2007 Conference Paper

• Wenhui Liao
• Yan Tong
• Zhiwei Zhu
• Qiang Ji

The paper describes a simple but effective framework for visual object tracking in video sequences. The main contribution of this work lies in the introduction of a case-based reasoning (CBR) method to maintain an accurate target model automatically and efficiently under significant appearance changes without drifting away. Specifically, an automatic case-base maintenance algorithm is proposed to dynamically update the case base, manage the case base to be competent and representative, and to maintain the case base in a reasonable size for real-time performance. Furthermore, the method can provide an accurate confidence measurement for each tracked object so that the tracking failures can be identified in time. Under the framework, a real-time face tracker is built to track human faces robustly under various face orientations, significant facial expressions, and illumination changes.

ICRA Conference 2001 Conference Paper

A New Technique for Camera Self-Calibration

• Qiang Ji
• Songtao Dai

Self camera calibration based on purely rotational movement of camera receives the most attention among different calibration methods. The purely rotational approach, however, assumes the camera rotates around its optical center, therefore yielding no translation. This assumption is not realistic since in practice the precise location of optical center is often unknown and rotation is often performed about an unknown but fixed point near the optical center. The rotation is therefore not pure in the sense that relative translation is introduced between two rotated camera frames. In this paper, we introduce a new rotation-based self camera calibration method, which explicitly accounts for the unknown translation. The problem is mathematically formulated and solved taking the translation into consideration. Experiments with both synthetic and real data show that the systemic errors from the ignorance of the translation can be effectively eliminated by our approach.

ICRA Conference 2001 Conference Paper

Camera Calibration With Genetic Algorithms

• Qiang Ji
• Yongmian Zhang

We present a novel approach based on genetic algorithms for performing camera calibration. Contrary to the classical nonlinear photogrammetric approach, the proposed technique can correctly find the near-optimal solution without the need of initial guesses (with only very loose parameter bounds) and with a minimum number of control points (7 points). Results from our extensive study using both synthetic and real image data as well as performance comparison with Tsai's procedure demonstrate the excellent performance of the proposed technique in terms of convergence, accuracy, and robustness.

ICRA Conference 2001 Conference Paper

Camera Self-Calibration from Ellipse Correspondences

• Qiang Ji
• Rong Hu

We introduce a new technique for camera self-calibration using ellipse correspondences. Based on an analysis of ellipse matches between the images obtained from the same viewpoint but with different and unknown view directions, our approach estimates the intrinsic camera parameters. We present both linear and nonlinear solutions to recovering intrinsic camera parameters. The algorithm's performance is validated extensively using both synthetic and real image data. Compared with similar techniques but using points, we observe a comparable performance. The use of ellipses, however, greatly simplifies feature matching between images, improves matching accuracy, and avoids mismatch.

AAAI Conference 1994 Short Paper

Dempster-Shafer and Bayesian Networks for CAD-Based Feature Extraction: A Comparative Investigation and Analysis

• Qiang Ji

Information pertaining to real world problems often contains noises and uncertainties. This has been a major challenge faced by the contemporary AI researchers. Of various paradigms developed for handing uncertainties, the Dempster-Shafer theory (DS) and the Bayesian Belief Networks (BBN) have received considerable attention in the AI community recently. They have been successfully applied to problems in medical diagnosis, decision-making, image understanding, machine vision, etc.. Despite their obvious success, blindly using them without understanding their limitations may result in computational difficulty and unsatisfying inference results. The aim of this paper is to analyze and compare the performance of the two paradigms in extracting manufacturing features from the solid model descriptions of objects. Such a comparison will serve to identify their strengths, weakness, and appropriate application domains.

ICRA Conference 1994 Conference Paper

Extracting and Identifying Form Features: A Bayesian Approach

• Michael M. Marefat
• Qiang Ji

Introduces a new uncertainty reasoning-based method for the identification and extraction of manufacturing features from solid model descriptions of objects. A major difficulty faced by previously proposed methods for feature extraction has been the interaction between features. In interacting situations, the representation for various primitive features is non-unique, making their recognition very difficult. We develop an approach based on generating, propagating and combining geometrical and topological evidences in a hierarchical belief network for identifying and extracting features. The methodology combines and propagates evidences to determine a set of correct virtual links to be augmented in the cavity graph representing a depression of the object, so that the resulting supergraph can be partitioned to obtain the features of the object. >