Qiang Ji

Zifei Wang, Wei Wen, Qiang Ji et al.

LLM agents complete complex tasks by composing multiple skills, and skill retrieval is a front-end stage for agents. Skill retrieval differs fundamentally from traditional document retrieval at the supervision level: top-K joint correctness depends not only on the semantic relevance of each individual query-skill pair, but also on whether the skills retrieved together can collaborate to fulfill the task under the given query. Such "skill compatibility" cannot be derived from independent relevance alone. Yet existing LLM-based data synthesis pipelines can produce a direct supervision signal for "which skills should not be jointly retrieved under this query" -- namely the LLM's own rejection decisions -- and this signal is routinely discarded as low-quality data. To address this gap, we propose Reject-as-Resource Retriever (R3) and construct R3-Skill, a bilingual (Chinese-English) skill retrieval benchmark targeting realistic agent skill routing. R3-Skill spans four language directions, features query phrasings close to real user requests, and is verified through multi-expert cross-checking. On R3-Skill, we build a two-stage retrieval system (R3-Embedding + R3-Reranker) with skill compatibility as an explicit training signal. Gradient analysis shows that the "push-away" signal is diluted by bilateral balancing in the bi-encoder but acts as lossless graded ranking supervision in the cross-encoder -- motivating its placement at the cross-encoder stage, as confirmed by ablations on two datasets. The R3-Embedding + R3-Reranker pipeline attains Hit@1 = 0.7714, NDCG@10 = 0.8327 and Set-Compat = 0.3525 on R3-Skill. The dataset, training code and model weights are released as open source for agent skill routing.

Zijun Cui, Tian Gao, Kartik Talamadupula et al. · ibm-research

Deep learning models, though having achieved great success in many different fields over the past years, are usually data hungry, fail to perform well on unseen samples, and lack of interpretability. Various prior knowledge often exists in the target domain and their use can alleviate the deficiencies with deep learning. To better mimic the behavior of human brains, different advanced methods have been proposed to identify domain knowledge and integrate it into deep models for data-efficient, generalizable, and interpretable deep learning, which we refer to as knowledge-augmented deep learning (KADL). In this survey, we define the concept of KADL, and introduce its three major tasks, i.e., knowledge identification, knowledge representation, and knowledge integration. Different from existing surveys that are focused on a specific type of knowledge, we provide a broad and complete taxonomy of domain knowledge and its representations. Based on our taxonomy, we provide a systematic review of existing techniques, different from existing works that survey integration approaches agnostic to taxonomy of knowledge. This survey subsumes existing works and offers a bird's-eye view of research in the general area of knowledge-augmented deep learning. The thorough and critical reviews of numerous papers help not only understand current progresses but also identify future directions for the research on knowledge-augmented deep learning.

Weixun Wang, XiaoXiao Xu, Wanhe An et al.

Agentic crafting requires LLMs to operate in real-world environments over multiple turns by taking actions, observing outcomes, and iteratively refining artifacts. Despite its importance, the open-source community lacks a principled, end-to-end ecosystem to streamline agent development. We introduce the Agentic Learning Ecosystem (ALE), a foundational infrastructure that optimizes the production pipeline for agentic model. ALE consists of three components: ROLL, a post-training framework for weight optimization; ROCK, a sandbox environment manager for trajectory generation; and iFlow CLI, an agent framework for efficient context engineering. We release ROME, an open-source agent grounded by ALE and trained on over one million trajectories. Our approach includes data composition protocols for synthesizing complex behaviors and a novel policy optimization algorithm, Interaction-Perceptive Agentic Policy Optimization (IPA), which assigns credit over semantic interaction chunks rather than individual tokens to improve long-horizon training stability. Empirically, we evaluate ROME within a structured setting and introduce Terminal Bench Pro, a benchmark with improved scale and contamination control. ROME demonstrates strong performance across benchmarks like SWE-bench Verified and Terminal Bench, proving the effectiveness of ALE.

Hanjing Wang, Dhiraj Joshi, Shiqiang Wang et al.

Predictions made by deep learning models are prone to data perturbations, adversarial attacks, and out-of-distribution inputs. To build a trusted AI system, it is therefore critical to accurately quantify the prediction uncertainties. While current efforts focus on improving uncertainty quantification accuracy and efficiency, there is a need to identify uncertainty sources and take actions to mitigate their effects on predictions. Therefore, we propose to develop explainable and actionable Bayesian deep learning methods to not only perform accurate uncertainty quantification but also explain the uncertainties, identify their sources, and propose strategies to mitigate the uncertainty impacts. Specifically, we introduce a gradient-based uncertainty attribution method to identify the most problematic regions of the input that contribute to the prediction uncertainty. Compared to existing methods, the proposed UA-Backprop has competitive accuracy, relaxed assumptions, and high efficiency. Moreover, we propose an uncertainty mitigation strategy that leverages the attribution results as attention to further improve the model performance. Both qualitative and quantitative evaluations are conducted to demonstrate the effectiveness of our proposed methods.

Yufei Zhang, Hanjing Wang, Jeffrey O. Kephart et al.

While 3D body reconstruction methods have made remarkable progress recently, it remains difficult to acquire the sufficiently accurate and numerous 3D supervisions required for training. In this paper, we propose \textbf{KNOWN}, a framework that effectively utilizes body \textbf{KNOW}ledge and u\textbf{N}certainty modeling to compensate for insufficient 3D supervisions. KNOWN exploits a comprehensive set of generic body constraints derived from well-established body knowledge. These generic constraints precisely and explicitly characterize the reconstruction plausibility and enable 3D reconstruction models to be trained without any 3D data. Moreover, existing methods typically use images from multiple datasets during training, which can result in data noise (\textit{e.g.}, inconsistent joint annotation) and data imbalance (\textit{e.g.}, minority images representing unusual poses or captured from challenging camera views). KNOWN solves these problems through a novel probabilistic framework that models both aleatoric and epistemic uncertainty. Aleatoric uncertainty is encoded in a robust Negative Log-Likelihood (NLL) training loss, while epistemic uncertainty is used to guide model refinement. Experiments demonstrate that KNOWN's body reconstruction outperforms prior weakly-supervised approaches, particularly on the challenging minority images.

Zijun Cui, Naiyu Yin, Yuru Wang et al.

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.

Bashirul Azam Biswas, Qiang Ji

The quality of scene graphs generated by the state-of-the-art (SOTA) models is compromised due to the long-tail nature of the relationships and their parent object pairs. Training of the scene graphs is dominated by the majority relationships of the majority pairs and, therefore, the object-conditional distributions of relationship in the minority pairs are not preserved after the training is converged. Consequently, the biased model performs well on more frequent relationships in the marginal distribution of relationships such as `on' and `wearing', and performs poorly on the less frequent relationships such as `eating' or `hanging from'. In this work, we propose virtual evidence incorporated within-triplet Bayesian Network (BN) to preserve the object-conditional distribution of the relationship label and to eradicate the bias created by the marginal probability of the relationships. The insufficient number of relationships in the minority classes poses a significant problem in learning the within-triplet Bayesian network. We address this insufficiency by embedding-based augmentation of triplets where we borrow samples of the minority triplet classes from its neighborhood triplets in the semantic space. We perform experiments on two different datasets and achieve a significant improvement in the mean recall of the relationships. We also achieve better balance between recall and mean recall performance compared to the SOTA de-biasing techniques of scene graph models.

Jianxuan Yang, Xinyue Guo, Zhi Cheng et al.

Recent advances in video-to-audio (V2A) generation enable high-quality audio synthesis from visual content, yet achieving robust and fine-grained controllability remains challenging. Existing methods suffer from weak textual controllability under visual-text conflict and imprecise stylistic control due to entangled temporal and timbre information in reference audio. Moreover, the lack of standardized benchmarks limits systematic evaluation. We propose ControlFoley, a unified multimodal V2A framework that enables precise control over video, text, and reference audio. We introduce a joint visual encoding paradigm that integrates CLIP with a spatio-temporal audio-visual encoder to improve alignment and textual controllability. We further propose temporal-timbre decoupling to suppress redundant temporal cues while preserving discriminative timbre features. In addition, we design a modality-robust training scheme with unified multimodal representation alignment (REPA) and random modality dropout. We also present VGGSound-TVC, a benchmark for evaluating textual controllability under varying degrees of visual-text conflict. Extensive experiments demonstrate state-of-the-art performance across multiple V2A tasks, including text-guided, text-controlled, and audio-controlled generation. ControlFoley achieves superior controllability under cross-modal conflict while maintaining strong synchronization and audio quality, and shows competitive or better performance compared to an industrial V2A system. Code, models, datasets, and demos are available at: https://yjx-research.github.io/ControlFoley/.

Yufei Zhang, Jeffrey O. Kephart, Qiang Ji

Fully-supervised monocular 3D hand reconstruction is often difficult because capturing the requisite 3D data entails deploying specialized equipment in a controlled environment. We introduce a weakly-supervised method that avoids such requirements by leveraging fundamental principles well-established in the understanding of the human hand's unique structure and functionality. Specifically, we systematically study hand knowledge from different sources, including biomechanics, functional anatomy, and physics. We effectively incorporate these valuable foundational insights into 3D hand reconstruction models through an appropriate set of differentiable training losses. This enables training solely with readily-obtainable 2D hand landmark annotations and eliminates the need for expensive 3D supervision. Moreover, we explicitly model the uncertainty that is inherent in image observations. We enhance the training process by exploiting a simple yet effective Negative Log Likelihood (NLL) loss that incorporates uncertainty into the loss function. Through extensive experiments, we demonstrate that our method significantly outperforms state-of-the-art weakly-supervised methods. For example, our method achieves nearly a 21\% performance improvement on the widely adopted FreiHAND dataset.

Shreya Ghosh, Abhinav Dhall, Munawar Hayat et al.

Eye gaze analysis is an important research problem in the field of Computer Vision and Human-Computer Interaction. Even with notable progress in the last 10 years, automatic gaze analysis still remains challenging due to the uniqueness of eye appearance, eye-head interplay, occlusion, image quality, and illumination conditions. There are several open questions, including what are the important cues to interpret gaze direction in an unconstrained environment without prior knowledge and how to encode them in real-time. We review the progress across a range of gaze analysis tasks and applications to elucidate these fundamental questions, identify effective methods in gaze analysis, and provide possible future directions. We analyze recent gaze estimation and segmentation methods, especially in the unsupervised and weakly supervised domain, based on their advantages and reported evaluation metrics. Our analysis shows that the development of a robust and generic gaze analysis method still needs to address real-world challenges such as unconstrained setup and learning with less supervision. We conclude by discussing future research directions for designing a real-world gaze analysis system that can propagate to other domains including Computer Vision, Augmented Reality (AR), Virtual Reality (VR), and Human Computer Interaction (HCI). Project Page: https://github.com/i-am-shreya/EyeGazeSurvey}{https://github.com/i-am-shreya/EyeGazeSurvey

Qiang Ji, Lin Cheng, Kaidi Huang et al.

The increasing penetration of intermittent renewable energy sources and the retirement of thermal units have widened the power system flexibility gap. Industrial demand response (DR) driven by real-time pricing is widely regarded as a viable solution. In this paper, we propose a framework to quantify the DR potential of a zero-carbon hydrogen metallurgy system (ZCHMS) considering shaft furnace's flexibility. First, we model the shaft furnace as a constrained flexible load and validate the model via simulation, achieving a root mean square error of 4.48\% of the rated load. Second, we formulate a DR potential evaluation method that determines baseline and DR-based production scheduling schemes by minimizing operating cost subject to production orders. Finally, the numerical results show that compared with the baseline, DR-based ZCHMS reduces operating cost by 6.6\%, incentivizing demand-side management in ironmaking and strengthening power-ironmaking synergies.

Yufei Zhang, Jeffrey O. Kephart, Zijun Cui et al.

While current methods have shown promising progress on estimating 3D human motion from monocular videos, their motion estimates are often physically unrealistic because they mainly consider kinematics. In this paper, we introduce Physics-aware Pretrained Transformer (PhysPT), which improves kinematics-based motion estimates and infers motion forces. PhysPT exploits a Transformer encoder-decoder backbone to effectively learn human dynamics in a self-supervised manner. Moreover, it incorporates physics principles governing human motion. Specifically, we build a physics-based body representation and contact force model. We leverage them to impose novel physics-inspired training losses (i.e., force loss, contact loss, and Euler-Lagrange loss), enabling PhysPT to capture physical properties of the human body and the forces it experiences. Experiments demonstrate that, once trained, PhysPT can be directly applied to kinematics-based estimates to significantly enhance their physical plausibility and generate favourable motion forces. Furthermore, we show that these physically meaningful quantities translate into improved accuracy of an important downstream task: human action recognition.

Xiang Zhang, Xiaotian Li, Taoyue Wang et al.

Social interactions dominate our perceptions of the world and shape our daily behavior by attaching social meaning to acts as simple and spontaneous as gestures, facial expressions, voice, and speech. People mimic and otherwise respond to each other's postures, facial expressions, mannerisms, and other verbal and nonverbal behavior, and form appraisals or evaluations in the process. Yet, no publicly-available dataset includes multimodal recordings and self-report measures of multiple persons in social interaction. Dyadic recordings and annotation are lacking. We present a new data corpus of multimodal dyadic interaction (45 dyads, 90 persons) that includes synchronized multi-modality behavior (2D face video, 3D face geometry, thermal spectrum dynamics, voice and speech behavior, physiology (PPG, EDA, heart-rate, blood pressure, and respiration), and self-reported affect of all participants in a communicative interaction scenario. Two types of dyads are included: persons with shared past history and strangers. Annotations include social signals, agreement, disagreement, and neutral stance. With a potent emotion induction, these multimodal data will enable novel modeling of multimodal interpersonal behavior. We present extensive experiments to evaluate multimodal dyadic communication of dyads with and without interpersonal history, and their affect. This new database will make multimodal modeling of social interaction never possible before. The dataset includes 20TB of multimodal data to share with the research community.

Hanjing Wang, Qiang Ji

Epistemic uncertainty quantification (UQ) identifies where models lack knowledge. Traditional UQ methods, often based on Bayesian neural networks, are not suitable for pre-trained non-Bayesian models. Our study addresses quantifying epistemic uncertainty for any pre-trained model, which does not need the original training data or model modifications and can ensure broad applicability regardless of network architectures or training techniques. Specifically, we propose a gradient-based approach to assess epistemic uncertainty, analyzing the gradients of outputs relative to model parameters, and thereby indicating necessary model adjustments to accurately represent the inputs. We first explore theoretical guarantees of gradient-based methods for epistemic UQ, questioning the view that this uncertainty is only calculable through differences between multiple models. We further improve gradient-driven UQ by using class-specific weights for integrating gradients and emphasizing distinct contributions from neural network layers. Additionally, we enhance UQ accuracy by combining gradient and perturbation methods to refine the gradients. We evaluate our approach on out-of-distribution detection, uncertainty calibration, and active learning, demonstrating its superiority over current state-of-the-art UQ methods for pre-trained models.

Naiyu Yin, Tian Gao, Yue Yu et al.

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 both 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 issue of heteroscedastic noise, we introduce relaxed and implementable sufficient conditions, proving the identifiability of a general class of SEM subject to these conditions. Based on the identifiable general SEM, we propose a novel formulation for DAG learning that accounts for the variation in noise variance across variables and observations. We then propose an effective two-phase iterative DAG learning algorithm to address the increasing optimization difficulties and to learn a causal DAG from data with heteroscedastic variable 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.

Qiang Ji, Lin Cheng, Yue Zhou et al.

The integration of the high penetration of intermittent renewable energy sources (RES) and the retirement of thermal units have significantly aggravated the flexibility scarcity and real-time balancing challenges in power systems. Low-carbon steel production systems, based on green-hydrogen ironmaking and electrified melting, possess substantial demand response (DR) potential. This paper proposes a process-aware DR evaluation framework for hydrogen-integrated zero-carbon steel plants coupled with methanol production (H2-DRI-EAF-MeOH). First, a novel zero-carbon steel production system architecture is established to explicitly represent the energy-material flow coupling relationships among electricity, hydrogen, heat, iron, steel, CO2, and methanol. Second, to explicitly capture electric arc furnace (EAF) operational constraints while preserving optimization tractability, an operating feasible region model is developed and validated using field data from a pure hydrogen direct reduced iron and EAF plant, yielding an average relative error of 4.1%. Finally, a process-aware DR scheduling model is formulated by incorporating the proposed process deviation penalties to balance economic performance against process disturbance costs and operational acceptability. Additionally, dual-side evaluation metrics are developed to quantify grid-side regulation performance and load-side flexibility characteristics. Case studies demonstrate that under real-time pricing, the proposed system achieves an average DR capacity of 275.4 MW, improves the RES-load matching degree from 0.262 to 0.508, and reduces total operational costs by 17.78% compared with the baseline scheduling scheme. The proposed framework provides a theoretical foundation for RES-steel-chemical synergies.

Yufei Zhang, Zijun Cui, Jeffrey O. Kephart et al.

While 3D hand reconstruction from monocular images has made significant progress, generating accurate and temporally coherent motion estimates from videos remains challenging, particularly during hand-object interactions. In this paper, we present a novel 3D hand motion recovery framework that enhances image-based reconstructions through a diffusion-based and physics-augmented motion refinement model. Our model captures the distribution of refined motion estimates conditioned on initial ones, generating improved sequences through an iterative denoising process. Instead of relying on scarce annotated video data, we train our model only using motion capture data without images. We identify valuable intuitive physics knowledge during hand-object interactions, including key motion states and their associated motion constraints. We effectively integrate these physical insights into our diffusion model to improve its performance. Extensive experiments demonstrate that our approach significantly improves various frame-wise reconstruction methods, achieving state-of-the-art (SOTA) performance on existing benchmarks.

Qiang Ji, Kang Wang

Model-based eye tracking has been a dominant approach for eye gaze tracking because of its ability to generalize to different subjects, without the need of any training data and eye gaze annotations. Model-based eye tracking, however, is susceptible to eye feature detection errors, in particular for eye tracking in the wild. To address this issue, we propose a Bayesian framework for model-based eye tracking. The proposed system consists of a cascade-Bayesian Convolutional Neural Network (c-BCNN) to capture the probabilistic relationships between eye appearance and its landmarks, and a geometric eye model to estimate eye gaze from the eye landmarks. Given a testing eye image, the Bayesian framework can generate, through Bayesian inference, the eye gaze distribution without explicit landmark detection and model training, based on which it not only estimates the most likely eye gaze but also its uncertainty. Furthermore, with Bayesian inference instead of point-based inference, our model can not only generalize better to different sub-jects, head poses, and environments but also is robust to image noise and landmark detection errors. Finally, with the estimated gaze uncertainty, we can construct a cascade architecture that allows us to progressively improve gaze estimation accuracy. Compared to state-of-the-art model-based and learning-based methods, the proposed Bayesian framework demonstrates significant improvement in generalization capability across several benchmark datasets and in accuracy and robustness under challenging real-world conditions.

Yue Yu, Tian Gao, Naiyu Yin et al.

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 cyclic solution to the optimization problem, and 2) then we employ the Hodge decomposition of graphs and learn an acyclic graph by projecting the cyclic 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.

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.

Zijun Cui, Pavan Kapanipathi, Kartik Talamadupula et al.

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.

Sicheng Zhao, Shangfei Wang, Mohammad Soleymani et al.

The wide popularity of digital photography and social networks has generated a rapidly growing volume of multimedia data (i.e., image, music, and video), resulting in a great demand for managing, retrieving, and understanding these data. Affective computing (AC) of these data can help to understand human behaviors and enable wide applications. In this article, we survey the state-of-the-art AC technologies comprehensively for large-scale heterogeneous multimedia data. We begin this survey by introducing the typical emotion representation models from psychology that are widely employed in AC. We briefly describe the available datasets for evaluating AC algorithms. We then summarize and compare the representative methods on AC of different multimedia types, i.e., images, music, videos, and multimodal data, with the focus on both handcrafted features-based methods and deep learning methods. Finally, we discuss some challenges and future directions for multimedia affective computing.

Chao Gou, Tianyu Shen, Wenbo Zheng et al.

There has been much progress in data-driven artificial intelligence technology for medical image analysis in the last decades. However, it still remains challenging due to its distinctive complexity of acquiring and annotating image data, extracting medical domain knowledge, and explaining the diagnostic decision for medical image analysis. In this paper, we propose a data-knowledge-driven framework termed as Parallel Medical Imaging (PMI) for intelligent medical image analysis based on the methodology of interactive ACP-based parallel intelligence. In the PMI framework, computational experiments with predictive learning in a data-driven way are conducted to extract medical knowledge for diagnostic decision support. Artificial imaging systems are introduced to select and prescriptively generate medical image data in a knowledge-driven way to utilize medical domain knowledge. Through the closed-loop optimization based on parallel execution, our proposed PMI framework can boost the generalization ability and alleviate the limitation of medical interpretation for diagnostic decisions. Furthermore, we illustrate the preliminary implementation of PMI method through the case studies of mammogram analysis and skin lesion image analysis. Experimental results on several public medical image datasets demonstrate the effectiveness of proposed PMI.

Yue Wu, Qiang Ji

The locations of the fiducial facial landmark points around facial components and facial contour capture the rigid and non-rigid facial deformations due to head movements and facial expressions. They are hence important for various facial analysis tasks. Many facial landmark detection algorithms have been developed to automatically detect those key points over the years, and in this paper, we perform an extensive review of them. We classify the facial landmark detection algorithms into three major categories: holistic methods, Constrained Local Model (CLM) methods, and the regression-based methods. They differ in the ways to utilize the facial appearance and shape information. The holistic methods explicitly build models to represent the global facial appearance and shape information. The CLMs explicitly leverage the global shape model but build the local appearance models. The regression-based methods implicitly capture facial shape and appearance information. For algorithms within each category, we discuss their underlying theories as well as their differences. We also compare their performances on both controlled and in the wild benchmark datasets, under varying facial expressions, head poses, and occlusion. Based on the evaluations, we point out their respective strengths and weaknesses. There is also a separate section to review the latest deep learning-based algorithms. The survey also includes a listing of the benchmark databases and existing software. Finally, we identify future research directions, including combining methods in different categories to leverage their respective strengths to solve landmark detection "in-the-wild".

Siqi Nie, Ziheng Wang, Qiang Ji

Many computer vision applications involve modeling complex spatio-temporal patterns in high-dimensional motion data. Recently, restricted Boltzmann machines (RBMs) have been widely used to capture and represent spatial patterns in a single image or temporal patterns in several time slices. To model global dynamics and local spatial interactions, we propose to theoretically extend the conventional RBMs by introducing another term in the energy function to explicitly model the local spatial interactions in the input data. A learning method is then proposed to perform efficient learning for the proposed model. We further introduce a new method for multi-class classification that can effectively estimate the infeasible partition functions of different RBMs such that RBM is treated as a generative model for classification purpose. The improved RBM model is evaluated on two computer vision applications: facial expression recognition and human action recognition. Experimental results on benchmark databases demonstrate the effectiveness of the proposed algorithm.

Siqi Nie, Meng Zheng, Qiang Ji

Deep directed generative models have attracted much attention recently due to their generative modeling nature and powerful data representation ability. In this paper, we review different structures of deep directed generative models and the learning and inference algorithms associated with the structures. We focus on a specific structure that consists of layers of Bayesian Networks due to the property of capturing inherent and rich dependencies among latent variables. The major difficulty of learning and inference with deep directed models with many latent variables is the intractable inference due to the dependencies among the latent variables and the exponential number of latent variable configurations. Current solutions use variational methods often through an auxiliary network to approximate the posterior probability inference. In contrast, inference can also be performed directly without using any auxiliary network to maximally preserve the dependencies among the latent variables. Specifically, by exploiting the sparse representation with the latent space, max-max instead of max-sum operation can be used to overcome the exponential number of latent configurations. Furthermore, the max-max operation and augmented coordinate ascent are applied to both supervised and unsupervised learning as well as to various inference. Quantitative evaluations on benchmark datasets of different models are given for both data representation and feature learning tasks.

Yue Wu, Chao Gou, Qiang Ji

Facial landmark detection, head pose estimation, and facial deformation analysis are typical facial behavior analysis tasks in computer vision. The existing methods usually perform each task independently and sequentially, ignoring their interactions. To tackle this problem, we propose a unified framework for simultaneous facial landmark detection, head pose estimation, and facial deformation analysis, and the proposed model is robust to facial occlusion. Following a cascade procedure augmented with model-based head pose estimation, we iteratively update the facial landmark locations, facial occlusion, head pose and facial de- formation until convergence. The experimental results on benchmark databases demonstrate the effectiveness of the proposed method for simultaneous facial landmark detection, head pose and facial deformation estimation, even if the images are under facial occlusion.

Yue Wu, Qiang Ji

Cascade regression framework has been shown to be effective for facial landmark detection. It starts from an initial face shape and gradually predicts the face shape update from the local appearance features to generate the facial landmark locations in the next iteration until convergence. In this paper, we improve upon the cascade regression framework and propose the Constrained Joint Cascade Regression Framework (CJCRF) for simultaneous facial action unit recognition and facial landmark detection, which are two related face analysis tasks, but are seldomly exploited together. In particular, we first learn the relationships among facial action units and face shapes as a constraint. Then, in the proposed constrained joint cascade regression framework, with the help from the constraint, we iteratively update the facial landmark locations and the action unit activation probabilities until convergence. Experimental results demonstrate that the intertwined relationships of facial action units and face shapes boost the performances of both facial action unit recognition and facial landmark detection. The experimental results also demonstrate the effectiveness of the proposed method comparing to the state-of-the-art works.

Yue Wu, Qiang Ji

Feature learning with deep models has achieved impressive results for both data representation and classification for various vision tasks. Deep feature learning, however, typically requires a large amount of training data, which may not be feasible for some application domains. Transfer learning can be one of the approaches to alleviate this problem by transferring data from data-rich source domain to data-scarce target domain. Existing transfer learning methods typically perform one-shot transfer learning and often ignore the specific properties that the transferred data must satisfy. To address these issues, we introduce a constrained deep transfer feature learning method to perform simultaneous transfer learning and feature learning by performing transfer learning in a progressively improving feature space iteratively in order to better narrow the gap between the target domain and the source domain for effective transfer of the data from the source domain to target domain. Furthermore, we propose to exploit the target domain knowledge and incorporate such prior knowledge as a constraint during transfer learning to ensure that the transferred data satisfies certain properties of the target domain. To demonstrate the effectiveness of the proposed constrained deep transfer feature learning method, we apply it to thermal feature learning for eye detection by transferring from the visible domain. We also applied the proposed method for cross-view facial expression recognition as a second application. The experimental results demonstrate the effectiveness of the proposed method for both applications.

Yue Wu, Qiang Ji

There have been tremendous improvements for facial landmark detection on general "in-the-wild" images. However, it is still challenging to detect the facial landmarks on images with severe occlusion and images with large head poses (e.g. profile face). In fact, the existing algorithms usually can only handle one of them. In this work, we propose a unified robust cascade regression framework that can handle both images with severe occlusion and images with large head poses. Specifically, the method iteratively predicts the landmark occlusions and the landmark locations. For occlusion estimation, instead of directly predicting the binary occlusion vectors, we introduce a supervised regression method that gradually updates the landmark visibility probabilities in each iteration to achieve robustness. In addition, we explicitly add occlusion pattern as a constraint to improve the performance of occlusion prediction. For landmark detection, we combine the landmark visibility probabilities, the local appearances, and the local shapes to iteratively update their positions. The experimental results show that the proposed method is significantly better than state-of-the-art works on images with severe occlusion and images with large head poses. It is also comparable to other methods on general "in-the-wild" images.

Yue Wu, Ziheng Wang, Qiang Ji

Facial feature detection from facial images has attracted great attention in the field of computer vision. It is a nontrivial task since the appearance and shape of the face tend to change under different conditions. In this paper, we propose a hierarchical probabilistic model that could infer the true locations of facial features given the image measurements even if the face is with significant facial expression and pose. The hierarchical model implicitly captures the lower level shape variations of facial components using the mixture model. Furthermore, in the higher level, it also learns the joint relationship among facial components, the facial expression, and the pose information through automatic structure learning and parameter estimation of the probabilistic model. Experimental results on benchmark databases demonstrate the effectiveness of the proposed hierarchical probabilistic model.

Yue Wu, Zuoguan Wang, Qiang Ji

Facial feature tracking is an active area in computer vision due to its relevance to many applications. It is a nontrivial task, since faces may have varying facial expressions, poses or occlusions. In this paper, we address this problem by proposing a face shape prior model that is constructed based on the Restricted Boltzmann Machines (RBM) and their variants. Specifically, we first construct a model based on Deep Belief Networks to capture the face shape variations due to varying facial expressions for near-frontal view. To handle pose variations, the frontal face shape prior model is incorporated into a 3-way RBM model that could capture the relationship between frontal face shapes and non-frontal face shapes. Finally, we introduce methods to systematically combine the face shape prior models with image measurements of facial feature points. Experiments on benchmark databases show that with the proposed method, facial feature points can be tracked robustly and accurately even if faces have significant facial expressions and poses.

Siqi Nie, Qiang Ji

Deep directed generative models have attracted much attention recently due to their expressive representation power and the ability of ancestral sampling. One major difficulty of learning directed models with many latent variables is the intractable inference. To address this problem, most existing algorithms make assumptions to render the latent variables independent of each other, either by designing specific priors, or by approximating the true posterior using a factorized distribution. We believe the correlations among latent variables are crucial for faithful data representation. Driven by this idea, we propose an inference method based on the conditional pseudo-likelihood that preserves the dependencies among the latent variables. For learning, we propose to employ the hard Expectation Maximization (EM) algorithm, which avoids the intractability of the traditional EM by max-out instead of sum-out to compute the data likelihood. Qualitative and quantitative evaluations of our model against state of the art deep models on benchmark datasets demonstrate the effectiveness of the proposed algorithm in data representation and reconstruction.

Siqi Nie, Denis Deratani Maua, Cassio Polpo de Campos et al.

This work presents novel algorithms for learning Bayesian network structures with 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 uniformly 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. Some properties of these methods are discussed and proven. The approaches are empirically compared to each other and to a state-of-the-art method for learning bounded treewidth structures on a collection of public data sets with up to 100 variables. The experiments show that our exact algorithm outperforms the state of the art, and that the approximate approach is fairly accurate.

Cassio Polpo 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.