While code large language models have demonstrated remarkable progress in code generation, the generated code often exhibits poor runtime efficiency, limiting its practical application in performance-sensitive scenarios. To address this limitation, we propose an efficiency-oriented reinforcement learning framework guided by a novel performance reward. Based on this framework, we take a deeper dive into the code efficiency problem, identifying then proposing methods to overcome key bottlenecks: (1) Dynamic exploration overcomes the static data constraints of offline fine-tuning, enabling the discovery of more efficient code implementations. (2) The error-insensitive reinforcement learning method and high-contrast efficiency signals are crucial for mitigating systematic errors and achieving effective optimization. (3) Online exploration is most effective when starting from a high-correctness baseline, as this allows for efficiency improvements without sacrificing accuracy. With these discoveries, we finally propose a two-stage tuning method, which achieves high and balanced performance across correctness and efficiency. The results of experiments show the effectiveness of the method, which improves code correctness by 10.18% and runtime efficiency by 7.75% on a 7B model, achieving performance comparable to much larger model.

The Myers-Briggs Type Indicator (MBTI) is one of the most influential personality theories reflecting individual differences in thinking, feeling, and behaving. MBTI personality detection has garnered considerable research interest and has evolved significantly over the years. However, this task tends to be overly optimistic, as it currently does not align well with the natural distribution of population personality traits. Specifically, the self-reported labels in existing datasets result in data quality issues and the hard labels fail to capture the full range of population personality distributions. In this paper, we identify the task by constructing MBTIBench, the first manually annotated MBTI personality detection dataset with soft labels, under the guidance of psychologists. Our experimental results confirm that soft labels can provide more benefits to other psychological tasks than hard labels. We highlight the polarized predictions and biases in LLMs as key directions for future research.

Honglin Mu, Han He, Yuxin Zhou, Yunlong Feng, Yang Xu, Libo Qin, Xiaoming Shi, Zeming Liu, Xudong Han, Qi Shi, Qingfu Zhu, Wanxiang Che. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

The accuracy of assigning fluorophore identity and abundance, known as spectral unmixing, in biological fluorescence microscopy images remains a significant challenge due to the substantial overlap in emission spectra among fluorophores. In traditional laser scanning confocal spectral microscopy, fluorophore information is acquired by recording emission spectra with a single combination of discrete excitation wavelengths. However, organic fluorophores possess characteristic excitation spectra in addition to their unique emission spectral signatures. In this paper, we propose a generalized multi-view machine learning approach that leverages both excitation and emission spectra to significantly improve the accuracy in differentiating multiple highly overlapping fluorophores in a single image. By recording emission spectra of the same field with multiple combinations of excitation wavelengths, we obtain data representing different views of the underlying fluorophore distribution in the sample. We then propose a multi-view machine learning framework that allows for the flexible incorporation of noise information and abundance constraints, enabling the extraction of spectral signatures from reference images and efficient recovery of corresponding abundances in unknown mixed images. Numerical experiments on simulated image data demonstrate the method's efficacy in improving accuracy, allowing for the discrimination of 100 fluorophores with highly overlapping spectra. Furthermore, validation on images of mixtures of fluorescently labeled Escherichia coli highlights the power of the proposed multi-view strategy in discriminating fluorophores with spectral overlap in real biological images.

Existing image augmentation methods consist of two categories: perturbation-based methods and generative methods. Perturbation-based methods apply pre-defined perturbations to augment an original image, but only locally vary the image, thus lacking image diversity. In contrast, generative methods bring more image diversity in the augmented images but may not preserve semantic consistency, thus may incorrectly change the essential semantics of the original image. To balance image diversity and semantic consistency in augmented images, we propose SGID, a Semantic-guided Generative Image augmentation method with Diffusion models for image classification. Specifically, SGID employs diffusion models to generate augmented images with good image diversity. More importantly, SGID takes image labels and captions as guidance to maintain semantic consistency between the augmented and original images. Experimental results show that SGID outperforms the best augmentation baseline by 1.72% on ResNet-50 (from scratch), 0.33% on ViT (ImageNet-21k), and 0.14% on CLIP-ViT (LAION-2B). Moreover, SGID can be combined with other image augmentation baselines and further improves the overall performance. We demonstrate the semantic consistency and image diversity of SGID through quantitative human and automated evaluations, as well as qualitative case studies.

Haochen Tan, Zhijiang Guo, Zhan Shi, Lu Xu, Zhili Liu, Yunlong Feng, Xiaoguang Li, Yasheng Wang, Lifeng Shang, Qun Liu, Linqi Song. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Cross-domain text classification is a crucial task as it enables models to adapt to a target domain that lacks labeled data. It leverages or reuses rich labeled data from the different but related source domain(s) and unlabeled data from the target domain. To this end, previous work focuses on either extracting domain-invariant features or task-agnostic features, ignoring domain-aware features that may be present in the target domain and could be useful for the downstream task. In this paper, we propose a two-stage framework for cross-domain text classification. In the first stage, we finetune the model with mask language modeling (MLM) and labeled data from the source domain. In the second stage, we further fine-tune the model with self-supervised distillation (SSD) and unlabeled data from the target domain. We evaluate its performance on a public cross-domain text classification benchmark and the experiment results show that our method achieves new state-of-the-art results for both single-source domain adaptations (94.17% +1.03%) and multi-source domain adaptations (95.09% +1.34%).

Large-scale high-quality training data is important for improving the performance of models. After trained with data that has rationales (reasoning steps), models gain reasoning capability. However, the dataset with high-quality rationales is relatively scarce due to the high annotation cost. To address this issue, we propose Self-motivated Learning framework. The framework motivates the model itself to automatically generate rationales on existing datasets. Based on the inherent rank from correctness across multiple rationales, the model learns to generate better rationales, leading to higher reasoning capability. Specifically, we train a reward model with the rank to evaluate the quality of rationales, and improve the performance of reasoning through reinforcement learning. Experiment results of Llama2 7B on multiple reasoning datasets show that our method significantly improves the reasoning ability of models, even outperforming InstructGPT in some datasets.

With the rise of Large Language Models (LLMs), AI assistants’ ability to utilize tools, especially through API calls, has advanced notably. This progress has necessitated more accurate evaluation methods. Many existing studies adopt static evaluation, where they assess AI assistants’ API call based on pre-defined dialogue histories. However, such evaluation method can be misleading, as an AI assistant might fail in generating API calls from preceding human interaction in real cases. Instead of the resource-intensive method of direct human-machine interactions, we propose Automated Dynamic Evaluation (AutoDE) to assess an assistant’s API call capability without human involvement. In our framework, we endeavor to closely mirror genuine human conversation patterns in human-machine interactions, using a LLM-based user agent, equipped with a user script to ensure human alignment. Experimental results highlight that AutoDE uncovers errors overlooked by static evaluations, aligning more closely with human assessment. Testing four AI assistants using our crafted benchmark, our method further mirrored human evaluation compared to conventional static evaluations.

Accurate localization is an essential technology for the flexible navigation of robots in large-scale environments. Both SLAM-based and map-based localization will increase the computing load due to the increase in map size, which will affect downstream tasks such as robot navigation and services. To this end, we propose a localization system based on Block Maps (BMs) to reduce the computational load caused by maintaining large-scale maps. Firstly, we introduce a method for generating block maps and the corresponding switching strategies, ensuring that the robot can estimate the state in large-scale environments by loading local map information. Secondly, global localization according to Branch-and-Bound Search (BBS) in the 3D map is introduced to provide the initial pose. Finally, a graph-based optimization method is adopted with a dynamic sliding window that determines what factors are being marginalized whether a robot is exposed to a BM or switching to another one, which maintains the accuracy and efficiency of pose tracking. Comparison experiments are performed on publicly available large-scale datasets. Results show that the proposed method can track the robot pose even though the map scale reaches more than 6 kilometers, while efficient and accurate localization is still guaranteed on NCLT [6] and M2DGR [35]. Codes and data will be publicly available on https://github.com/YixFeng/blocklocalization.

In this work, we propose a novel method named \textbf{Auto}mated \textbf{P}rocess-\textbf{S}upervised \textbf{V}erifier (\textbf{\textsc{AutoPSV}}) to enhance the reasoning capabilities of large language models (LLMs) by automatically annotating the reasoning steps. \textsc{AutoPSV} begins by training a verification model on the correctness of final answers, enabling it to generate automatic process annotations. This verification model assigns a confidence score to each reasoning step, indicating the probability of arriving at the correct final answer from that point onward. We detect relative changes in the verification's confidence scores across reasoning steps to automatically annotate the reasoning process, enabling error detection even in scenarios where ground truth answers are unavailable. This alleviates the need for numerous manual annotations or the high computational costs associated with model-induced annotation approaches. We experimentally validate that the step-level confidence changes learned by the verification model trained on the final answer correctness can effectively identify errors in the reasoning steps. We demonstrate that the verification model, when trained on process annotations generated by \textsc{AutoPSV}, exhibits improved performance in selecting correct answers from multiple LLM-generated outputs. Notably, we achieve substantial improvements across five datasets in mathematics and commonsense reasoning. The source code of \textsc{AutoPSV} is available at \url{https://github.com/rookie-joe/AutoPSV}.

MOTIVATION: Multispectral biological fluorescence microscopy has enabled the identification of multiple targets in complex samples. The accuracy in the unmixing result degrades (i) as the number of fluorophores used in any experiment increases and (ii) as the signal-to-noise ratio in the recorded images decreases. Further, the availability of prior knowledge regarding the expected spatial distributions of fluorophores in images of labeled cells provides an opportunity to improve the accuracy of fluorophore identification and abundance. RESULTS: We propose a regularized sparse and low-rank Poisson regression unmixing approach (SL-PRU) to deconvolve spectral images labeled with highly overlapping fluorophores which are recorded in low signal-to-noise regimes. First, SL-PRU implements multipenalty terms when pursuing sparseness and spatial correlation of the resulting abundances in small neighborhoods simultaneously. Second, SL-PRU makes use of Poisson regression for unmixing instead of least squares regression to better estimate photon abundance. Third, we propose a method to tune the SL-PRU parameters involved in the unmixing procedure in the absence of knowledge of the ground truth abundance information in a recorded image. By validating on simulated and real-world images, we show that our proposed method leads to improved accuracy in unmixing fluorophores with highly overlapping spectra. AVAILABILITY AND IMPLEMENTATION: The source code used for this article was written in MATLAB and is available with the test data at https://github.com/WANGRUOGU/SL-PRU.

With the continuous improvement of supercomputer performance and the integration of artificial intelligence with traditional scientific computing, the scale of applications is gradually increasing, from millions to tens of millions of computing cores, which raises great challenges to achieve high scalability and efficiency of parallel applications on super-large-scale systems. Taking the Sunway exascale prototype system as an example, in this paper we first analyze the challenges of high scalability and high efficiency for parallel applications in the exascale era. To overcome these challenges, the optimization technologies used in the parallel supporting environment software on the Sunway exascale prototype system are highlighted, including the parallel operating system, input/output (I/O) optimization technology, ultra-large-scale parallel debugging technology, 10-million-core parallel algorithm, and mixed-precision method. Parallel operating systems and I/O optimization technology mainly support large-scale system scaling, while the ultra-large-scale parallel debugging technology, 10-million-core parallel algorithm, and mixed-precision method mainly enhance the efficiency of large-scale applications. Finally, the contributions to various applications running on the Sunway exascale prototype system are introduced, verifying the effectiveness of the parallel supporting environment design.

In a regression setup, we study in this brief the performance of Gaussian empirical gain maximization (EGM), which includes a broad variety of well-established robust estimation approaches. In particular, we conduct a refined learning theory analysis for Gaussian EGM, investigate its regression calibration properties, and develop improved convergence rates in the presence of heavy-tailed noise. To achieve these purposes, we first introduce a new weak moment condition that could accommodate the cases where the noise distribution may be heavy-tailed. Based on the moment condition, we then develop a novel comparison theorem that can be used to characterize the regression calibration properties of Gaussian EGM. It also plays an essential role in deriving improved convergence rates. Therefore, the present study broadens our theoretical understanding of Gaussian EGM.

This article presents Jdebug, a fast, non-intrusive and scalable fault locating tool for extreme-scale parallel applications. Large-scale debugging has drawn more attention with the increasing scale of supercomputers and applications. To eliminate program intrusion caused by traditional instrumentation or interception during debugging information acquisition, we introduce the out-of-band management into large-scale debugging. We propose a rapid information gathering scheme that separates user and debugging traffic to solve scalability problem and to eliminate program interference during merging data. Observations of Program Counters (PC) and performance characteristics in suspended applications find abnormalities and help locate abnormal threads caused by software errors or hardware failures effectively. Evaluation shows that Jdebug collects PCs of over 20 million cores on the new Sunway supercomputer within 1.97 seconds, and can locate the abnormal threads in 1.4 seconds with an accuracy of 92.5%. In the running test of three fundamental benchmarks (HPL, HPCG, Graph500) and seventeen real-world applications, Jdebug quickly and accurately locates abnormal threads to help find scalability errors and hardware failures including memory access failures, communication failures, and execution component failures, which validates its effectiveness.

Stemming from information-theoretic learning, the correntropy criterion and its applications to machine learning tasks have been extensively studied and explored. Its application to regression problems leads to the robustness-enhanced regression paradigm: correntropy-based regression. Having drawn a great variety of successful real-world applications, its theoretical properties have also been investigated recently in a series of studies from a statistical learning viewpoint. The resulting big picture is that correntropy-based regression regresses toward the conditional mode function or the conditional mean function robustly under certain conditions. Continuing this trend and going further, in this study, we report some new insights into this problem. First, we show that under the additive noise regression model, such a regression paradigm can be deduced from minimum distance estimation, implying that the resulting estimator is essentially a minimum distance estimator and thus possesses robustness properties. Second, we show that the regression paradigm in fact provides a unified approach to regression problems in that it approaches the conditional mean, the conditional mode, and the conditional median functions under certain conditions. Third, we present some new results when it is used to learn the conditional mean function by developing its error bounds and exponential convergence rates under conditional ([Formula: see text])-moment assumptions. The saturation effect on the established convergence rates, which was observed under ([Formula: see text])-moment assumptions, still occurs, indicating the inherent bias of the regression estimator. These novel insights deepen our understanding of correntropy-based regression, help cement the theoretic correntropy framework, and enable us to investigate learning schemes induced by general bounded nonconvex loss functions.

We develop in this letter a framework of empirical gain maximization (EGM) to address the robust regression problem where heavy-tailed noise or outliers may be present in the response variable. The idea of EGM is to approximate the density function of the noise distribution instead of approximating the truth function directly as usual. Unlike the classical maximum likelihood estimation that encourages equal importance of all observations and could be problematic in the presence of abnormal observations, EGM schemes can be interpreted from a minimum distance estimation viewpoint and allow the ignorance of those observations. Furthermore, we show that several well-known robust nonconvex regression paradigms, such as Tukey regression and truncated least square regression, can be reformulated into this new framework. We then develop a learning theory for EGM by means of which a unified analysis can be conducted for these well-established but not fully understood regression approaches. This new framework leads to a novel interpretation of existing bounded nonconvex loss functions. Within this new framework, the two seemingly irrelevant terminologies, the well-known Tukey's biweight loss for robust regression and the triweight kernel for nonparametric smoothing, are closely related. More precisely, we show that Tukey's biweight loss can be derived from the triweight kernel. Other frequently employed bounded nonconvex loss functions in machine learning, such as the truncated square loss, the Geman-McClure loss, and the exponential squared loss, can also be reformulated from certain smoothing kernels in statistics. In addition, the new framework enables us to devise new bounded nonconvex loss functions for robust learning.

This paper studies the nonparametric modal regression problem systematically from a statistical learning viewpoint. Originally motivated by pursuing a theoretical understanding of the maximum correntropy criterion based regression (MCCR), our study reveals that MCCR with a tending-to-zero scale parameter is essentially modal regression. We show that the nonparametric modal regression problem can be approached via the classical empirical risk minimization. Some efforts are then made to develop a framework for analyzing and implementing modal regression. For instance, the modal regression function is described, the modal regression risk is defined explicitly and its Bayes rule is characterized; for the sake of computational tractability, the surrogate modal regression risk, which is termed as the generalization risk in our study, is introduced. On the theoretical side, the excess modal regression risk, the excess generalization risk, the function estimation error, and the relations among the above three quantities are studied rigorously. It turns out that under mild conditions, function estimation consistency and convergence may be pursued in modal regression as in vanilla regression protocols such as mean regression, median regression, and quantile regression. On the practical side, the implementation issues of modal regression including the computational algorithm and the selection of the tuning parameters are discussed. Numerical validations on modal regression are also conducted to verify our findings.

In this paper, we consider the $\ell_q-$regularized kernel regression with $0 < q \leq 1$. In form, the algorithm minimizes a least-square loss functional adding a coefficient-based $\ell_q-$penalty term over a linear span of features generated by a kernel function. We study the asymptotic behavior of the algorithm under the framework of learning theory. The contribution of this paper is two-fold. First, we derive a tight bound on the $\ell_2-$empirical covering numbers of the related function space involved in the error analysis. Based on this result, we obtain the convergence rates for the $\ell_1-$regularized kernel regression which is the best so far. Second, for the case $0 < q < 1$, we show that the regularization parameter plays a role as a trade-off between sparsity and convergence rates. Under some mild conditions, the fraction of non-zero coefficients in a local minimizer of the algorithm will tend to $0$ at a polynomial decay rate when the sample size $m$ becomes large. As the concerned algorithm is non-convex, we also discuss how to generate a minimizing sequence iteratively, which can help us to search a local minimizer around any initial point.

The demand for automatic extraction of true information (i.e., truths) from conflicting multi-source data has soared recently. A variety of truth discovery methods have witnessed great successes via jointly estimating source reliability and truths. All existing truth discovery methods focus on providing a point estimator for each object's truth, but in many real-world applications, confidence interval estimation of truths is more desirable, since confidence interval contains richer information. To address this challenge, in this paper, we propose a novel truth discovery method (ETCIBoot) to construct confidence interval estimates as well as identify truths, where the bootstrapping techniques are nicely integrated into the truth discovery procedure. Due to the properties of bootstrapping, the estimators obtained by ETCIBoot are more accurate and robust compared with the state-of-the-art truth discovery approaches. The proposed framework is further adapted to deal with large-scale truth discovery task in distributed paradigm. Theoretically, we prove the asymptotical consistency of the confidence interval obtained by ETCIBoot. Experimentally, we demonstrate that ETCIBoot is not only effective in constructing confidence intervals but also able to obtain better truth estimates.

We study the density estimation problem with observations generated by certain dynamical systems that admit a unique underlying invariant Lebesgue density. Observations drawn from dynamical systems are not independent and moreover, usual mixing concepts may not be appropriate for measuring the dependence among these observations. By employing the $\mathcal{C}$-mixing concept to measure the dependence, we conduct statistical analysis on the consistency and convergence of the kernel density estimator. Our main results are as follows: First, we show that with properly chosen bandwidth, the kernel density estimator is universally consistent under $L_1$-norm; Second, we establish convergence rates for the estimator with respect to several classes of dynamical systems under $L_1$-norm. In the analysis, the density function $f$ is only assumed to be Hölder continuous or pointwise Hölder controllable which is a weak assumption in the literature of nonparametric density estimation and also more realistic in the dynamical system context. Last but not least, we prove that the same convergence rates of the estimator under $L_\infty$-norm and $L_1$-norm can be achieved when the density function is Hölder continuous, compactly supported, and bounded. The bandwidth selection problem of the kernel density estimator for dynamical system is also discussed in our study via numerical simulations.

The demand for automatic extraction of true information (i.e., truths) from conflicting multi-source data has soared recently. A variety of truth discovery methods have witnessed great successes via jointly estimating source reliability and truths. All existing truth discovery methods focus on providing a point estimator for each object's truth, but in many real-world applications, confidence interval estimation of truths is more desirable, since confidence interval contains richer information. To address this challenge, in this paper, we propose a novel truth discovery method (ETCIBoot) to construct confidence interval estimates as well as identify truths, where the bootstrapping techniques are nicely integrated into the truth discovery procedure. Due to the properties of bootstrapping, the estimators obtained by ETCIBoot are more accurate and robust compared with the state-of-the-art truth discovery approaches. Theoretically, we prove the asymptotical consistency of the confidence interval obtained by ETCIBoot. Experimentally, we demonstrate that ETCIBoot is not only effective in constructing confidence intervals but also able to obtain better truth estimates.

Kernelized elastic net regularization (KENReg) is a kernelization of the well-known elastic net regularization (Zou & Hastie, 2005). The kernel in KENReg is not required to be a Mercer kernel since it learns from a kernelized dictionary in the coefficient space. Feng, Yang, Zhao, Lv, and Suykens (2014) showed that KENReg has some nice properties including stability, sparseness, and generalization. In this letter, we continue our study on KENReg by conducting a refined learning theory analysis. This letter makes the following three main contributions. First, we present refined error analysis on the generalization performance of KENReg. The main difficulty of analyzing the generalization error of KENReg lies in characterizing the population version of its empirical target function. We overcome this by introducing a weighted Banach space associated with the elastic net regularization. We are then able to conduct elaborated learning theory analysis and obtain fast convergence rates under proper complexity and regularity assumptions. Second, we study the sparse recovery problem in KENReg with fixed design and show that the kernelization may improve the sparse recovery ability compared to the classical elastic net regularization. Finally, we discuss the interplay among different properties of KENReg that include sparseness, stability, and generalization. We show that the stability of KENReg leads to generalization, and its sparseness confidence can be derived from generalization. Moreover, KENReg is stable and can be simultaneously sparse, which makes it attractive theoretically and practically.

This letter addresses the robustness problem when learning a large margin classifier in the presence of label noise. In our study, we achieve this purpose by proposing robustified large margin support vector machines. The robustness of the proposed robust support vector classifiers (RSVC), which is interpreted from a weighted viewpoint in this work, is due to the use of nonconvex classification losses. Besides the robustness, we also show that the proposed RSCV is simultaneously smooth, which again benefits from using smooth classification losses. The idea of proposing RSVC comes from M-estimation in statistics since the proposed robust and smooth classification losses can be taken as one-sided cost functions in robust statistics. Its Fisher consistency property and generalization ability are also investigated. Besides the robustness and smoothness, another nice property of RSVC lies in the fact that its solution can be obtained by solving weighted squared hinge loss-based support vector machine problems iteratively. We further show that in each iteration, it is a quadratic programming problem in its dual space and can be solved by using state-of-the-art methods. We thus propose an iteratively reweighted type algorithm and provide a constructive proof of its convergence to a stationary point. Effectiveness of the proposed classifiers is verified on both artificial and real data sets.

This letter investigates the supervised learning problem with observations drawn from certain general stationary stochastic processes. Here by general, we mean that many stationary stochastic processes can be included. We show that when the stochastic processes satisfy a generalized Bernstein-type inequality, a unified treatment on analyzing the learning schemes with various mixing processes can be conducted and a sharp oracle inequality for generic regularized empirical risk minimization schemes can be established. The obtained oracle inequality is then applied to derive convergence rates for several learning schemes such as empirical risk minimization (ERM), least squares support vector machines (LS-SVMs) using given generic kernels, and SVMs using gaussian kernels for both least squares and quantile regression. It turns out that for independent and identically distributed (i.i.d.) processes, our learning rates for ERM recover the optimal rates. For non-i.i.d. processes, including geometrically [Formula: see text]-mixing Markov processes, geometrically [Formula: see text]-mixing processes with restricted decay, [Formula: see text]-mixing processes, and (time-reversed) geometrically [Formula: see text]-mixing processes, our learning rates for SVMs with gaussian kernels match, up to some arbitrarily small extra term in the exponent, the optimal rates. For the remaining cases, our rates are at least close to the optimal rates. As a by-product, the assumed generalized Bernstein-type inequality also provides an interpretation of the so-called effective number of observations for various mixing processes.

This paper addresses the robust gradient learning (RGL) problem. Gradient learning models aim at learning the gradient vector of some target functions in supervised learning problems, which can be further used to applications, such as variable selection, coordinate covariance estimation, and supervised dimension reduction. However, existing GL models are not robust to outliers or heavy-tailed noise. This paper provides an RGL framework to address this problem in both regression and classification. This is achieved by introducing a robust regression loss function and proposing a robust classification loss. Moreover, our RGL algorithm works in an instance-based kernelized dictionary instead of some fixed reproducing kernel Hilbert space, which may provide more flexibility. To solve the proposed nonconvex model, a simple computational algorithm based on gradient descent is provided and the convergence of the proposed method is also analyzed. We then apply the proposed RGL model to applications, such as nonlinear variable selection and coordinate covariance estimation. The efficiency of our proposed model is verified on both synthetic and real data sets.

This paper addresses the robust low-rank tensor recovery problems. Tensor recovery aims at reconstructing a low-rank tensor from some linear measurements, which finds applications in image processing, pattern recognition, multitask learning, and so on. In real-world applications, data might be contaminated by sparse gross errors. However, the existing approaches may not be very robust to outliers. To resolve this problem, this paper proposes approaches based on the regularized redescending M-estimators, which have been introduced in robust statistics. The robustness of the proposed approaches is achieved by the regularized redescending M-estimators. However, the nonconvexity also leads to a computational difficulty. To handle this problem, we develop algorithms based on proximal and linearized block coordinate descent methods. By explicitly deriving the Lipschitz constant of the gradient of the data-fitting risk, the descent property of the algorithms is present. Moreover, we verify that the objective functions of the proposed approaches satisfy the Kurdyka-Łojasiewicz property, which establishes the global convergence of the algorithms. The numerical experiments on synthetic data as well as real data verify that our approaches are robust in the presence of outliers and still effective in the absence of outliers.

© 1994-2012 IEEE. In this letter, we propose a rank-one tensor updating algorithm for solving tensor completion problems. Unlike the existing methods which penalize the tensor by using the sum of nuclear norms of unfolding matrices, our optimization model directly employs the tensor nuclear norm which is studied recently. Under the framework of the conditional gradient method, we show that at each iteration, solving the proposed model amounts to computing the tensor spectral norm and the related rank-one tensor. Because the problem of finding the related rank-one tensor is NP-hard, we propose a subroutine to solve it approximately, which is of low computational complexity. Experimental results on real datasets show that our algorithm is efficient and effective.

Visual saliency is a probabilistic estimate of how likely a given spatial area in an image or video is to attract human visual attention relative to other areas. Bottom-up saliency models aggregate low-level image features like luminance and color contrast, flicker, 2D motion, etc. to construct a plausible saliency map. In this paper, we introduce 3D motion (object movements towards or away from the observer) into bottom-up video saliency modeling. Given availability of per-pixel depth maps, we first propose a novel algorithm to estimate 3D motion vectors (3DMVs) for arbitrarily shaped sub-blocks in texture-plus-depth videos. We then derive two feature channels from 3DMVs to be incorporated into a widely accepted bottom-up saliency model. Experiments on subjective quality of Region-of-Interest (ROI) based video coding show that our enriched saliency model with 3DMV channels is more accurate in estimating human visual attention.

Visual saliency is a probabilistic estimate of how likely a spatial area in an image or video frame is to attract human visual attention relative to other areas. When existing bottom-up saliency models aggregate low-level features to construct a plausible saliency map, only 2-D motion cues are used as motion features, even though videos typically capture dynamic 3-D scenes. In this paper, we introduce 3-D motion into bottom-up saliency modeling for texture-plus-depth videos. We first propose an efficient 3-D motion estimation algorithm, which computes a 3-D motion vector (3DMV) for each sub-block in the frame. Using the computed 3DMVs, we then derive several saliency channels (called 3DMV channels), which are incorporated into a bottom-up saliency model to obtain enhanced saliency maps. Experiments tracking human gaze show that incorporating our 3DMV channels into bottom-up saliency model significantly improves the accuracy of derived saliency maps.

Eye gaze is now used as a content adaptation trigger in interactive media applications, such as customized advertisement in video, and bit allocation in streaming video based on region-of-interest (ROI). The reaction time of a gaze-based networked system, however, is lower-bounded by the network round trip time (RTT). Furthermore, only low-sampling-rate gaze data is available when commonly available webcam is employed for gaze tracking. To realize responsive adaptation of media content even under non-negligible RTT and using common low-cost webcams, we propose a Hidden Markov Model (HMM) based gaze-prediction system that utilizes the visual saliency of the content being viewed. Specifically, our HMM has two states corresponding to two of human's intrinsic gaze behavioral movements, and its model parameters are derived offline via analysis of each video's visual saliency maps. Due to the strong prior of likely gaze locations offered by saliency information, accurate runtime gaze prediction is possible even under large RTT and using common webcam. We demonstrate the applicability of our low-cost gaze prediction system by focusing on ROI-based bit allocation for networked video streaming. To reduce transmission rate of a video stream without degrading viewer's perceived visual quality, we allocate more bits to encode the viewer's current spatial ROI, while devoting fewer bits in other spatial regions. The challenge lies in overcoming the delay between the time a viewer's ROI is detected by gaze tracking, to the time the effected video is encoded, delivered and displayed at the viewer's terminal. To this end, we use our proposed low-cost gaze prediction system to predict future eye gaze locations, so that optimized bit allocation can be performed for future frames. Through extensive subjective testing, we show that bit-rate can be reduced by up to 29% without noticeable visual quality degradation when RTT is as high as 200 ms.

The ability of a person to perceive image details falls precipitously with larger angle away from his visual focus. At any given bitrate, perceived visual quality can be improved by employing region-of-interest (ROI) coding, where higher encoding quality is judiciously applied only to regions close to a viewer's focal point. Straight-forward matching of viewer's focal point with ROI coding using a live encoder, however, is computation-intensive. In this paper, we propose a system that supports ROI coding without the need of a live encoder. The system is based on dynamic switching between two pre-encoded streams of the same content: one at high quality (HQ), and the other at mixed quality (MQ), where quality of a spatial region depends on its pre-computed visual saliency values. Distributed source coding (DSC) frames are periodically inserted to facilitate switching. Using a Hidden Markov Model (HMM) to model a viewer's temporal gaze movement, MQ stream is pre-encoded based on ROI coding to minimize the expected streaming rate, while keeping the probability of a viewer observing low quality (LQ) spatial regions below an application-specific ϵ. At stream time, the viewer's gaze locations are collected and transmitted to server for intelligent stream switching. In particular, server employs MQ stream only if: i) viewer's tracked gaze location falls inside the high-saliency regions, and ii) the probability that a viewer's gaze point will soon move outside high-saliency regions, computed using tracked gaze data and updated saliency values, is below ϵ. Experiments showed that video streaming rate can be reduced by up to 44%, and subjective quality is noticeably better than a competing scheme at the same rate where the entire video is encoded using equal quantization.

With the advent of eye gaze tracking technology, eye gaze is increasingly being used as a media interaction trigger in a variety of applications, such as eye typing, video content customization, and network video streaming based on region-of-interest (ROI). The reaction time of a gaze-based networked system, however, is in practice lower-bounded by the round trip time (RTT) of today's networks, which can be large. To improve the efficacy of gaze-based networked systems, in the paper we propose a Hidden Markov Model (HMM)-based gaze prediction strategy to predict future gaze locations to lower end-to-end reaction delay. We first design an HMM with three states corresponding to human's three major types of intrinsic eye movements. HMM parameters are obtained offline on a per-video basis during training phase. During testing phase, a window of noisy gaze observations are collected in real-time as input to a forward algorithm, which computes the most likely HMM state. Given the deduced HMM state, linear prediction is used to predict gaze location RTT seconds into the future. We demonstrate the applicability of our gaze prediction strategy by focusing on ROI-based bit allocation for network video streaming. To reduce transmission rate of a video stream without degrading viewer's perceived visual quality, we allocate more bits to encode the viewer's current spatial ROI, while devoting fewer bits in other spatial regions. The challenge lies in overcoming the delay between the time a viewer's ROI is detected by gaze tracking, to the time the effected video is encoded, delivered and displayed at the viewer's terminal. To this end, we use our proposed gaze-prediction strategy to predict future eye gaze locations, so that optimized bit allocation can be performed for future frames. Our experiments show that bit rate can be reduced by 21% without noticeable visual quality degradation when end-to-end network delay is as high as 200ms.