Haibo Li

Haibo Li

Computing posterior distributions in large-scale Bayesian linear inverse problems is challenging due to the high dimensionality of the parameter space. In this work, we develop a data-informed framework that shifts the computational focus from the parameter space to the data space. We rigorously characterize an intrinsically low-dimensional data space, establish its isometric embedding into the parameter space, and show that the prior-to-posterior update is confined to a data-informed subspace. This perspective allows posterior inference to be carried out in a reduced data-informed subspace. Based on this formulation, we propose a quotient-space Golub--Kahan bidiagonalization method to construct data-informed Krylov subspaces, and integrate empirical Bayesian inference into the iterative framework, enabling simultaneous hyperparameter estimation and posterior approximation in a matrix-free manner. Numerical experiments on representative problems support the theoretical framework and demonstrate the effectiveness of the resulting method.

Jun Ye, Haibo Li, Lili Xiao

In this paper numerical methods for solving stochastic differential equations with Markovian switching (SDEwMSs) are developed by pathwise approximation. The proposed family of strong predictor-corrector Euler-Maruyama methods is designed to overcome the propagation of errors during the simulation of an approximate path. This paper not only shows the strong convergence of the numerical solution to the exact solution but also reveals the order of the error under some conditions on the coefficient functions. A natural analogue of $p$-stability criterion is studied. Numerical examples are given to illustrate the computational efficiency of the new predictor-corrector Euler-Maruyama approximation.

Haibo Li, Qingyue Deng, Jijiang Li et al.

Projector compensation seeks to correct geometric and photometric distortions that occur when images are projected onto nonplanar or textured surfaces. However, most existing methods are highly setup-dependent, requiring fine-tuning or retraining whenever the surface, lighting, or projector-camera pose changes. Progress has been limited by two key challenges: (1) the absence of large, diverse training datasets and (2) existing geometric correction models are typically constrained by specific spatial setups; without further retraining or fine-tuning, they often fail to generalize directly to novel geometric configurations. We introduce SIComp, the first Setup-Independent framework for full projector Compensation, capable of generalizing to unseen setups without fine-tuning or retraining. To enable this, we construct a large-scale real-world dataset spanning 277 distinct projector-camera setups. SIComp adopts a co-adaptive design that decouples geometry and photometry: A carefully tailored optical flow module performs online geometric correction, while a novel photometric network handles photometric compensation. To further enhance robustness under varying illumination, we integrate intensity-varying surface priors into the network design. Extensive experiments demonstrate that SIComp consistently produces high-quality compensation across diverse unseen setups, substantially outperforming existing methods in terms of generalization ability and establishing the first generalizable solution to projector compensation. The code and dataset are available on our project page: https://hai-bo-li.github.io/SIComp/

Xiaogang Cheng, Bin Yang, Kaige Tan et al.

In human-centered intelligent building, real-time measurements of human thermal comfort play critical roles and supply feedback control signals for building heating, ventilation, and air conditioning (HVAC) systems. Due to the challenges of intra- and inter-individual differences and skin subtleness variations, there is no satisfactory solution for thermal comfort measurements until now. In this paper, a non-invasive measuring method based on skin sensitivity index and deep learning (NISDL) was proposed to measure real-time skin temperature. A new evaluating index, named skin sensitivity index (SSI), was defined to overcome individual differences and skin subtleness variations. To illustrate the effectiveness of SSI proposed, two multi-layers deep learning framework (NISDL method I and II) was designed and the DenseNet201 was used for extracting features from skin images. The partly personal saturation temperature (NIPST) algorithm was use for algorithm comparisons. Another deep learning algorithm without SSI (DL) was also generated for algorithm comparisons. Finally, a total of 1.44 million image data was used for algorithm validation. The results show that 55.6180% and 52.2472% error values (NISDL method I, II) are scattered at [0, 0.25), and the same error intervals distribution of NIPST is 35.3933%.

Bin Yang, Xiaogang Cheng, Dengxin Dai et al.

Individual thermal comfort perception gives important feedback signals for energy efficient control of smart buildings. However, there is no effective method to measure real-time thermal comfort status of individual occupant until now. For overcoming this challenge, a novel macro posed based non-invasive perception method for thermal comfort (NIMAP) was presented. The occupant pose images were captured by normal phone camera (computer or cell phone) and the corresponding 2D coordinates can be obtained. Based on this, a novel pose recognition algorithm for thermal comfort, including 12 sub-algorithms, was presented. The 12 thermal comfort related macro poses can be recognized. Further, based on Fanger theory, 369 subjects were invited for subjective questionnaire survey. 3 human occupants participated in the validation of the proposed method and massive data were collected. All the 12 thermal comfort related poses can be recognized effectively.

Xiaogang Cheng, Bin Yang, Anders Hedman et al.

Human thermal comfort measurement plays a critical role in giving feedback signals for building energy efficiency. A non-invasive measuring method based on subtleness magnification and deep learning (NIDL) was designed to achieve a comfortable, energy efficient built environment. The method relies on skin feature data, e.g., subtle motion and texture variation, and a 315-layer deep neural network for constructing the relationship between skin features and skin temperature. A physiological experiment was conducted for collecting feature data (1.44 million) and algorithm validation. The non-invasive measurement algorithm based on a partly-personalized saturation temperature model (NIPST) was used for algorithm performance comparisons. The results show that the mean error and median error of the NIDL are 0.4834 Celsius and 0.3464 Celsius which is equivalent to accuracy improvements of 16.28% and 4.28%, respectively.

Xiaogang Cheng, Guoqing Liu, Anders Hedman et al.

Vision-based methods for visibility estimation can play a critical role in reducing traffic accidents caused by fog and haze. To overcome the disadvantages of current visibility estimation methods, we present a novel data-driven approach based on Gaussian image entropy and piecewise stationary time series analysis (SPEV). This is the first time that Gaussian image entropy is used for estimating atmospheric visibility. To lessen the impact of landscape and sunshine illuminance on visibility estimation, we used region of interest (ROI) analysis and took into account relative ratios of image entropy, to improve estimation accuracy. We assume fog and haze cause blurred images and that fog and haze can be considered as a piecewise stationary signal. We used piecewise stationary time series analysis to construct the piecewise causal relationship between image entropy and visibility. To obtain a real-world visibility measure during fog and haze, a subjective assessment was established through a study with 36 subjects who performed visibility observations. Finally, a total of two million videos were used for training the SPEV model and validate its effectiveness. The videos were collected from the constantly foggy and hazy Tongqi expressway in Jiangsu, China. The contrast model of visibility estimation was used for algorithm performance comparison, and the validation results of the SPEV model were encouraging as 99.14% of the relative errors were less than 10%.

Yang Zhong, Josephine Sullivan, Haibo Li

Predicting attributes from face images in the wild is a challenging computer vision problem. To automatically describe face attributes from face containing images, traditionally one needs to cascade three technical blocks --- face localization, facial descriptor construction, and attribute classification --- in a pipeline. As a typical classification problem, face attribute prediction has been addressed using deep learning. Current state-of-the-art performance was achieved by using two cascaded Convolutional Neural Networks (CNNs), which were specifically trained to learn face localization and attribute description. In this paper, we experiment with an alternative way of employing the power of deep representations from CNNs. Combining with conventional face localization techniques, we use off-the-shelf architectures trained for face recognition to build facial descriptors. Recognizing that the describable face attributes are diverse, our face descriptors are constructed from different levels of the CNNs for different attributes to best facilitate face attribute prediction. Experiments on two large datasets, LFWA and CelebA, show that our approach is entirely comparable to the state-of-the-art. Our findings not only demonstrate an efficient face attribute prediction approach, but also raise an important question: how to leverage the power of off-the-shelf CNN representations for novel tasks.

Yang Zhong, Josephine Sullivan, Haibo Li

Predicting facial attributes from faces in the wild is very challenging due to pose and lighting variations in the real world. The key to this problem is to build proper feature representations to cope with these unfavourable conditions. Given the success of Convolutional Neural Network (CNN) in image classification, the high-level CNN feature, as an intuitive and reasonable choice, has been widely utilized for this problem. In this paper, however, we consider the mid-level CNN features as an alternative to the high-level ones for attribute prediction. This is based on the observation that face attributes are different: some of them are locally oriented while others are globally defined. Our investigations reveal that the mid-level deep representations outperform the prediction accuracy achieved by the (fine-tuned) high-level abstractions. We empirically demonstrate that the midlevel representations achieve state-of-the-art prediction performance on CelebA and LFWA datasets. Our investigations also show that by utilizing the mid-level representations one can employ a single deep network to achieve both face recognition and attribute prediction.

Yang Zhong, Haibo Li

Different from face verification, face identification is much more demanding. To reach comparable performance, an identifier needs to be roughly N times better than a verifier. To expect a breakthrough in face identification, we need a fresh look at the fundamental building blocks of face recognition. In this paper we focus on the selection of a suitable signal representation and better matching strategy for face identification. We demonstrate how Gabor phase could be leveraged to improve the performance of face identification by using the Block Matching method. Compared to the existing approaches, the proposed method features much lower algorithmic complexity: face images are only filtered by a single-scale Gabor filter pair and the matching is performed between any pairs of face images at hand without involving any training process. Benchmark evaluations show that the proposed approach is totally comparable to and even better than state-of-the-art algorithms, which are typically based on more features extracted from a large set of Gabor faces and/or rely on heavy training processes.

Zhihan Lv, Alaa Halawani, Shengzhong Feng et al.

This is the preprint version of our paper on Personal and Ubiquitous Computing. There is an increasing interest in creating pervasive games based on emerging interaction technologies. In order to develop touch-less, interactive and augmented reality games on vision-based wearable device, a touch-less motion interaction technology is designed and evaluated in this work. Users interact with the augmented reality games with dynamic hands/feet gestures in front of the camera, which triggers the interaction event to interact with the virtual object in the scene. Three primitive augmented reality games with eleven dynamic gestures are developed based on the proposed touch-less interaction technology as proof. At last, a comparing evaluation is proposed to demonstrate the social acceptability and usability of the touch-less approach, running on a hybrid wearable framework or with Google Glass, as well as workload assessment, user's emotions and satisfaction.

Zhihan Lv, Haibo Li

This is the preprint version of our paper on 2015 International Conference on Virtual Rehabilitation (ICVR2015). In this paper, we described the imagination scenarios of a touch-less interaction technology for hemiplegia, which can support either hand or foot interaction with the smartphone or head mounted device (HMD). The computer vision interaction technology is implemented in our previous work, which provides a core support for gesture interaction by accurately detecting and tracking the hand or foot gesture. The patients interact with the application using hand/foot gesture motion in the camera view.

Zhihan Lv, Liangbing Feng, Shengzhong Feng et al.

This is the preprint version of our paper on IEEE Virtual Reality Conference 2015. A touch-less interaction technology on vision based wearable device is designed and evaluated. Users interact with the application with dynamic hands/feet gestures in front of the camera. Several proof-of-concept prototypes with eleven dynamic gestures are developed based on the touch-less interaction. At last, a comparing user study evaluation is proposed to demonstrate the usability of the touch-less approach, as well as the impact on user's emotion, running on a wearable framework or Google Glass.