Guanqun Cao

Shuoyang Wang, Guanqun Cao, Zuofeng Shang

We propose a new approach, called as functional deep neural network (FDNN), for classifying multi-dimensional functional data. Specifically, a deep neural network is trained based on the principle components of the training data which shall be used to predict the class label of a future data function. Unlike the popular functional discriminant analysis approaches which rely on Gaussian assumption, the proposed FDNN approach applies to general non-Gaussian multi-dimensional functional data. Moreover, when the log density ratio possesses a locally connected functional modular structure, we show that FDNN achieves minimax optimality. The superiority of our approach is demonstrated through both simulated and real-world datasets.

Shamsuddeen Hassan Muhammad, Nedjma Ousidhoum, Idris Abdulmumin et al.

People worldwide use language in subtle and complex ways to express emotions. Although emotion recognition--an umbrella term for several NLP tasks--impacts various applications within NLP and beyond, most work in this area has focused on high-resource languages. This has led to significant disparities in research efforts and proposed solutions, particularly for under-resourced languages, which often lack high-quality annotated datasets. In this paper, we present BRIGHTER--a collection of multi-labeled, emotion-annotated datasets in 28 different languages and across several domains. BRIGHTER primarily covers low-resource languages from Africa, Asia, Eastern Europe, and Latin America, with instances labeled by fluent speakers. We highlight the challenges related to the data collection and annotation processes, and then report experimental results for monolingual and crosslingual multi-label emotion identification, as well as emotion intensity recognition. We analyse the variability in performance across languages and text domains, both with and without the use of LLMs, and show that the BRIGHTER datasets represent a meaningful step towards addressing the gap in text-based emotion recognition.

Jingming Xia, Guanqun Cao, Guang Ma et al.

Monocular depth estimation involves predicting depth from a single RGB image and plays a crucial role in applications such as autonomous driving, robotic navigation, 3D reconstruction, etc. Recent advancements in learning-based methods have significantly improved depth estimation performance. Generative models, particularly Stable Diffusion, have shown remarkable potential in recovering fine details and reconstructing missing regions through large-scale training on diverse datasets. However, models like CLIP, which rely on textual embeddings, face limitations in complex outdoor environments where rich context information is needed. These limitations reduce their effectiveness in such challenging scenarios. Here, we propose a novel image-based semantic embedding that extracts contextual information directly from visual features, significantly improving depth prediction in complex environments. Evaluated on the KITTI and Waymo datasets, our method achieves performance comparable to state-of-the-art models while addressing the shortcomings of CLIP embeddings in handling outdoor scenes. By leveraging visual semantics directly, our method demonstrates enhanced robustness and adaptability in depth estimation tasks, showcasing its potential for application to other visual perception tasks.

Shuoyang Wang, Guanqun Cao

The intrinsically infinite-dimensional features of the functional observations over multidimensional domains render the standard classification methods effectively inapplicable. To address this problem, we introduce a novel multiclass functional deep neural network (mfDNN) classifier as an innovative data mining and classification tool. Specifically, we consider sparse deep neural network architecture with rectifier linear unit (ReLU) activation function and minimize the cross-entropy loss in the multiclass classification setup. This neural network architecture allows us to employ modern computational tools in the implementation. The convergence rates of the misclassification risk functions are also derived for both fully observed and discretely observed multidimensional functional data. We demonstrate the performance of mfDNN on simulated data and several benchmark datasets from different application domains.

Guanqun Cao, Shan Luo

Humans usually perceive the world in a multimodal way that vision, touch, sound are utilised to understand surroundings from various dimensions. These senses are combined together to achieve a synergistic effect where the learning is more effectively than using each sense separately. For robotics, vision and touch are two key senses for the dexterous manipulation. Vision usually gives us apparent features like shape, color, and the touch provides local information such as friction, texture, etc. Due to the complementary properties between visual and tactile senses, it is desirable for us to combine vision and touch for a synergistic perception and manipulation. Many researches have been investigated about multimodal perception such as cross-modal learning, 3D reconstruction, multimodal translation with vision and touch. Specifically, we propose a cross-modal sensory data generation framework for the translation between vision and touch, which is able to generate realistic pseudo data. By using this cross-modal translation method, it is desirable for us to make up inaccessible data, helping us to learn the object's properties from different views. Recently, the attention mechanism becomes a popular method either in visual perception or in tactile perception. We propose a spatio-temporal attention model for tactile texture recognition, which takes both spatial features and time dimension into consideration. Our proposed method not only pays attention to the salient features in each spatial feature, but also models the temporal correlation in the through the time. The obvious improvement proves the efficiency of our selective attention mechanism. The spatio-temporal attention method has potential in many applications such as grasping, recognition, and multimodal perception.

Jiaqi Jiang, Guanqun Cao, Daniel Fernandes Gomes et al.

Crack detection is of great significance for monitoring the integrity and well-being of the infrastructure such as bridges and underground pipelines, which are harsh environments for people to access. In recent years, computer vision techniques have been applied in detecting cracks in concrete structures. However, they suffer from variances in light conditions and shadows, lacking robustness and resulting in many false positives. To address the uncertainty in vision, human inspectors actively touch the surface of the structures, guided by vision, which has not been explored in autonomous crack detection. In this paper, we propose a novel approach to detect and reconstruct cracks in concrete structures using vision-guided active tactile perception. Given an RGB-D image of a structure, the rough profile of the crack in the structure surface will first be segmented with a fine-tuned Deep Convolutional Neural Networks, and a set of contact points are generated to guide the collection of tactile images by a camera-based optical tactile sensor. When contacts are made, a pixel-wise mask of the crack can be obtained from the tactile images and therefore the profile of the crack can be refined by aligning the RGB-D image and the tactile images. Extensive experiment results have shown that the proposed method improves the effectiveness and robustness of crack detection and reconstruction significantly, compared to crack detection with vision only, and has the potential to enable robots to help humans with the inspection and repair of the concrete infrastructure.

Guanqun Cao, Jiaqi Jiang, Chen Lu et al.

Tactile sensing is important for robots to perceive the world as it captures the texture and hardness of the object in contact and is robust to illumination and colour variances. However, due to the limited sensing area and the resistance of the fixed surface, current tactile sensors have to tap the tactile sensor on target object many times when assessing a large surface, i.e., pressing, lifting up and shifting to another region. This process is ineffective and time consuming. It is also undesirable to drag such sensors as this often damages the sensitive membrane of the sensor or the object. To address these problems, we propose a cylindrical optical tactile sensor named TouchRoller that can roll around its center axis. It maintains being in contact with the assessed surface throughout the entire motion, which allows for measuring the object continuously and effectively. Extensive experiments show that the TouchRoller sensor can cover a textured surface of 8cm*11cm in a short time of 10s, much more effectively than a flat optical tactile sensor (in 196s). The reconstructed map of the texture from the collected tactile images has a high Structural Similarity Index (SSIM) of 0.31 on average, when compared with the visual texture. In addition, the contacts on the sensor can be localised with a low localisation error, 2.63mm in the center regions and 7.66mm on average. The proposed sensor will enable the fast assessment of large surfaces with high-resolution tactile sensing, and also the effective collection of tactile images.

Shuoyang Wang, Guanqun Cao, Zuofeng Shang

In this work, we propose a deep neural network method to perform nonparametric regression for functional data. The proposed estimators are based on sparsely connected deep neural networks with ReLU activation function. By properly choosing network architecture, our estimator achieves the optimal nonparametric convergence rate in empirical norm. Under certain circumstances such as trigonometric polynomial kernel and a sufficiently large sampling frequency, the convergence rate is even faster than root-$n$ rate. Through Monte Carlo simulation studies we examine the finite-sample performance of the proposed method. Finally, the proposed method is applied to analyze positron emission tomography images of patients with Alzheimer disease obtained from the Alzheimer Disease Neuroimaging Initiative database.

Guanqun Cao, Yi Zhou, Danushka Bollegala et al.

Recently, tactile sensing has attracted great interest in robotics, especially for facilitating exploration of unstructured environments and effective manipulation. A detailed understanding of the surface textures via tactile sensing is essential for many of these tasks. Previous works on texture recognition using camera based tactile sensors have been limited to treating all regions in one tactile image or all samples in one tactile sequence equally, which includes much irrelevant or redundant information. In this paper, we propose a novel Spatio-Temporal Attention Model (STAM) for tactile texture recognition, which is the very first of its kind to our best knowledge. The proposed STAM pays attention to both spatial focus of each single tactile texture and the temporal correlation of a tactile sequence. In the experiments to discriminate 100 different fabric textures, the spatially and temporally selective attention has resulted in a significant improvement of the recognition accuracy, by up to 18.8%, compared to the non-attention based models. Specifically, after introducing noisy data that is collected before the contact happens, our proposed STAM can learn the salient features efficiently and the accuracy can increase by 15.23% on average compared with the CNN based baseline approach. The improved tactile texture perception can be applied to facilitate robot tasks like grasping and manipulation.

Guanqun Cao, Alexandros Iosifidis, Moncef Gabbouj et al.

We study the problem of learning to rank from multiple information sources. Though multi-view learning and learning to rank have been studied extensively leading to a wide range of applications, multi-view learning to rank as a synergy of both topics has received little attention. The aim of the paper is to propose a composite ranking method while keeping a close correlation with the individual rankings simultaneously. We present a generic framework for multi-view subspace learning to rank (MvSL2R), and two novel solutions are introduced under the framework. The first solution captures information of feature mappings from within each view as well as across views using autoencoder-like networks. Novel feature embedding methods are formulated in the optimization of multi-view unsupervised and discriminant autoencoders. Moreover, we introduce an end-to-end solution to learning towards both the joint ranking objective and the individual rankings. The proposed solution enhances the joint ranking with minimum view-specific ranking loss, so that it can achieve the maximum global view agreements in a single optimization process. The proposed method is evaluated on three different ranking problems, i.e. university ranking, multi-view lingual text ranking and image data ranking, providing superior results compared to related methods.

Guanqun Cao, Alexandros Iosifidis, Moncef Gabbouj

Face verification is a problem approached in the literature mainly using nonlinear class-specific subspace learning techniques. While it has been shown that kernel-based Class-Specific Discriminant Analysis is able to provide excellent performance in small- and medium-scale face verification problems, its application in today's large-scale problems is difficult due to its training space and computational requirements. In this paper, generalizing our previous work on kernel-based class-specific discriminant analysis, we show that class-specific subspace learning can be cast as a regression problem. This allows us to derive linear, (reduced) kernel and neural network-based class-specific discriminant analysis methods using efficient batch and/or iterative training schemes, suited for large-scale learning problems. We test the performance of these methods in two datasets describing medium- and large-scale face verification problems.

Guanqun Cao, Alexandros Iosifidis, Ke Chen et al.

In this paper, the problem of multi-view embedding from different visual cues and modalities is considered. We propose a unified solution for subspace learning methods using the Rayleigh quotient, which is extensible for multiple views, supervised learning, and non-linear embeddings. Numerous methods including Canonical Correlation Analysis, Partial Least Sqaure regression and Linear Discriminant Analysis are studied using specific intrinsic and penalty graphs within the same framework. Non-linear extensions based on kernels and (deep) neural networks are derived, achieving better performance than the linear ones. Moreover, a novel Multi-view Modular Discriminant Analysis (MvMDA) is proposed by taking the view difference into consideration. We demonstrate the effectiveness of the proposed multi-view embedding methods on visual object recognition and cross-modal image retrieval, and obtain superior results in both applications compared to related methods.