Demosaicking is a critical process in the digital imaging pipeline, tasked with reconstructing full-color images from sampled data captured by R/G/B color sensors. The challenge arises from two-thirds of the pixel data being missing, which complicates the task of accurate reconstruction. Recent deep learning-based solutions have yielded considerable advancements in demosaicking performance. However, they are computationally intensive and rely on large model architectures, rendering them unsuitable for edge-devices deployment. This work introduces a novel demosaicking method to address these challenges based on green learning (GL), named green image demosaicking (GID). GID offers model transparency while significantly reducing the model size and computational complexity against deep learning methods. Notably, GID does not utilize neural networks. Instead, it is built upon unsupervised representation learning and supervised feature dimension reduction. GID effectively addresses the challenges of big data in vision applications and enhances predictive accuracy during decision-making. GID is engineered for rapid execution with parallel training, making it well-suited for real-time vision tasks on resource-constrained devices.

The discriminant ability of features plays a central role in classification tasks. Deep learning (DL) utilizes back-propagation to yield discriminant features with an end-to-end depth structure, which lacks interpretability. A new learning paradigm, Green Learning (GL), has been proposed to address the weaknesses of DL, including high carbon footprints, large model sizes, and mathematical opaqueness. Following this idea, a statistics-based feature generation (SFG) method is proposed to boost system performance further. SFG consists of two modules: 1) feature subset selection and 2) discriminant feature generation via linear combination. In the first module, SFG traces the splitting features along individual tree paths within auxiliary XGBoost classifiers, which form the desired feature subsets for each binary label subspace. In the second module, SFG determines the weights of features in each subspace by formulating a least-square normal equation supervised by its corresponding binary sub-labels. SFG enables the adaptive assessment of feature importance at global and various local scales. Besides, it reduces the computational requirement by working in low-dimensional feature sub-spaces. Extensive experiments are conducted on classical image classification tasks to demonstrate the effectiveness and efficiency of SFG.

Knowledge graph entity typing (KGET) aims to predict the missing entity types in knowledge graphs (KG). The relationship between entities and their corresponding types is often expressed using a single relation, hasType. However, hasType has a limited capability for modeling diverse entity-type relationships in the embedding space. In this paper, we first introduce multiple auxiliary relations to model the complex entity-type relationship. We propose an efficient and robust algorithm to group similar entity types together and assign a unique auxiliary relation to each group. Then, with the auxiliary relations, we propose an Asynchronous representation learning framework for KGET, named AsyncET, where entity and type embeddings are updated alternatively. Consequently, the quality of entity embeddings is gradually improved during training by infusing type information. In addition, entity types with different granularities and semantics can be properly modeled in the embedding space. Experimental results show that AsyncET can substantially improve the performance of embedding-based methods on the KGET task and has a significant advantage over state-of-the-art neural network-based methods in terms of model sizes and inference time.

AI algorithms at the edge demand smaller model sizes and lower computational complexity. To achieve these objectives, we adopt a green learning (GL) paradigm rather than the deep learning paradigm. GL has three modules: 1) unsupervised representation learning, 2) supervised feature learning, and 3) supervised decision learning. We focus on the second module in this work. In particular, we derive new discriminant features from proper linear combinations of input features, denoted by x, obtained in the first module. They are called complementary and raw features, respectively. Along this line, we present a novel supervised learning method to generate highly discriminant complementary features based on the least-squares normal transform (LNT). LNT consists of two steps. First, we convert a C-class classification problem to a binary classification problem. The two classes are assigned with 0 and 1, respectively. Next, we formulate a least-squares regression problem from the N-dimensional (N-D) feature space to the 1-D output space, and solve the least-squares normal equation to obtain one N-D normal vector, denoted by a1. Since one normal vector is yielded by one binary split, we can obtain M normal vectors with M splits. Then, Ax is called an LNT of x, where transform matrix A$\in R^{M\times N}$ by stacking $\mathrm{a}_{J}^{T}$, j=1,, M, and the LNT, Ax, can generate M new features. The newly generated complementary features are shown to be more discriminant than the raw features. Experiments show that the classification performance can be improved by these new features.

High Efficiency Video Coding (HEVC) achieves significant coding performance over H.264. However, the performance gain is achieved at the cost of substantially higher encoding complexity, in which the coding tree unit (CTU) partition is one of the most time-consuming parts due to the rate-distortion optimization-based ergodic search of all possible quad-tree partitions. To address this problem, this paper proposes a texture-classification accelerated convolutional neural network (CNN)-based fast intra CU partition scheme to reduce the encoding complexity for intra-coding in HEVC, by taking into consideration of the heterogeneous texture characteristics into the CNN-based classification. First, a threshold-based texture classification model is developed to identify the heterogeneous and homogeneous CTUs, through jointly consideration of the CU depth, quantization parameter and texture complexity. Second, three different CNN structures are designed and trained to predict the CU partition mode for each CU layer in the heterogeneous CTUs. Finally, extensive experimental results show that the proposed scheme can reduce intra-mode encoding time by 62.13% with negligible BD-rate loss of 2.01%, consistently outperforming two state-of-the-art CNN-based schemes in terms of both coding performance and complexity reduction.

Evaluation of coding efficiency is traditionally modeled as a continuous rate-distortion (R-D) function, where the peak signal-to-noise ratio (PSNR) is adopted as the quality measure. Although the PSNR-versus-bitrate curve offers some useful tradeoff information between video quality and coding bit-rates, it does not take human perceptual experience into account. In this work, by following the recent image/video quality assessment framework based on the just-noticeable-difference (JND) notion, we conduct a subjective test for HEVC (High Efficiency Video Codec) video to measure the QP value that lies in the boundary of perceptually lossless and lossy coded bit streams for each human subject. This is also known as the first JND point. It is observed that the statistics of the first JND points of 30 subjects follows the normal distribution for a great majority of test sequences. Finally, a machine-learning approach is proposed to predict the mean of the group-based JND distribution based on extracted video features. It is shown by experimental results that the mean JND point can be predicted accurately.

Identifying interpretable discriminative high-order feature interactions given limited training data in high dimensions is challenging in both machine learning and data mining. In this paper, we propose a factorization based sparse learning framework termed FHIM for identifying high-order feature interactions in linear and logistic regression models, and study several optimization methods for solving them. Unlike previous sparse learning methods, our model FHIM recovers both the main effects and the interaction terms accurately without imposing tree-structured hierarchical constraints. Furthermore, we show that FHIM has oracle properties when extended to generalized linear regression models with pairwise interactions. Experiments on simulated data show that FHIM outperforms the state-of-the-art sparse lear-ning techniques. Further experiments on our experimentally generated data from patient blood samples using a novel SOMAmer (Slow Off-rate Modified Aptamer) technology show that, FHIM performs blood-based cancer diagnosis and bio-marker discovery for Renal Cell Carcinoma much better than other competing methods, and it identifies interpretable block-wise high-order gene interactions predictive of cancer stages of samples. A literature survey shows that the interactions identified by FHIM play important roles in cancer development.

Summary form only given. In order to limit error propagation, we divide the topological data of the entire mesh into several segments. Each segment is identified by its synchronization word and header. Due to the use of the arithmetic coder, data of a whole segment would often become useless in the presence of even a single bit error. Furthermore, several adjacent segments may be corrupted simultaneously at high bit error rates (BER). As a result, a lot of data would be required to be retransmitted in the presence of errors. Retransmitted data may also in turn get corrupted in high BER conditions. This would result in a considerable loss of coding efficiency and increased delay. We propose the use of reversible variable length codes (RVLC) to solve this problem. RVLC not only prevents error propagation in one segment but also efficiently detects the distorted portion of the bitstream due to their capability of two-way decoding. This would allow the recovery of a large portion of data from a corrupted segment. The amount of retransmitted data can thus be drastically reduced. RVLC can be matched to various sources with different probability distributions by adjusting their suffix length, and have been found suitable for image and video coding. However, the application of RVLC to robust 3D mesh coding has not yet been studied. Our study of the suitability of RVLC for the topological data is presented in this research. Experiments have been carried to prove the efficiency of the proposed robust 3D graphic coding algorithm. To design an efficient pre-defined code table, a large set of 300 MPEG-4 selected 3D models have been used in our experiments. The use of predefined code tables would result in a significantly reduced computational complexity.