Faculty of Computing and Informatics

The advancement of Information Technology has undeniably brought substantial changes to the way the world operates today and improved our lives significantly. Ever since learning analytics is introduced, it has been widely used in education to do learner profiling, which is a process of gathering and analyzing enormous amounts of data about a particular student's interaction in online learning activities. In this study, we study and compare several learning analytics methods used by the institutions in improving student success. The methods include Student Success Algorithm, Beacon, Logistic regression, naïve Bayes classification method, and Blackboard Analytics. Besides, we also study on what type of data is extracted by each method and how the data is extracted to predict student success. Then, the advantages, disadvantages and limitations of using these methods are listed in the discussion part. Furthermore, we propose the suitable method out of five and justify the reason for the proposal. Last but not least, based on the justification, we select naïve Bayes classification method as the suitable method to be recommended to other institutions.

Hegemoni merupakan konsep yang tercutus dari pemikiran Barat. Ia bermaksud penguasaan dominasi atau pemimpininan sesebuah negara atau kumpulan terhadap negara atau kumpulan lain. Hegemoni berasal daripada perkataan Inggeris iaitu Hegemony yang pada asalnya dipinjam daripada bahasa Yunani (Greek) iaitu hegemonia 1 , datangnya daripada kata hegemon 2 yang bermaksud ketua atau pemimpin. Hegemon pula datangnya daripada kata hegeisthai yang juga bermaksud pemimpin.

We introduce a new image geometric transformation, named tearable image warping, for content-aware image retargeting and recomposition. In tearable image warping, an object is allowed to partially detached from the background during warping, which allows the background to warp more freely without distorting the object. The part of the object that is still attached to the background ensures that spatial semantics between the object and its environment is preserved. Compared to traditional non-homogeneous image warping, tearable warping produces retargeted results with less severe distortions, especially in cases of extreme retargeting. Compared to scene carving, tearable warping can better preserve the global context and achieve better scene consistency by preserving the semantic connectedness between an object and its environment. In addition, tearable warping is also able to alter the objectbackground relationship within the image, which makes it quite suitable for aesthetics-based image recomposition. We also show that tearable image warping is a unified approach of traditional non-homogeneous image warping and the cut-and-paste techniques.

Aesthetics is a subjective concept that is likely to be perceived differently among people of different ages, genders, and cultural backgrounds. While techniques that directly compute this concept in images has seen increasing attention by the multimedia and machine-learning community, there are very few attempts at encoding the influences from the photographer's viewpoint. This work demonstrates how the aesthetic quality of photos can be better learned by accounting for the demographic background of a photographer. A new AVA-PD (Photographer Demographic) dataset is created to supplement the AVA dataset by providing photographers' age, gender and location attributes. Two deep convolutional neural network (CNN) architectures are proposed to utilize demographic information for aesthetic prediction of photos; both are shown to yield better prediction capabilities compared to most existing approaches. By leveraging on AVA-PD meta-data, we also present some additional machine-learnable tasks such as identifying the photographer and predicting photography styles from a person's gallery of photos.

Every day 1.8+ billion images are being uploaded to Facebook, Instagram, Flickr, Snapchat, and WhatsApp [6]. The exponential growth of visual media has made quality assessment become increasingly important for various applications, from image acquisition, synthesis, restoration, and enhancement, to image search and retrieval, storage, and recognition. There have been two related but different classes of visual quality assessment techniques: image quality assessment (IQA) and image aesthetics assessment (IAA). As perceptual assessment tasks, subjective IQA and IAA share some common underlying factors that affect user judgments. Moreover, they are similar in methodology (especially NR-IQA in-the-wild and IAA). However, the emphasis for each is different: IQA focuses on low-level defects e.g. processing artefacts, noise, and blur, while IAA puts more emphasis on abstract and higher-level concepts that capture the subjective aesthetics experience, e.g. established photographic rules enc...

Due to the high capability of learning robust features, convolutional neural networks (CNN) are becoming a mainstay solution for many computer vision problems, including aesthetic quality assessment (AQA). However, there remains the issue that learning with CNN requires time-consuming and expensive data annotations especially for a task like AQA. In this paper, we present a novel approach to AQA that incorporates self-supervised learning (SSL) by learning how to inpaint images according to photographic rules such as rules-of-thirds and visual saliency. We conduct extensive quantitative experiments on a variety of pretext tasks and also different ways of masking patches for inpainting, reporting fairer distribution-based metrics. We also show the suitability and practicality of the inpainting task which yielded comparably good benchmark results with much lighter model complexity.

User-centric network (UCN), which organizes a dynamic transmission point group (TPG) for each user, is regarded as a promising candidate to meet the exponential growth of mobile data traffic for 5G system. However, the severe interference under dense TP deployment in UCN from co-channel neighbor cell worsens the user performance. In this paper, to combat the fluctuation of user rate, a user-centric power control strategy is proposed, where TPs will take power control coefficient β to effectively mitigate the strong interference for each user within TPG of radius coefficient µ. Based on the strategy, semi-closed expressions of network downlink performance metric are first derived, including coverage probability and average achievable rate to the typical user, and average spectral efficiency of TP with the consideration of the impact of TPG overlapping on the signal link. The TPs and the users are modeled as independent 2-D Poisson point processes. The theoretical analysis confirms that the optimization of β and µ, which determine the area and intensity for power control, respectively, can realize the tradeoff between interference mitigation and resource utilization. Numerical results demonstrate significant performance gains of the user-centric power control strategy in coverage probability, average achievable user rate, and TP spectral efficiency, which can be improved at most by 30%, 15%, and 42%, respectively. In addition, the analysis gives the optimal values of β and µ according to the distance between TP and user. INDEX TERMS User-centric network, power control, interference mitigation, Poisson point processes.

This paper describes the implementation of ODECAL, a realtime physics powered, rag doll simulation system with animation blending ability. Unlike the traditional key frame animation rag doll system, our animating 3D character can blend into physics state to perform rag doll simulation and vice verse seamlessly. It can even be applied to any form of creatures with bone based articulation. ODECAL can be used for the development of computer games as well as virtual reality applications to enhance the realism and sense of immersion. ODECAL was build with flexible design in mind to allow it to integrate easily with any 3D rendering toolkits and game engines. It was written entirely in C++ using object oriented design to provide programmer a "developer friendly" modularize architecture for large scale software project. We also utilized open source technologies for low cost development as well as its strong cross platform feature.

A photograph that has visually dominant subjects in general induces stronger aesthetic interest. Inspired by this, we have developed a new approach to enhance image aesthetics through saliency retargeting. Our method alters low-level image features of the objects in the photograph such that their computed saliency measurements in the modified image become consistent with the intended order of their visual importance. The goal of our approach is to produce an image that can redirect the viewers' attention to the most important objects in the image, and thus making these objects the main subjects. Since many modified images can satisfy the same specified order of visual importance, we trained an aesthetics score prediction model to pick the one with the best aesthetics. Results from our user experiments support the effectiveness of our approach.

We present a semi-automatic photographic recomposition approach that employs a semantics-preserving warp of the input image to enhance the visual dominance of the main subjects. Our method uses the tearable image warping method to shift the subjects against the background (and vice versa), so that their visual dominance is improved, and yet preserve the desired spatial semantics between the subjects and the background. The recomposition is guided by a measure of the resulting visual dominance of the main subjects. Our user experiment shows the effectiveness of the approach.

We present a saliency-enhanced method for the classification of professional photos and snapshots. First, we extract the salient regions from an image by utilizing a visual saliency model. We assume that the salient regions contain the photo subject. Then, in addition to a set of discriminative global image features, we extract a set of salient features that characterize the subject and depict the subject-background relationship. Our high-level perceptual approach produces a promising 5-fold cross-validation (5-CV) classification accuracy of 78.8%, significantly higher than existing approaches that concentrate mainly on global features.

The Joint Workshop on Aesthetic and Technical Quality Assessment of Multimedia and Media Analytics for Societal Trends (ATQAM/ MAST) aims to bring together researchers and professionals working in fields ranging from computer vision, multimedia computing, multimodal signal processing to psychology and social sciences. It is divided into two tracks: ATQAM and MAST. ATQAM track: Visual quality assessment techniques can be divided into image and video technical quality assessment (IQA and VQA, or broadly TQA) and aesthetics quality assessment (AQA). While TQA is a long-standing field, having its roots in media compression, AQA is relatively young. Both have received increased attention with developments in deep learning. The topics have mostly been studied separately, even though they deal with similar aspects of the underlying subjective experience of media. The aim is to bring together individuals in the two fields of TQA and AQA for sharing of ideas and discussions on current trends, developments, issues, and future directions. MAST track: The research area of media content analytics has been traditionally used to refer to applications involving inference of higher level semantics from multimedia content. However, multimedia is typically created for human consumption, and we believe it is necessary to adopt a human-centered approach to this analysis, which would not only enable a better understanding of how viewers Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the owner/author(s).

We introduce a new image geometric transformation, named tearable image warping, for content-aware image retargeting and recomposition. In tearable image warping, an object is allowed to partially detached from the background during warping, which allows the background to warp more freely without distorting the object. The part of the object that is still attached to the background ensures that spatial semantics between the object and its environment is preserved. Compared to traditional non-homogeneous image warping, tearable warping produces retargeted results with less severe distortions, especially in cases of extreme retargeting. Compared to scene carving, tearable warping can better preserve the global context and achieve better scene consistency by preserving the semantic connectedness between an object and its environment. In addition, tearable warping is also able to alter the objectbackground relationship within the image, which makes it quite suitable for aesthetics-based...

This paper reviews the first NTIRE challenge on perceptual image enhancement with the focus on proposed solutions and results. The participating teams were solving a real-world photo enhancement problem, where the goal was to map low-quality photos from the iPhone 3GS device to the same photos captured with Canon 70D DSLR camera. The considered problem embraced a number of computer vision subtasks, such as image denoising, image resolution and sharpness enhancement, image color/contrast/exposure adjustment, etc. The target metric used in this challenge combined fidelity scores (PSNR and SSIM) with solutions' perceptual results measured in a user study. From above 200 registered participants, 13 teams submitted solutions for the final test phase of the challenge. The proposed solutions significantly improved baseline results, defining the state-of-the-art for practical image enhancement.

Facial expressions vary from the visible to the subtle. In recent years, the analysis of micro-expressions-a natural occurrence resulting from the suppression of one's true emotions, has drawn the attention of researchers with a broad range of potential applications. However, spotting microexpressions in long videos becomes increasingly challenging when intertwined with normal or macro-expressions. In this paper, we propose a shallow optical flow three-stream CNN (SOFTNet) model to predict a score that captures the likelihood of a frame being in an expression interval. By fashioning the spotting task as a regression problem, we introduce pseudo-labeling to facilitate the learning process. We demonstrate the efficacy and efficiency of the proposed approach on the recent MEGC 2020 benchmark, where state-of-the-art performance is achieved on CAS(ME) 2 with equally promising results on SAMM Long Videos.

The recent surge in deep learning methods across multiple modalities has resulted in an increased interest in image captioning. Most advances in image captioning are still focused on the generation of factual-centric captions, which mainly describe the contents of an image. However, generating captions to provide a meaningful and opinionated critique of photographs is less studied. This paper presents a framework for leveraging aesthetic features encoded from an image aesthetic scorer, to synthesize human-like textual critique via a sequence decoder. Experiments on a large-scale dataset show that the proposed method is capable of producing promising results on relevant metrics relating to semantic diversity and synonymity, with qualitative observations demonstrating likewise. We also suggest the use of Word Mover's Distance as a semantically intuitive and informative metric for this task.

Monocular omnidirectional depth estimation is receiv-ing considerable research attention due to its broad applications for sensing 360 ◦ surroundings. Existing approaches in this field suffer from limitations in recovering small object details and data lost during the ground-truth depth map acquisition. In this paper, a novel monocular omnidirectional depth estimation model, namely HiMODE is proposed based on a hybrid CNN+Transformer (encoder-decoder) architecture whose modules are efficiently designed to mitigate distortion and computational cost, without performance degradation. Firstly, we design a feature pyramid network based on the HNet block to extract high-resolution features near the edges. The performance is further improved, benefiting from a self and cross attention layer and spatial/temporal patches in the Transformer encoder and decoder, respectively. Besides, a spatial residual block is employed to reduce the number of parameters. By jointly passing the deep features ext...