This tutorial paper presents a didactic treatment of the emerging topic of signal processing on higher-order networks. Drawing analogies from discrete and graph signal processing, we introduce the building blocks for processing data on simplicial complexes and hypergraphs, two common abstractions of higher-order networks that can incorporate polyadic relationships.We provide basic introductions to simplicial complexes and hypergraphs, making special emphasis on the concepts needed for processing signals on them. Leveraging these concepts, we discuss Fourier analysis, signal denoising, signal interpolation, node embeddings, and non-linear processing through neural networks in these two representations of polyadic relational structures. In the context of simplicial complexes, we specifically focus on signal processing using the Hodge Laplacian matrix, a multi-relational operator that leverages the special structure of simplicial complexes and generalizes desirable properties of the Laplacian matrix in graph signal processing. For hypergraphs, we present both matrix and tensor representations, and discuss the trade-offs in adopting one or the other. We also highlight limitations and potential research avenues, both to inform practitioners and to motivate the contribution of new researchers to the area.

Scenario-based question answering (SQA) has attracted an increasing research interest. Compared with the well-studied machine reading comprehension (MRC), SQA is a more challenging task: a scenario may contain not only a textual passage to read but also structured data like tables, i.e., tabular scenario based question answering (TSQA). AI applications of TSQA such as answering multiple-choice questions in high-school exams require synthesizing data in multiple cells and combining tables with texts and domain knowledge to infer answers. To support the study of this task, we construct GeoTSQA. This dataset contains 1k real questions contextualized by tabular scenarios in the geography domain. To solve the task, we extend state-of-the-art MRC methods with TTGen, a novel table-to-text generator. It generates sentences from variously synthesized tabular data and feeds the downstream MRC method with the most useful sentences. Its sentence ranking model fuses the information in the scenario, question, and domain knowledge. Our approach outperforms a variety of strong baseline methods on GeoTSQA.

This survey reviews explainability methods for vision-based self-driving systems. The concept of explainability has several facets and the need for explainability is strong in driving, a safety-critical application. Gathering contributions from several research fields, namely computer vision, deep learning, autonomous driving, explainable AI (X-AI), this survey tackles several points. First, it discusses definitions, context, and motivation for gaining more interpretability and explainability from self-driving systems. Second, major recent state-of-the-art approaches to develop self-driving systems are quickly presented. Third, methods providing explanations to a black-box self-driving system in a post-hoc fashion are comprehensively organized and detailed. Fourth, approaches from the literature that aim at building more interpretable self-driving systems by design are presented and discussed in detail. Finally, remaining open-challenges and potential future research directions are identified and examined.

In highway scenarios, an alert human driver will typically anticipate early cut-in/cut-out maneuvers of surrounding vehicles using visual cues mainly. Autonomous vehicles must anticipate these situations at an early stage too, to increase their safety and efficiency. In this work, lane-change recognition and prediction tasks are posed as video action recognition problems. Up to four different two-stream-based approaches, that have been successfully applied to address human action recognition, are adapted here by stacking visual cues from forward-looking video cameras to recognize and anticipate lane-changes of target vehicles. We study the influence of context and observation horizons on performance, and different prediction horizons are analyzed. The different models are trained and evaluated using the PREVENTION dataset. The obtained results clearly demonstrate the potential of these methodologies to serve as robust predictors of future lane-changes of surrounding vehicles proving an accuracy higher than 90% in time horizons of between 1-2 seconds.

Training Generative Adversarial Networks (GAN) on high-fidelity images usually requires large-scale GPU-clusters and a vast number of training images. In this paper, we study the few-shot image synthesis task for GAN with minimum computing cost. We propose a lightweight GAN structure that gains superior quality on 1024 1024 resolution. Notably, the model converges from scratch with just a few hours of training on a single RTX-2080 GPU, and has a consistent performance, even with less than 100 training samples. Two technique designs constitute our work, a skip-layer channel-wise excitation module and a self-supervised discriminator trained as a feature-encoder. The fascinating ability to synthesize images using the state-of-the-art (SOTA) Generative Adversarial Networks (GANs) (Goodfellow et al., 2014) display a great potential of GANs for many intriguing real-life applications, such as image translation, photo editing, and artistic creation. However, expensive computing cost and the vast amount of required training data limit these SOTAs in real applications with only small image sets and low computing budgets. In real-life scenarios, the available samples to train a GAN can be minimal, such as the medical images of a rare disease, a particular celebrity's portrait set, and a specific artist's artworks. Transferlearning with a pre-trained model (Mo et al., 2020; Wang et al., 2020) is one solution for the lack of training images. Nevertheless, there is no guarantee to find a compatible pre-training dataset.

Video sentiment analysis as a decision-making process is inherently complex, involving the fusion of decisions from multiple modalities and the so-caused cognitive biases. Inspired by recent advances in quantum cognition, we show that the sentiment judgment from one modality could be incompatible with the judgment from another, i.e., the order matters and they cannot be jointly measured to produce a final decision. Thus the cognitive process exhibits "quantum-like" biases that cannot be captured by classical probability theories. Accordingly, we propose a fundamentally new, quantum cognitively motivated fusion strategy for predicting sentiment judgments. In particular, we formulate utterances as quantum superposition states of positive and negative sentiment judgments, and uni-modal classifiers as mutually incompatible observables, on a complex-valued Hilbert space with positive-operator valued measures. Experiments on two benchmarking datasets illustrate that our model significantly outperforms various existing decision level and a range of state-of-the-art content-level fusion approaches. The results also show that the concept of incompatibility allows effective handling of all combination patterns, including those extreme cases that are wrongly predicted by all uni-modal classifiers.

We present observations of a region of the Galactic plane taken during the Early Science Program of the Australian Square Kilometre Array Pathfinder (ASKAP). In this context, we observed the SCORPIO field at 912 MHz with an uncompleted array consisting of 15 commissioned antennas. The resulting map covers a square region of ~40 deg^2, centred on (l, b)=(343.5{\deg}, 0.75{\deg}), with a synthesized beam of 24"x21" and a background rms noise of 150-200 {\mu}Jy/beam, increasing to 500-600 {\mu}Jy/beam close to the Galactic plane. A total of 3963 radio sources were detected and characterized in the field using the CAESAR source finder. We obtained differential source counts in agreement with previously published data after correction for source extraction and characterization uncertainties, estimated from simulated data. The ASKAP positional and flux density scale accuracy were also investigated through comparison with previous surveys (MGPS, NVSS) and additional observations of the SCORPIO field, carried out with ATCA at 2.1 GHz and 10" spatial resolution. These allowed us to obtain a measurement of the spectral index for a subset of the catalogued sources and an estimated fraction of (at least) 8% of resolved sources in the reported catalogue. We cross-matched our catalogued sources with different astronomical databases to search for possible counterparts, finding ~150 associations to known Galactic objects. Finally, we explored a multiparametric approach for classifying previously unreported Galactic sources based on their radio-infrared colors.

In this work we present an explainable system for emotion attribution and recommendation (called DEGARI) relying on a recently introduced commonsense reasoning framework (the TCL logic) which is based on a human-like procedure for the automatic generation of novel concepts in a Description Logics knowledge base. Starting from an ontological formalization of emotions (known as ArsEmotica), the system exploits the logic TCL to automatically generate novel commonsense semantic representations of compound emotions (e.g. Love as derived from the combination of Joy and Trust according to the ArsEmotica model). The generated emotions correspond to prototypes, i.e. commonsense representations of given concepts, and have been used to reclassify emotion-related contents in a variety of artistic domains, ranging from art datasets to the editorial content available in RaiPlay, the online multimedia platform of RAI Radiotelevisione Italiana (the Italian public broadcasting company). We have tested our system (1) by reclassifying the available contents in the tested dataset with respect to the new generated compound emotions (2) with an evaluation, in the form of a controlled user study experiment, of the feasibility of using the obtained reclassifications as recommended emotional content. The obtained results are encouraging and pave the way to many possible further improvements and research directions.

We introduce the "Incremental Implicitly-Refined Classi-fication (IIRC)" setup, an extension to the class incremental learning setup where the incoming batches of classes have two granularity levels. i.e., each sample could have a high-level (coarse) label like "bear" and a low-level (fine) label like "polar bear". Only one label is provided at a time, and the model has to figure out the other label if it has already learnfed it. This setup is more aligned with real-life scenarios, where a learner usually interacts with the same family of entities multiple times, discovers more granularity about them, while still trying not to forget previous knowledge. Moreover, this setup enables evaluating models for some important lifelong learning challenges that cannot be easily addressed under the existing setups. These challenges can be motivated by the example "if a model was trained on the class bear in one task and on polar bear in another task, will it forget the concept of bear, will it rightfully infer that a polar bear is still a bear? and will it wrongfully associate the label of polar bear to other breeds of bear?". We develop a standardized benchmark that enables evaluating models on the IIRC setup. We evaluate several state-of-the-art lifelong learning algorithms and highlight their strengths and limitations. For example, distillation-based methods perform relatively well but are prone to incorrectly predicting too many labels per image. We hope that the proposed setup, along with the benchmark, would provide a meaningful problem setting to the practitioners

The remarkable ability of deep neural networks to perfectly fit training data when optimized by gradient-based algorithms is yet to be fully explained theoretically. Explanations by recent theoretical works rely on the networks to be wider by orders of magnitude than the ones used in practice. In this work, we take a step towards closing the gap between theory and practice. We show that a randomly initialized deep neural network with ReLU activation converges to a global minimum in a logarithmic number of gradient-descent iterations, under a considerably milder condition on its width. Our analysis is based on a novel technique of training a network with fixed activation patterns. We study the unique properties of the technique that allow an improved convergence, and can be transformed at any time to an equivalent ReLU network of a reasonable size. We derive a tight finite-width Neural Tangent Kernel (NTK) equivalence, suggesting that neural networks trained with our technique generalize well at least as good as its NTK, and it can be used to study generalization as well.