Abstract

Stylized view generation of scenes captured casually using a camera has received much attention recently. The geometry and appearance of the scene are typically captured as neural point sets or neural radiance fields in the previous work. An image stylization method is used to stylize the captured appearance by training its network jointly or iteratively with the structure capture network. The state-of-the-art SNeRF method trains the NeRF and stylization network in an alternating manner. These methods have high training time and require joint optimization. In this work, we present StyleTRF, a compact, quick-to-optimize strategy for stylized view generation using TensoRF. The appearance part is fine-tuned using sparse stylized priors of a few views rendered using the TensoRF representation for a few iterations. Our method thus effectively decouples style-adaption from view capture and is much faster than the previous methods. We show state-of-the-art results on several scenes used for this purpose.

Abstract

Keyword Spotting (KWS) detects a set of pre-defined spoken keywords. Building a KWS system for an arbitrary set requires massive training datasets. We propose to use the text transcripts from an Automatic Speech Recognition (ASR) system alongside triplets for KWS training. The intermediate representation from the ASR system trained on a speech corpus is used as acoustic word embeddings for keywords. Triplet loss is added to the Connectionist Temporal Classification (CTC) loss in the ASR while training. This method achieves an Average Precision (AP) of 0.843 over 344 words unseen by the model trained on the TIMIT dataset. In contrast, the Multi-View recurrent method that learns jointly on the text and acoustic embeddings achieves only 0.218 for out-of-vocabulary words. This method is also applied to low-resource languages such as Tamil by converting Tamil characters to English using transliteration. This is a very challenging novel task for which we provide a dataset of transcripts for the keywords. Despite our model not generalizing well, we achieve a benchmark AP of 0.321 on over 38 words unseen by the model on the MSWC Tamil keyword set. The model also produces an accuracy of 96.2% for classification tasks on the Google Speech Commands dataset. Index Terms: speech recognition, keyword spotting, lowresource languages

Abstract

Existing Math Word Problem (MWP) solvers have achieved high accuracy on benchmark datasets. However, prior works have shown that such solvers do not generalize well and rely on superficial cues to achieve high performance. In this paper, we first conduct experiments to showcase that this behaviour is mainly associated with the limited size and diversity present in existing MWP datasets. Next, we propose several data augmentation techniques broadly categorized into Substitution and Paraphrasing based methods. By deploying these methods we increase the size of existing datasets by five folds. Extensive experiments on two benchmark datasets across three state-of-the-art MWP solvers show that proposed methods increase the generalization and robustness of existing solvers. On average, proposed methods significantly increase the state-of-the-art results by over five percentage points on benchmark datasets. Further, the solvers trained on the augmented dataset perform comparatively better on the challenge test set. We also show the effectiveness of proposed techniques through ablation studies and verify the quality of augmented samples through human evaluation.

Abstract

Periodic pattern mining is an emerging technique for knowledge discovery. Most previous approaches have aimed to find only those patterns that exhibit full (or perfect) periodic behavior in databases. Consequently, the existing approaches miss interesting patterns that exhibit partial periodic behavior in a database. With this motivation, this paper proposes a novel model for finding partial periodic patterns that may exist in temporal databases. An efficient pattern-growth algorithm, called Partial Periodic Pattern-growth (3P-growth), is also presented, which can effectively find all desired patterns within a database. Substantial experiments on both real-world and synthetic databases showed that our algorithm is not only efficient in terms of memory and runtime, but is also highly scalable. Finally, the effectiveness of our patterns is demonstrated using two case studies. In the first case study, our model was employed to identify the highly polluted areas in Japan. In the second case study, our model was employed to identify the road segments on which people regularly face traffic congestion.

Abstract

In an Intelligent Precision Agriculture (IPA), several Internet of Things (IoT) smart devices and drones can be deployed to monitor an agricultural environment. The drones can be further utilized to collect the data from smart devices and send to the Ground Station Server (GSS). However, insecure communication among the smart devices, drones and the GSS make the IoT agriculture environment vulnerable to various potential attacks. For this goal, a new authentication and key management scheme for IoT-enabled IPA, called AKMS-AgriIoT, has been put forward with the private blockchain-based solution. The blocks formed with the encrypted transactions and their respective signatures by the GSS are mined by the cloud servers to verify and add the blocks in the private blockchain center. A detailed security analysis and comparative study reveal that the proposed AKMS-AgriIoT supports better security, and provides more functionality features, less communication costs and comparable computation costs as compared to other relevant schemes. In addition, the blockchain-based implementation on the proposed AKMS-AgriIoT has been also carried out.

Abstract

—Effective design of autopilots for fixed-wing unmanned aerial vehicles (UAVs) is still a great challenge, due to unmodeled effects and uncertainties that these vehicles exhibit during flight. Unmodeled effects and uncertainties comprise longitudinal/lateral cross-couplings, as well as poor knowledge of equilibrium points (trimming points) of the UAV dynamics. The main contribution of this article is a new adaptive autopilot design, based on uncertain Euler–Lagrange dynamics of the UAV and where the control can explicitly take into account under-actuation in the dynamics, reduced structural knowledge of cross-couplings and trimming points. This system uncertainty is handled via appropriately designed adaptive laws: stability of the controlled UAV is analyzed. Hardware-in-the-loop tests, comparisons with an Ardupilot autopilot and with a robustified autopilot validate the effectiveness of the control design, even in the presence of strong saturation of the UAV actuators.

Abstract

—Connected vehicle means providing different services, such as advanced driver-assistance systems (ADAS) from vehicles connected to the network. Vehicular ad-hoc networks (VANETs) can support vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communications to realize connected vehicle. In VANETs, secure communication must be ensured, as otherwise it can lead to traffic accidents and human injuries. Recently, many studies on V2I authentication have been conducted to guarantee the security of V2I communications. However, recent V2I authentication protocols do not consider the handover situation, and it causes unnecessary computations. As vehicles have limited computing resources, unnecessary computation can lead to overload to the vehicles. In recent years, blockchain-based VANET is an active field of research because it can provide decentralization, data integrity and transparency. Using the strength of the blockchain technology, we design a blockchain-based handover authentication protocol for VANETs. In the proposed protocol, vehicles only perform lightweight computations in handover situations for efficiency of the network. We also conduct the formal analysis such as Burrows–Abadi–Needham (BAN) logic, Real-Or-Random (ROR) oracle model, and Automated Validation of Internet Security Protocols and Applications (AVISPA) simulation to the proposed protocol. We simulate the proposed protocol using network simulator 3 (NS-3) to verify that the proposed protocol is practical. Finally, we compare the computational cost and security features of the proposed protocol with existing protocols to show that the proposed protocol is more secure and efficient.

Abstract

The Securities and Exchange Board of India is the regulatory body for securities and commodity market in India. A growing number of SEBI documents ranging from government regulations to legal case files are now available in the digital form. Advances in natural language processing and machine learning provide opportunities for extracting semantic insights from these documents. We present here a system that performs semantic processing of SEBI documents using state-of-the-art language models to produce enriched regulations containing timelines of amendments and cross references to legal case files.

Abstract

How the brain captures the meaning of linguistic stimuli across multiple views is still a critical open question in neuroscience. Consider three different views of the concept apartment: (1) picture (WP) presented with the target word label, (2) sentence (S) using the target word, and (3) word cloud (WC) containing the target word along with other semantically related words. Unlike previous efforts, which focus only on single view analysis, in this paper, we study the effectiveness of brain decoding in a zero-shot cross-view learning setup. Further, we propose brain decoding in the novel context of cross-view-translation tasks like image captioning (IC), image tagging (IT), keyword extraction (KE), and sentence formation (SF). Using extensive experiments, we demonstrate that cross-view zero-shot brain decoding is practical leading to ∼0.68 average pairwise accuracy across view pairs. Also, the decoded representations are sufficiently detailed to enable high accuracy for cross-view-translation tasks with following pairwise accuracy: IC (78.0), IT (83.0), KE (83.7) and SF (74.5).

Abstract

Several popular Transformer based language models have been found to be successful for text-driven brain encoding. However, existing literature leverages only pretrained text Transformer models and has not explored the efficacy of task-specific learned Transformer representations. In this work, we explore transfer learning from representations learned for ten popular natural language processing tasks (two syntactic and eight semantic) for predicting brain responses from two diverse datasets: Pereira (subjects reading sentences from paragraphs) and Narratives (subjects listening to the spoken stories). Encoding models based on task features are used to predict activity in different regions across the whole brain. Features from coreference resolution, NER, and shallow syntax parsing explain greater variance for the reading activity. On the other hand, for the listening activity, tasks such as paraphrase generation, summarization, and natural language inference show better encoding performance. Experiments across all 10 task representations provide the following cognitive insights: (i) language left hemisphere has higher predictive brain activity versus language right hemisphere, (ii) posterior medial cortex, temporoparieto-occipital junction, dorsal frontal lobe have higher correlation versus early auditory and auditory association cortex, (iii) syntactic and semantic tasks display a good predictive performance across brain region