Abstract

Emotion evoked by an advertisement plays a key role in influencing brand recall and eventual consumer choices. Automatic ad affect recognition has several useful applications. However, the use of content-based feature representations does not give insights into how affect is modulated by aspects such as the ad scene setting, salient object attributes and their interactions. Neither do such ap- proaches inform us on how humans prioritize visual information for ad understanding. Our work addresses these lacunae by decom- posing video content into detected objects, coarse scene structure, object statistics and actively attended objects identified via eye- gaze. We measure the importance of each of these information channels by systematically incorporating related information into ad affect prediction models. Contrary to the popular notion that ad affect hinges on the narrative and the clever use of linguistic and social cues, we find that actively attended objects and the coarse scene structure better encode affective information as compared to individual scene objects or conspicuous background elements.

Abstract

Ontology engineering aims to specify meaning to computer as accurately as possible since that would enable any kind of application or any amount of analysis required for a given domain. But for that, one needs to first understand the distinction between form and content in reality, for which, understanding the distinction between logical form and onto-logical (ontological) form becomes crucial. In this work, we propose an ontological form - punctuator - in contrast with logical form like proposition, and contend that formal ontology, in its proper sense, is possible only through the ontological form and not the logical form since the former is apt to do the logic of entities whereas the latter is apt to do the logic of sentences about entities. Once we establish this point, we need to think how to specify meaning as descriptively/objectively as possible. One of the best ways to do that is to minimize the amount of human intervention necessary for building the ontology since the objectivity of an ontology (or anything) is inversely proportional to the amount of human intervention in it. For this, we propose a novel concept called ‘Generative Ontology’ where the States-ofAffairs (SOAs) are modeled as graphs, and specify rules to generate potentially infinite number of complex graphs from a finite number of simple graphs. For this, we use the ontological form mentioned above, and we take Vaies. ika ontology, one of the philosophical schools in Indian tradition which focuses on foundational ontology, as a case-inpoint, and specify generation, interpretation as well as parsing rules for its graphs (SOAs) according to the Vaieika worldview and establish the formalness of such a system. Though this work is proposing yet another foundational ontology, its uniqueness lies in its generative nature and the ontological form which it uses to do so.

Abstract

Bug report filing is a major part of software maintenance. Due to the asynchronous nature of the bug filing process, duplicate bug reports are filed. Detecting duplicate bug reports is an important aspect of software maintenance since the same bug should not be assigned to different developers. In this poster, we present Deep Word Embedding Network for computing similarity between two bug reports for the task of duplicate bug report detection. We propose to learn a two step model to calculate similarity between two bug reports by means of word embeddings and a deep neural network. We run experiments on two large datasets of Mozilla Project and Open Office Project and compare the proposed approach with baselines and related approaches. Through this initial work, we show that a combination of word embeddings and deep neural networks can be used to improve duplicate bug report detection.

Abstract

With improved digital literacy and cheaper data connections, crowdsourcing has become more prevalent. Crowdsourcing tasks such as image tagging, language translation, etc. have contributors with varied skill level. Question and answers, software development/testing and product design are more serious tasks and require expert contributions. With increasing security threats, crowdsourcing in 'security' domain is seen as an upcoming trend. In the survey, opportunities and challenges in crowdsourcing security are analyzed based on a survey conducted with 229 participants. The results provide insights on motivation, quality mechanisms and improvement areas for increased participation. 'Question and Answers' that includes information sharing and 'software development and testing' that includes Bug Bounty are identified as top crowdsourcing tasks by security specialists although they are concerned about security and privacy of information. Among quality attributes analyzed, contributor 'credibility' is identified as a key area of improvement for increased participation in crowdsourcing.

Abstract

Permalloy is commonly used to boost the overall permeability of on-chip inductors for radio frequencies. To capacitate the use of Permalloy at high frequencies, its high-frequency behaviour is studied by exploring the role of domain dynamics in RF applications. In this work, Aluminium lines covered with discrete Permalloy films are studied through simulation and fabrication. The effect of domain dynamics due to various domain patterns, applied RF power and DC bias level on high-frequency inductance is thoroughly analysed.

Abstract

Several designer controllable parameters and their effect on various specifications like switching time, sampling speed and input amplitude of all-optical Binary Delta Sigma Modulator (BDSM) are analyzed and possibility of enhancing the performance is discussed.

Abstract

In this paper we discuss the VLSI implementation of the new radix-2 Decimation In Time (DIT) Fast Fourier Transform (FFT) algorithm with reduced arithmetic complexity which is based on scaling the twiddle factor. Some signal processing require high performance FFT processors and to meet these performance requirements, the processor needs to be pipelined and parallelized. An optimized ASIC design is derived from this new radix-2 algorithm with fewer multipliers and adopted a complete parallel and pipelined architecture for hardware implementation of a 64 point FFT. The implementation results show that the proposed architecture significantly reduces the hardware area by 13.74 percent and power consumption by 16 percent when compared to the standard FFT architecture. Simulation of design units is done in Xilinx ISE WebPack 13.1 and synthesized using Cadence Encounter RTL Compiler.

Abstract

In this paper, we design and evaluate a convolutional autoencoder that perturbs an input face image to impart privacy to a subject. Specifically, the proposed autoencoder transforms an input face image such that the transformed image can be successfully used for face recognition but not for gender classification. In order to train this autoencoder, we propose a novel training scheme, referred to as semiadversarial training in this work. The training is facilitated by attaching a semi-adversarial module consisting of an auxiliary gender classifier and an auxiliary face matcher to the autoencoder. The objective function utilized for training this network has three terms: one to ensure that the perturbed image is a realistic face image; another to ensure that the gender attributes of the face are confounded; and a third to ensure that biometric recognition performance due to the perturbed image is not impacted. Extensive experiments confirm the efficacy of the proposed architecture in extending gender privacy to face images.

Abstract

The HITL paradigm has been extended as SITL (SocietyIn-The-Loop) to account for the broader role of AI in the society and vice versa. To open up these otherwise opaque systems and their nexus of interactions with humans, there is a need to make tools to program and debug the algorithmic social contract, a pact between various human stakeholders, mediated by machines. In this paper, we propose one such tool, the ESO-5W1H framework to adjudge the role of humans and machines in their respective interactions and to structure the underlying decision making process such that accountability and liability for each system action-interactions can be brought to the fore. We discuss the working of this conceptual framework in the context of three use cases: the Self-driving car, an AI-based jury, and Neural Networks

Abstract

An effective news recommendation system should harness the his- torical information of the user based on her interactions as well as the content of the articles. In this paper we propose a novel deep learning model for news recommendation which utilizes the content of the news articles as well as the sequence in which the articles were read by the user. To model both of these information, which are essentially of different types, we propose a simple yet effective architecture which utilizes a 3-dimensional Convolutional Neural Network which takes the word embeddings of the articles present in the user history as its input. Using such a method en- dows the model with the capability to automatically learn spatial (features of a particular article) as well as temporal features (fea- tures across articles read by a user) which signify the interest of the user. At test time, we use this in combination with a 2-dimensional Convolutional Neural Network for recommending articles to users. On a real-world dataset our method outperformed strong baselines which also model the news recommendation problem using neural networks.