Abstract

Multi-object tracking has seen a lot of progress recently, albeit with substantial annotation costs for developing better and larger labeled datasets. In this work, we remove the need for annotated datasets by proposing an unsupervised re-identification network, thus sidestepping the labeling costs entirely, required for training. Given unlabeled videos, our proposed method (SimpleReID) first generates tracking labels using SORT [ 3] and trains a ReID network to predict the generated labels using crossentropy loss. We demonstrate that SimpleReID performs substantially better than simpler alternatives, and we recover the full performance of its supervised counterpart consistently across diverse tracking frameworks. The observations are unusual because unsupervised ReID is not expected to excel in crowded scenarios with occlusions, and drastic viewpoint changes. By incorporating our unsupervised SimpleReID with CenterTrack trained on augmented still images, we establish a new state-of-the-art performance on popular datasets like MOT16/17 without using tracking supervision, beating current best (CenterTrack) by 0.2-0.3 MOTA and 4.4-4.8 IDF1 scores. We further provide evidence for limited scope for improvement in IDF1 scores beyond our unsupervised ReID in the studied settings. Our investigation suggests reconsideration towards more sophisticated, supervised, end-to-end trackers [56 , 5] by showing promise in simpler unsupervised alternatives.

Abstract

In this paper, we propose the use of Message Sequence Charts (MSC) as a representation for visualizing narrative text in Hindi. An MSC is a formal representation allowing the depiction of actors and interactions among these actors in a scenario, apart from supporting a rich framework for formal inference. We propose an approach to extract MSC actors and interactions from a Hindi narrative. As a part of the approach, we enrich an existing event annotation scheme where we provide guidelines for annotation of the mood of events (realis vs irrealis) and guidelines for annotation of event arguments. We report performance on multiple evaluation criteria by experimenting with Hindi narratives from Indian History. Though Hindi is the fourth most-spoken first language in the world, from the NLP perspective it has comparatively lesser resources than English. Moreover, there is relatively less work in the context of event processing in Hindi. Hence, we believe that this work is among the initial works for Hindi event processing.

Abstract

Given the recent progress in language modeling using Transformer-based neural models and an active interest in generating stylized text, we present an approach to leverage the generalization capabilities of a language model to rewrite an input text in a target author’s style. Our proposed approach adapts a pre-trained language model to generate author-stylized text by fine-tuning on the author-specific corpus using a denoising autoencoder (DAE) loss in a cascaded encoder-decoder framework. Optimizing over DAE loss allows our model to learn the nuances of an author’s style without relying on parallel data, which has been a severe limitation of the previous related works in this space. To evaluate the efficacy of our approach, we propose a linguistically motivated framework to quantify stylistic alignment of the generated text to the target author at lexical, syntactic and surface levels. The evaluation framework is both interpretable as it leads to several insights about the model, and self-contained as it does not rely on external classifiers, e.g. sentiment or formality classifiers. Qualitative and quantitative assessment indicates that the proposed approach rewrites the input text with better alignment to the target style while preserving the original content better than state-of-the-art baselines.

Abstract

Integrating components of vehicular network with the Internet has emerged recently for fulfilling the ever-growing demand for a safe and comfortable driving experience. Road Side Unit (RSU) clouds help in serving requests arriving from vehicles but are limited by available resources. It is also required to reduce the overhead cost corresponding to Virtual Machine (VM) migrations caused by high mobility of vehicles. Also, requests need to be served within their stipulated delay constraint. In this work, we propose a novel algorithm to schedule requests at RSU clouds. Our algorithm efficiently schedules service requests from vehicles while taking care of their delay constraints and VM migrations. The simulation results confirm that our proposed scheduling technique helps in serving more number of requests within their stipulated delay constraint with lesser VM migrations.

Abstract

This paper presents a novel approach designed to answer questions on a reading comprehension passage. It is an end-to-end system which first focuses on comprehending the given passage wherein it converts unstructured passage into a structured data and later proceeds to answer the questions related to the passage using solely the aforementioned structured data. To the best of our knowledge, the proposed design is first of its kind which accounts for entire process of comprehending the passage and then answering the questions associated with the passage. The comprehension stage converts the passage into a Discourse Collection that comprises of the relation shared amongst logical sentences in given passage along with the key characteristics of each sentence. This design has its applications in academic domain , query comprehension in speech systems among others.

Abstract

Energy consumption has dramatically increased in the residential building sector over the past few years. Many researchers today are interested not only in designing energy-efficient buildings but also in evaluating the actual building performance and managing operations for delivering the design intent. Monitoring building performance using currently available sensors and mobile applications poses challenges in terms of cost and standardization. This paper presents a new approach to make sensors affordable and inter-operable by designing open-source hardware and using well-established standards for data communication and storage, thereby making energy monitoring ubiquitous and affordable in the residential sector. The proposed solution uses low-power loggers, Bluetooth Low Energy wireless communication version 4 for data transfer from loggers to mobile phones for further transfer to cloud, oneM2M standard to ensure interoperability, and NGSI-LD for data management.

Abstract

In the last decade, civic crowdfunding has proved to be effective in generating funds for the provision of public projects. However, the existing literature deals only with citizen's with positive valuation and symmetric belief towards the project's provision. In this work, we present novel mechanisms which break these two barriers, i.e., mechanisms which incorporate negative valuation and asymmetric belief, independently. For negative valuation, we present a methodology for converting existing mechanisms to mechanisms that incorporate agents with negative valuations. Particularly, we adapt existing PPR and PPS mechanisms, to present novel PPRN and PPSN mechanisms which incentivize strategic agents to contribute to the project based on their true preference. With respect to asymmetric belief, we propose a reward scheme Belief Based Reward (BBR) based on Robust Bayesian Truth Serum mechanism. With BBR, we propose a general mechanism for civic crowdfunding which incorporates asymmetric agents. We leverage PPR and PPS, to present PPRx and PPSx. We prove that in PPRx and PPSx, agents with greater belief towards the project's provision contribute more than agents with lesser belief. Further, we also show that contributions are such that the project is provisioned at equilibrium.

Abstract

Neural text-to-speech synthesis (NTTS) models have shown significant progress in generating high-quality speech, however they require a large quantity of training data. This makes creating models for multiple styles expensive and time-consuming. In this paper different styles of speech are analysed based on prosodic variations, from this a model is proposed to synthesise speech in the style of a newscaster, with just a few hours of supplementary data. We pose the problem of synthesising in a target style using limited data as that of creating a bi-style model that can synthesise both neutral-style and newscaster-style speech via a one-hot vector which factorises the two styles. We also propose conditioning the model on contextual word embeddings, and extensively evaluate it against neutral NTTS, and neutral concatenative-based synthesis. This model closes the gap in perceived style-appropriateness between natural recordings for newscaster-style of speech, and neutral speech synthesis by approximately two-thirds.

Abstract

Musical training causes structural and functional changes in the brain due to its sensory-motor demands. This leads to differences in how musicians perceive and process music as compared to nonmusicians, thereby providing insights into brain adaptations and plasticity. Correlational studies and network analysis investigations have indicated the presence of large-scale brain networks involved in the processing of music and have highlighted the differences between musicians and non-musicians. However, studies on functional connectivity in the brain during music listening tasks have thus far focused solely on static network analysis. Dynamic Functional Connectivity (DFC) studies have lately been found useful in unearthing meaningful, time-varying functional connectivity information in both resting-state and task-based experimental settings. In this study, we examine DFC in the fMRI obtained from two groups of participants, 18 musicians and 18 non-musicians, while they listened to a musical stimulus in a naturalistic setting. We utilize spatial Group Independent Component Analysis (ICA), sliding time window correlations, and a deterministic agglomerative clustering of windowed correlation matrices to identify quasi-stable Functional Connectivity (FC) states in the two groups. To compute cluster centroids that represent FC states, we device and present a method that primarily utilizes windowed correlation matrices occurring repeatedly over time and across participants, while excluding matrices corresponding to spontaneous fluctuations. Preliminary analysis indicate states with greater visuo-sensorimotor integration in musicians, larger presence of DMN states in non-musicians, and variability in states found in musicians due to differences in training and prior experiences.

Abstract

. Automatic research paper summarization is a fairly interesting topic that has garnered significant interest in the research community in recent years. In this paper, we introduce team Helium’s system description for the CL-SciSumm shared task colocated with SIGIR 2019. We specifically attempt the first task, targeting in building an improved recall system of reference text spans from a given citing research paper (Task 1A) and constructing better models for comprehension of scientific facets (Task 1B). Our architecture incorporates transfer learning by utilising a combination of pretrained embeddings which are subsequently used for building models for the given tasks. In particular - for task 1A, we locate the related text spans referred to by the citation text by creating paired text representations and employ pre-trained embedding mechanisms in conjunction with XGBoost, a gradient boosted decision tree algorithm to identify textual entailment. For task 1B, we make use of the same pretrained embeddings and use the RAKEL algorithm for multi-label classification. Our goal is to enable better scientific research comprehension and we believe that a new approach involving transfer learning will certainly add value to the research community working on these tasks.