Spoken English proficiency is a powerful driver of economic mobility for low-income Indian youth, yet opportunities for spoken practice remain scarce in schools. We investigate the deployment of a voice-based chatbot for English conversation practice across four low-resource schools in Delhi. Through a six-day field study combining observations and interviews, we captured the perspectives of students, teachers, and principals. Findings confirm high demand across all groups, with notable gains in student speaking confidence. Our multi-stakeholder analysis surfaced a tension in long-term adoption vision: students favored open-ended conversational practice, while administrators emphasized curriculum-aligned assessment. We offer design recommendations for voice-enabled chatbots in low-resource multilingual contexts, highlighting the need for more intelligible speech output for non-native learners, one-tap interactions with simplified interfaces, and actionable analytics for educators. Beyond language learning, our findings inform the co-design of future AI-based educational technologies that are socially sustainable within the complex ecosystem of low-resource schools.

Crime prediction (CP) plays a pivotal role in urban analytics, contributing significantly to personal safety and societal stability. Unlike conventional time series forecasting, CP faces unique difficulties due to the inherent sparsity of crime incidents, particularly within small spatial regions and limited time windows. This sparsity, coupled with the non-Gaussian distribution of crime data—characterized by an excess of zero events and over-dispersion—presents a critical challenge for the signal processing community. In this regard, we propose a novel framework, Spatial-Temporal Multivariate Zero-Inflated Negative Binomial Graph Neural Networks (STMGNN-ZINB), which integrates diffusion and convolutional graph networks to capture spatial, temporal, and multivariate dependencies. By leveraging a Zero-Inflated Negative Binomial distribution, the STMGNN-ZINB effectively models the over-dispersed and zero-heavy nature of crime data, significantly improving both prediction accuracy and confidence interval estimation. Experimental results on real-world datasets demonstrate that our STMGNN-ZINB outperforms state-of-the-art CP methods, offering a robust tool for crime early warning and explicable insights into urban crime dynamics.

Sunny Rai, Khushang Zaveri, Shreya Havaldar, Soumna Nema, Lyle Ungar, Sharath Chandra Guntuku. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

Dialogue systems are designed to offer human users social support or functional services through natural language interactions. Traditional conversation research has put significant emphasis on a system’s response-ability, including its capacity to understand dialogue context and generate appropriate responses. However, the key element of proactive behavior—a crucial aspect of intelligent conversations—is often overlooked in these studies. Proactivity empowers conversational agents to lead conversations towards achieving pre-defined targets or fulfilling specific goals on the system side. Proactive dialogue systems are equipped with advanced techniques to handle complex tasks, requiring strategic and motivational interactions, thus representing a significant step towards artificial general intelligence. Motivated by the necessity and challenges of building proactive dialogue systems, we provide a comprehensive review of various prominent problems and advanced designs for implementing proactivity into different types of dialogue systems, including open-domain dialogues, task-oriented dialogues, and information-seeking dialogues. We also discuss real-world challenges that require further research attention to meet application needs in the future, such as proactivity in dialogue systems that are based on large language models, proactivity in hybrid dialogues, evaluation protocols and ethical considerations for proactive dialogue systems. By providing a quick access and overall picture of the proactive dialogue systems domain, we aim to inspire new research directions and stimulate further advancements towards achieving the next level of conversational AI capabilities, paving the way for more dynamic and intelligent interactions within various application domains.

Shreya Havaldar, Salvatore Giorgi, Sunny Rai, Thomas Talhelm, Sharath Chandra Guntuku, Lyle Ungar. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

Mental health conversational agents (a.k.a. chatbots) are widely studied for their potential to offer accessible support to those experiencing mental health challenges. Previous surveys on the topic primarily consider papers published in either computer science or medicine, leading to a divide in understanding and hindering the sharing of beneficial knowledge between both domains. To bridge this gap, we conduct a comprehensive literature review using the PRISMA framework, reviewing 534 papers published in both computer science and medicine. Our systematic review reveals 136 key papers on building mental health-related conversational agents with diverse characteristics of modeling and experimental design techniques. We find that computer science papers focus on LLM techniques and evaluating response quality using automated metrics with little attention to the application while medical papers use rule-based conversational agents and outcome metrics to measure the health outcomes of participants. Based on our findings on transparency, ethics, and cultural heterogeneity in this review, we provide a few recommendations to help bridge the disciplinary divide and enable the cross-disciplinary development of mental health conversational agents.

Adaptive mobile device-based health interventions often use machine learning models trained on non-mobile device data, such as social media text, due to the difficulty and high expense of collecting large text message (SMS) data. Therefore, understanding the differences and generalization of models between these platforms is crucial for proper deployment. We examined the psycho-linguistic differences between Facebook and text messages, and their impact on out-of-domain model performance, using a sample of 120 users who shared both. We found that users use Facebook for sharing experiences (e.g., leisure) and SMS for task-oriented and conversational purposes (e.g., plan confirmations), reflecting the differences in the affordances. To examine the downstream effects of these differences, we used pre-trained Facebook-based language models to estimate age, gender, depression, life satisfaction, and stress on both Facebook and SMS. We found no significant differences in correlations between the estimates and self-reports across 6 of 8 models. These results suggest using pre-trained Facebook language models to achieve better accuracy with just-in-time interventions.

Underwater Image Quality Assessment (UIQA) poses specific challenges due to blur, dispersion of light, and color garbling caused by water turbulence. Images captured by Autonomous Underwater Vehicles (AVS) correlate poorly along their RGB channels, as blue and green channel components dominate. We propose a novel lightweight no-reference (NR) UIQA architecture based on depthwise-separable convolutions and global sparse attention that surpasses the existing deep learning architectures in terms of performance as well as parameter count and Multiply-Accumulate operations (MACs). Proposed model gives 3.64% increase in SRCC and 6.11% increase in PLCC in comparison to state-of-the-art for UEQAB dataset. Our work also illustrates the effectiveness of depthwise separable convolutions for underwater image quality assessment. Our empirical analysis confirms less redundancy among the channels of a feature map when depthwise separable convolutions are used compared to standard convolutions by increasing representational efficiency.

While popular Television (TV) shows are airing, some users interested in these shows publish social media posts about the show. Analyzing social media posts related to a TV show can be beneficial for gaining insights about what happened during scenes of the show. This is a challenging task partly because a significant number of social media posts associated with a TV show or event may not clearly describe what happened during the event. In this work, we propose a method to predict social media posts (associated with scenes of a TV show) that are indicative of what transpired during the scenes of the show. We evaluate our method on social media (Twitter) posts associated with an episode of a popular TV show, Game of Thrones. We show that for each of the identified scenes, with high AUC’s, our method can predict posts that are indicative of what happened in a scene from those that are not-indicative. Based on Twitters policy, we will make the Tweeter ID’s of the Twitter posts used for this work publicly available.

With the boom of social media communication, teleconferencing, and online classes, audiovisual communication over bandwidth strained networks has become an integral part of our lives. Consequently, the growing demand for the quality of experience necessitates developing algorithms to measure and enrich user experience. Prior studies have mainly focused on assessing speech quality and intelligibility with reference to audio quality assessment, while other categories in user-generated multimedia (UGM) are less explored. Moreover, frequency-domain properties of speech and UGM audio are significantly different from each other. Furthermore, there is a lack of a standard dataset for the quality assessment of UGM. Considering these limitations, in this article, we first develop the IIT-JMU-UGM audio dataset consisting of 1150 audio clips, with diverse context, content, and types of degradation commonly observed in real-world scenarios and annotated with the subjective quality scores. Finally, we propose a non-intrusive audio quality assessment metric using a stacked gated-recurrent-unit-based deep learning framework. The proposed model outperforms several baseline methods, including state-of-the-art non-intrusive and intrusive approaches. The resulting Pearson’s correlation coefficient of 0.834 indicates that the proposed method efficiently mirrors human auditory perception.

Quality assessment of 3D-synthesized images has traditionally been based on detecting specific categories of distortions such as stretching, black-holes, blurring, etc. However, such approaches have limitations in accurately detecting distortions entirely in 3D synthesized images affecting their performance. This work proposes an algorithm to efficiently detect the distortions and subsequently evaluate the perceptual quality of 3D synthesized images. The process of generation of 3D synthesized images produces a few pixel shift between reference and 3D synthesized image, and hence they are not properly aligned with each other. To address this, we propose using morphological operation (opening) in the residual image to reduce perceptually unimportant information between the reference and the distorted 3D synthesized image. The residual image suppresses the perceptually unimportant information and highlights the geometric distortions which significantly affect the overall quality of 3D synthesized images. We utilized the information present in the residual image to quantify the perceptual quality measure and named this algorithm as Perceptually Unimportant Information Reduction (PU-IR) algorithm. At the same time, the residual image cannot capture the minor structural and geometric distortions due to the usage of erosion operation. To address this, we extract the perceptually important deep features from the pre-trained VGG-16 architectures on the Laplacian pyramid. The distortions in 3D synthesized images are present in patches, and the human visual system perceives even the small levels of these distortions. With this view, to compare these deep features between reference and distorted image, we propose using cosine similarity and named this algorithm as Deep Features extraction and comparison using Cosine Similarity (DF-CS) algorithm. The cosine similarity is based upon their similarity rather than computing the magnitude of the difference of deep features. Finally, the pooling is done to obtain the objective quality scores using simple multiplication to both PU-IR and DF-CS algorithms. Our source code is available online: https://github.com/sadbhawnathakur/3D-Image-Quality-Assessment.

Existing Quality Assessment (QA) algorithms consider identifying "black-holes" to assess perceptual quality of 3D-synthesized views. However, advancements in rendering and inpainting techniques have made black-hole artifacts near obsolete. Further, 3D-synthesized views frequently suffer from stretching artifacts due to occlusion that in turn affect perceptual quality. Existing QA algorithms are found to be inefficient in identifying these artifacts, as has been seen by their performance on the IETR dataset. We found, empirically, that there is a relationship between the number of blocks with stretching artifacts in view and the overall perceptual quality. Building on this observation, we propose a Convolutional Neural Network (CNN) based algorithm that identifies the blocks with stretching artifacts and incorporates the number of blocks with the stretching artifacts to predict the quality of 3D-synthesized views. To address the challenge with existing 3D-synthesized views dataset, which has few samples, we collect images from other related datasets to increase the sample size and increase generalization while training our proposed CNN-based algorithm. The proposed algorithm identifies blocks with stretching distortions and subsequently fuses them to predict perceptual quality without reference, achieving improvement in performance compared to existing no-reference QA algorithms that are not trained on the IETR dataset. The proposed algorithm can also identify the blocks with stretching artifacts efficiently, which can further be used in downstream applications to improve the quality of 3D views. Our source code is available online: https://github.com/sadbhawnathakur/3D-Image-Quality-Assessment.

We propose a two-stage Convolutional Neural Network (CNN) based classification framework for detecting COVID-19 and Community Acquired Pneumonia (CAP) using the chest Computed Tomography (CT) scan images. In the first stage, an infection - COVID-19 or CAP, is detected using a pre-trained DenseNet architecture. Then, in the second stage, a fine-grained three-way classification is done using EfficientNet architecture. The proposed COVID+CAP-CNN framework achieved a slice-level classification accuracy of over 94% at identifying COVID-19 and CAP. Further, the proposed framework has the potential to be an initial screening tool for differential diagnosis of COVID-19 and CAP, achieving a validation accuracy of over 89.3% at the finer three-way COVID-19, CAP, and healthy classification. Within the IEEE ICASSP 2021 Signal Processing Grand Challenge (SPGC) on COVID-19 Diagnosis, our proposed two-stage classification framework achieved an overall accuracy of 90% and sensitivity of .857, .9, and .942 at distinguishing COVID-19, CAP, and normal individuals respectively, to rank first in the evaluation. Code and model weights are available at https://github.com/shubhamchaudhary2015/ct_covid19_cap_cnn

Haze is an intrusion element that disrupts color fidelity and contrast of outdoor natural images, affecting their perceptual quality. The differential characteristics of hazy images compared to other natural images restrict the generalization of existing image quality assessment (IQA) algorithms. At the same time, efficient IQA algorithms for predicting the perceptual quality of naturally hazed images have not been proposed in the literature due to lack of a relevant dataset. To address this, we build the IIT-JMU Hazy Image Dataset comprising of 1000 high-definition hazy natural images consisting of diverse categories such as landscape, forests, roads, seascapes, and cityscapes, along with their subjective quality ratings. We present an analysis of existing natural-scene-statistics-based IQA algorithms on hazy natural images. In this article, we propose a convolutional-neural-network-based quality assessment algorithm for hazy natural images along with an IQA metric called deep learning-based haze perceptual quality evaluator (DLHPQE). The proposed DLHPQE efficiently predicts the perceptual quality of hazy natural images without a reference. Our results demonstrate that the DLHPQE outperforms existing state-of-the-art no-reference IQAs in terms of several performance parameters such as Pearson linear correlation coefficient, Spearman rank-order correlation coefficient, Kendall's rank-order correlation coefficient, and root-mean-square error.

Modeling politeness across cultures helps to improve intercultural communication by uncovering what is considered appropriate and polite. We study the linguistic features associated with politeness across American English and Mandarin Chinese. First, we annotate 5,300 Twitter posts from the United States (US) and 5,300 Sina Weibo posts from China for politeness scores. Next, we develop an English and Chinese politeness feature set, 'PoliteLex'. Combining it with validated psycholinguistic dictionaries, we study the correlations between linguistic features and perceived politeness across cultures. We find that on Mandarin Weibo, future-focusing conversations, identifying with a group affiliation, and gratitude are considered more polite compared to English Twitter. Death-related taboo topics, use of pronouns (with the exception of honorifics), and informal language are associated with higher impoliteness on Mandarin Weibo than on English Twitter. Finally, we build language-based machine learning models to predict politeness with an F1 score of 0.886 on Mandarin Weibo and 0.774 on English Twitter.

Color-difference interpolation (CDI) has been a widely used technique for various color demosaicking methods. CDI-based methods perform interpolation in the color-difference domain assuming that the color-difference signal is a low-pass signal. Recently, a residual interpolation (RI) algorithm, which conducts interpolation in the residual domain, has been developed, and it assumes that the residual domain is flatter or smoother than the channel-difference domain. In this paper, we comprehensively show a frequency domain analysis of these assumptions and observe that it is image dependent and creates artifacts in the interpolated image. With this view, we propose an algorithm that uses the inter-color correlation as well as the residual smoothness among the different channel much better than the existing algorithms. Experimental results emphasize that the proposed algorithm atribute better performances the existing algorithms in terms of both visual and objective quality.

With multitudes of image processing applications, image quality assessment (IQA) has become a prerequisite for obtaining maximally distinctive statistics from images. Despite the widespread research in this domain over several years, existing IQA algorithms have a number of key limitations concerning different image distortion types and algorithms' computational efficiency. Images that are synthesized using depth image-based rendering have applications in various disciplines, such as free viewpoint videos, which enable synthesis of novel realistic images in the referenceless environment. In the literature, very few no-reference (NR) quality assessment metrics of three-dimensional (3-D) synthesized images are proposed, and most of them are computationally expensive, which makes it difficult for them to be deployed in real-time applications. In this paper, we attribute the geometrically distorted pixels as outliers in 3-D synthesized images. This assumption is validated using the three $sigma$ rule-based robust outlyingness ratio. We propose a novel fast and accurate blind IQA metric of 3-D synthesized images using nonlinear median filtering since the median filtering has the capability of identifying and removing outliers. The advantages of the proposed algorithm are twofold. First, it uses a simple technique, i.e., median filtering, to capture the level of geometric and structural distortions (up to some extend). Second, the proposed algorithm has higher computational efficiency. Experiments show the superiority of the proposed NR IQA algorithm over existing state-of-the-art full-, reduced-, and NR IQA methods, in terms of both predicting accuracy and computational complexity.

The increased proliferation of data production technologies (e.g., cameras) and consumption avenues (e.g., social media) has led to images and videos being utilized by users to convey innate preferences and tastes. This has opened up the possibility of using multimedia as a source for user-modeling. This work attempts to model personality traits (based on the Five Factor Theory) of users using a collection of images they tag as `favorite' (or like) on Flickr. First, a set of semantic features are proposed to be used for representing different concepts in images which influence users to like them. The addition of the proposed features led to improvement over state-of-the-art by 12 percent. Second, a novel machine learning approach is developed to model users' personality based on the image features (resulting in upto 15 percent improvement). Third, efficacy of the semantic features and the modeling approach is shown in recommending images based on personality modeling. Using the modeling approach, recommendations are made regarding the factors that might influence users with different personality traits to like an image.

The next generation of multimedia services have to be optimized in a personalized way, taking user factors into account for the evaluation of individual experience. Previous works have investigated the influence of user factors mostly in a controlled laboratory environment which often includes a limited number of users and fails to reflect real-life environment. Social media, especially Facebook, provide an interesting alternative for Internet-based subjective evaluation. In this article, we develop (and open-source) a Facebook application, named YouQ 1 , as an experimental platform for studying individual experience for videos. Our results show that subjective experiments based on YouQ can produce reliable results as compared to a controlled laboratory experiment. Additionally, YouQ has the ability to collect user information automatically from Facebook, which can be used for modeling individual experience.

Much of our online communication is textmediated and, lately, more common with automated agents.Unlike interacting with humans, these agents currently do not tailor their language to the type of person they are communicating to.In this pilot study, we measure the extent to which human perception of basic user trait information -gender and age -is controllable through text.Using automatic models of gender and age prediction, we estimate which tweets posted by a user are more likely to mis-characterize his traits.We perform multiple controlled crowdsourcing experiments in which we show that we can reduce the human prediction accuracy of gender to almost random -an over 20% drop in accuracy.Our experiments show that it is practically feasible for multiple applications such as text generation, text summarization or machine translation to be tailored to specific traits and perceived as such.

Most of the existing image reconstruction algorithms are application specific, and have generalization issues due to the need for parameter tuning and an unknown level of signal distortion. Addressing these problems, in this paper, we propose an efficient perceptually motivated and maximum a posterior (MAP)-based generic framework for image reconstruction. This can be applied to several image/video processing applications, where there is a necessity to improve reconstruction accuracy and suppress visible artifacts, such as denoising, deinterlacing, interpolation, de-blocking of Jpeg/Jpeg-2000, and demosaicing. The gradient magnitudes are noise insensitive to a moderate levels of noise and we propose to utilize this property for finding pixels with similar edge semantics in the neighborhood when neighboring pixels are noisy. With this view, we incorporate the gradient magnitude similarity based image quality assessment metric with the MAP estimation and, in turn, it can better approximate the variance of the MAP, as compared to nonlinear filters. The proposed generic algorithm (without manually tuning any parameters) is shown to produce a better quality of reconstruction when compared to the state-of-the-art application-specific algorithms, for most of the image processing applications.

Recommending content to users involves understanding a) what to present and b) how to present them, so as to increase quality of experience (QoE) and thereby, content consumption. This work attempts to address the question of how to present contents in a way so that the user finds it easy to get to desired content. While the process of User Interface (UI) design is dependent on several human factors, there are basic design components and their combination that have to be common to any recommender system user interface. Personalization of the UI design process involves picking the right components and their combination, and presenting a UI to suit the usage behavior of an individual user, so as to enhance the QoE. This work proposes a system that learns from a user's content consumption patterns and makes some recommendations regarding how to present the content for the user (in the context of Video-On-Demand/Live-TV services on Computer displays), so as to enhance the QoE of the recommender system.

Recommending items that have rarely/never been viewed by users is a bottleneck for collaborative filtering (CF) based recommendation algorithms. To alleviate this problem, item content representation (mostly in textual form) has been used as auxiliary information for learning latent factor representations. In this work we present a novel method for learning latent factor representation for videos based on modelling the emotional connection between user and item. First of all we present a comparative analysis of state-of-the art emotion modelling approaches that brings out a surprising finding regarding the efficacy of latent factor representations in modelling emotion in video content. Based on this finding we present a method visual-CLiMF for learning latent factor representations for cold start videos based on implicit feedback. Visual-CLiMF is based on the popular collaborative less-is-more approach but demonstrates how emotional aspects of items could be used as auxiliary information to improve MRR performance. Experiments on a new data set and the Amazon products data set demonstrate the effectiveness of visual-CLiMF which outperforms existing CF methods with or without content information.

Automatically understanding and discriminating different users' liking for an image is a challenging problem. This is because the relationship between image features (even semantic ones extracted by existing tools, viz., faces, objects, and so on) and users' likes is non-linear, influenced by several subtle factors. This paper presents a deep bi-modal knowledge representation of images based on their visual content and associated tags (text). A mapping step between the different levels of visual and textual representations allows for the transfer of semantic knowledge between the two modalities. Feature selection is applied before learning deep representation to identify the important features for a user to like an image. The proposed representation is shown to be effective in discriminating users based on images they like and also in recommending images that a given user likes, outperforming the state-of-the-art feature representations by ∼ 15 %-20%. Beyond this test-set performance, an attempt is made to qualitatively understand the representations learned by the deep architecture used to model user likes.

The interplay between system, context, and human factors is important in perception of multimedia quality. However, studies on human factors are very limited in comparison to those for system and context factors. This article presents an attempt to explore the influence of personality and cultural traits on perception of multimedia quality. As a first step, a database consisting of 144 video sequences from 12 short movie excerpts has been assembled and rated by 114 participants from a cross-cultural population, thereby providing a useful ground-truth for this (as well as future) study. As a second step, three statistical models are compared: (i) a baseline model to only consider system factors; (ii) an extended model to include personality and culture; and (iii) an optimistic model in which each participant is modeled. As a third step, predictive models based on content, affect, system, and human factors are trained to generalize the statistical findings. As shown by statistical analysis, personality and cultural traits represent 9.3% of the variance attributable to human factors, and human factors overall predict an equal or higher proportion of variance compared to system factors. Moreover, the quality-enjoyment correlation varies across the excerpts. Predictive models trained by including human factors demonstrate about 3% and 9% improvement over models trained solely based on system factors for predicting perceived quality and enjoyment. As evidenced by this, human factors indeed are important in perceptual multimedia quality, but the results suggest further investigation of moderation effects and a broader range of human factors is necessary.

Affect is evoked through an intricate relationship between the characteristics of stimuli, individuals, and systems of perception. While affect is widely researched, few studies consider the combination of multimedia system characteristics and human factors together. As such, this paper explores the influence of personality (Five-Factor Model) and cultural traits (Hofstede Model) on the intensity of multimedia-evoked positive and negative affects (emotions). A set of 144 video sequences (from 12 short movie clips) were evaluated by 114 participants from a cross-cultural population, producing 1232 ratings. On this data, three multilevel regression models are compared: a baseline model that only considers system factors; an extended model that includes personality and culture; and an optimistic model in which each participant is modelled. An analysis shows that personal and cultural traits represent 5.6% of the variance in positive affect and 13.6% of the variance in negative affect. In addition, the affect-enjoyment correlation varied across the clips. This suggests that personality and culture play a key role in predicting the intensity of negative affect and whether or not it is enjoyed, but a more sophisticated set of predictors is needed to model positive affect with the same efficacy.

Computationally modeling users `liking' for image(s) requires understanding how to effectively represent the image so that different factors influencing user `likes' are considered. In this work, an evaluation of the state-of-the-art visual features in multimedia understanding at the task of predicting user `likes' is presented, based on a collection of images crawled from Flickr. Secondly, a probabilistic approach for modeling `likes' based only on tags is proposed. The approach of using both visual and text-based features is shown to improve the state-of-the-art performance by 12%. Analysis of the results indicate that more human-interpretable and semantic representations are important for the task of predicting very subtle response of `likes'.

Perception of multimedia quality is shaped by a rich interplay between system, context and human factors. While system and context factors are widely researched, few studies consider human factors as sources of systematic variance. This paper presents an analysis on the influence of personality and cultural traits on the perception of multimedia quality. A set of 144 video sequences (from 12 short movie excerpts) were rated by 114 participants from a cross-cultural population, producing 1232 ratings. On this data, three models are compared: a baseline model that only considers system factors; an extended model that includes personality and culture as human factors; and an optimistic model in which each participant is modelled as a random effect. An analysis shows that personality and cultural traits represent 9.3\% of the variance attributable to human factors while human factors overall predict an equal or higher proportion of variance compared to system factors. In addition, the quality-enjoyment correlation varied across the excerpts. This suggests that human factors play an important role in perceptual multimedia quality, but further research to explore moderation effects and a broader range of human factors is warranted.