Abstract

This work introduces Talk2BEV, a large vision-language model (LVLM) interface for bird’s-eye view (BEV) maps in autonomous driving contexts. While existing perception systems for autonomous driving scenarios have largely focused on a pre-defined (closed) set of object categories and driving scenarios, Talk2BEV blends recent advances in general-purpose language and vision models with BEV-structured map representations, eliminating the need for task-specific models. This enables a single system to cater to a variety of autonomous driving tasks encompassing visual and spatial reasoning, predicting the intents of traffic actors, and decision-making based on visual cues. We extensively evaluate Talk2BEV on a large number of scene understanding tasks that rely on both the ability to interpret free-form natural language queries and in grounding these queries to the visual context embedded into the language-enhanced BEV map. To enable further research in LVLMs for autonomous driving scenarios, we develop and release Talk2BEV-Bench, a benchmark encompassing 1000 human-annotated BEV scenarios, with more than 20,000 questions and ground-truth responses from the NuScenes dataset.

Abstract

A Completely Automated Public Turing Test to Tell Computers and Humans Apart (CAPTCHA) is one of the primary barriers between notorious bots and legitimate human users. However, advancements in Artificial Intelligence (AI) have enabled malicious bots to circumvent CAPTCHA challenges effectively. As a result, several types of CAPTCHA have been rendered ineffective. In this paper, we introduce Swiss Cheese CAPTCHA, a novel sensor-based solution designed to be easily solvable by humans while presenting multiple barriers for bots (similar to the Swiss Cheese Model). We leverage a range of human cognitive abilities and Generic Sensor API in modern devices to provide robust protection against automated attacks by making it more computationally expensive for bots to produce a valid answer within a stipulated time. We conducted two user studies to assess our proposal's effectiveness: one involving 116 participants to assess the likability and improvise the design and the other, with 107 participants, to investigate the impact of improvised design changes on cognitive abilities. Our results from these studies show an average completion time of 4.76 seconds and 6.12 seconds, with a success rate of 90.3% and 83.25%, respectively. By analyzing the 2141 resultant trajectories from both the user studies, we assess the learnability, error recovery rate, efficiency, and satisfaction of using the scheme. Finally, we devise an automated attack against our proposal to analyze its security in real world; we find the probability of attack success is low. We also make our dataset available for further research.

Abstract

Development of software products can often result in generation of Software Development Waste (SDW). For example, developers may possibly need to rework implementations that cater to ambiguous feature stories. COVID-19 pandemic has influenced the way software development teams operate worldwide. We studied the impact of pandemic enforced work-from-home situation (PWS) on generation of SDW. As a part of a multi-year study, we surveyed 615 participants and interviewed 31 from the software industry across eight countries specializing in various domains. We observed a rise in SDWs, and were able to identify new type of SDW, and other wastes that could be reclassified into existing types of wastes.

Abstract

The use of emerging technologies like Virtual Reality (VR) in therapeutic settings has increased in the past few years. By incorporating VR, a mental health condition like depression can be assessed effectively, while also providing personalized motivation and meaningful engagement for treatment purposes. The integration of external sensors further enhances the engagement of the subjects with the VR scenes. This paper presents a comprehensive review of existing literature on the detection and treatment of depression using VR. It explores various types of VR scenes, external hardware, innovative metrics, and targeted user studies conducted by researchers and professionals in the field. The paper also discusses potential requirements for designing VR scenes specifically tailored for depression assessment and treatment, with the aim of guiding future practitioners in this area.

Abstract

News headline generation is a crucial task in increasing productivity for both the readers and producers of news. This task can easily be aided by automated News headline-generation models. However, the presence of irrelevant headlines in scraped news articles results in sub-optimal performance of generation models. We propose that relevance-based headline classification can greatly aid the task of generating relevant headlines. Relevance-based headline classification involves categorizing news headlines based on their relevance to the corresponding news articles. While this task is well-established in English, it remains under-explored in low-resource languages like Telugu due to a lack of annotated data. To address this gap, we present TeClass, the first-ever human-annotated Telugu news headline classification dataset, containing 78,534 annotations across 26,178 article-headline pairs. We experiment with various baseline models and provide a comprehensive analysis of their results. We further demonstrate the impact of this work by fine-tuning various headline generation models using TeClass dataset. The headlines generated by the models fine-tuned on highly relevant article-headline pairs, showed about a 5 point increment in the ROUGE-L scores. To encourage future research, the annotated dataset as well as the annotation guidelines will be made publicly available.

Abstract

Software practitioners use various methods in Requirements Engineering (RE) to elicit, analyze and specify the requirements of a enterprise products. The methods impact the final product characteristics and influence product delivery. Ad-hoc usage of the methods by software practitioners can lead to inconsistency and ambiguity in the product. With the notable rise in enterprise products, games, etc. across various domains, Virtual Reality (VR) has become an essential technology for the future. The methods adopted for requirement engineering for developing VR products requires a detailed study. This paper presents a mapping study on requirement engineering methods prescribed and used for developing VR applications including requirements elicitation, requirements analysis, and requirements specification. Our study provides insights into the use of such methods in the VR community and suggests using specific requirement engineering methods in various fields of interest. We also discuss future directions in requirement engineering for VR products.

Abstract

We focus on the problem of LiDAR point cloud based loop detection (or Finding) and closure (LDC) for mobile robots. State-of-the-art (SOTA) methods directly generate learned embeddings from a given point cloud, require large data augmentation, and are not robust to wide viewpoint variations in 6 Degrees-of-Freedom (DOF). Moreover, the absence of strong priors in an unstructured point cloud leads to highly inaccurate LDC. In this original approach, we propose independent roll and pitch canonicalization of point clouds using a common dominant ground plane. We discretize the canonicalized point clouds along the axis perpendicular to the ground plane leads to images simi- lar to digital elevation maps (DEMs), which expose strong spatial priors in the scene. Our experiments show that LDC based on learnt embeddings from such DEMs is not only data efficient but also significantly more robust, and generalizable than the current SOTA. We report an (aver- age precision for loop detection, mean absolute transla- tion/rotation error) improvement of (8.4, 16.7/5.43)% on the KITTI08 sequence, and (11.0, 34.0/25.4)% on GPR10 sequence, over the current SOTA. To further test the ro- bustness of our technique on point clouds in 6-DOF motion we create and opensource a custom dataset called Lidar- UrbanFly Dataset (LUF) which consists of point clouds ob- tained from a LiDAR mounted on a quadrotor. More details on our website https://gsc2001.github.io/FinderNet/

Abstract

Coastal waters are complex, dynamic, and sensitive, and any change in the system impacts the marine environment and life. Coastal water quality has been decreasing due to the incursion of anthropogenic derived waste and toxins into the ocean. This study investigates water quality along the Kollam coast of Kerala State, India, using Sentinel-2 Multispectral Imager (MSI) data for the period of 2019–2022. Four key water quality parameters, chlorophyll (Chl-a), total suspended matter (TSM), turbidity, and coloured dissolved organic matter (CDOM), were analysed for seasonal variations and driving factors. The study highlights the potential of web-based platforms like Google Earth Engine for facilitating large-scale water quality assessments. The results reveal a distinct seasonal pattern in all parameters, primarily influenced by monsoonal riverine discharge and anthropogenic activities as contributing factors to water quality degradation. Overall, the study emphasises the need for comprehensive monitoring and management strate- gies to ensure the long-term sustainability of the coastal ecosystem.

Abstract

fMRI studies using naturalistic stimuli like movies present an almost ecologically valid condition to examine dynamic functional connectivity, similar to resting-state conditions. In our comparative study of task and resting-state conditions, we analyzed fMRI data collected from ten healthy participants while watching an 8 minute 45 seconds full-movie selected for empathy and emotion attributed regions of brain. The work extends findings from functional connectivity analysis leveraging graph learning methods applied to time-series data from 54 bilateral brain regions, with particular focus on key areas like the Insula, Anterior Cingulate Cortex, and parietal regions critical for empathy. Match dynamics analysis, supported by connectome-network findings, reveals alignment with the resting-state during low emotional valence intervals of the movie but diverges notably during high emotional valence intervals, suggesting a shared connectivity pattern between stimulus-induced directed (controlled) mind wandering textit{(bottom-up process)} and resting-state activity textit{(top-down process)}. The sparsity-based method shows a 98% match with viewer ratings on the emotion contagion scale, surpassing the 84% match achieved by Pearson's correlation-based method. This nuanced understanding of neural dynamics in empathy-related tasks versus resting-state enhances the understanding of the networks underlying cognitive processes in real-life situations (naturalistic) and the use of resting-state for the same.

Abstract

Functional MRI research using naturalistic stimuli (like movies) can help examine brain networks supporting empathy. Applying graph learning methods to whole-brain time-series signals, we propose a novel fMRI signal processing pipeline that includes high-pass filtering, voxel-level clustering, and windowed graph learning with a sparsity-based approach. The fMRI dataset is from passive viewing of an 8-minute movie shown to 14 healthy volunteers. The emotion rating of the movies by age-matched 40 participants is the ground truth. We considered a total of 54 regions extracted from the AAL Atlas for the study. The sparsity-based graph learning method consistently outperforms in capturing variations in the emotion scale, achieving over 88% match of the graph cluster labels averaged across participants. Temporal analysis reveals a high fit to the emotion scale supported by the method’s effectiveness in capturing dynamic connectomes through graph clustering, indicating the role of contextual inference in building empathy. While the edge-weight dynamics analysis underscores the superiority of sparsity-based learning, the connectome-network analysis highlights the crucial role of the Insula, Amygdala, and Thalamus in empathy, with lateral brain connections facilitating synchronized responses. Spectral filtering analysis by band-pass filter isolated the regions linked to emotional and empathy processing in scenes with high emotional context. We also observe strong similarities between the movies in graph cluster labels, connectome-network analysis, and spectral filtering-based analyses, revealing robust neural correlates of empathy. These findings contribute to a better understanding of the neural dynamics associated with empathy and identify regions specific to empathetic responses to naturalistic stimuli.