Abstract

Current Non-Audible Murmur (NAM)-to-speech techniques rely on voice cloning to simulate ground-truth speech from paired whispers. However, the simulated speech often lacks intelligibility and fails to generalize well across different speakers. To address this issue, we focus on learning phoneme-level alignments from paired whispers and text and employ a Textto-Speech (TTS) system to simulate the ground-truth. To reduce dependence on whispers, we learn phoneme alignments directly from NAMs, though the quality is constrained by the available training data. To further mitigate reliance on NAM/whisper data for ground-truth simulation, we propose incorporating the lip modality to infer speech and introduce a novel diffusionbased method that leverages recent advancements in lip-tospeech technology. Additionally, we release the MultiNAM dataset with over 7.96 hours of paired NAM, whisper, video, and text data from two speakers and benchmark all methods on this dataset. Speech samples and the dataset are available at https://diff-nam.github.io/DiffNAM/

Abstract

Image captioning systems are unable to generate fine-grained captions as they are trained on data that is either noisy (alt-text) or generic (human annotations). This is further exacerbated by maximum likelihood training that encourages generation of frequently occurring phrases. Previous works have tried to address this limitation by fine-tuning captioners with a self-retrieval (SR) reward. However, we find that SR fine-tuning has a tendency to reduce caption faithfulness and even hallucinate. In this work, we circumvent this bottleneck by improving the MLE initialization of the captioning system and designing a curriculum for the SR fine-tuning process. To this extent, we present (1) Visual Caption Boosting, a novel framework to instill fine-grainedness in generic image captioning datasets while remaining anchored in human annotations; and (2) BagCurri, a carefully designed training curriculum that more optimally leverages the contrastive nature of the self-retrieval reward. Jointly, they enable the captioner to describe fine-grained aspects in the image while preserving faithfulness to ground-truth captions. Our approach outperforms previous work by +8.9% on SR against 99 random distractors (RD100) (Dessi et al., 2023); and +7.6% on ImageCoDe. Additionally, existing metrics to evaluate captioning systems fail to reward diversity or evaluate a model's fine-grained understanding ability. Our third contribution addresses this by proposing self-retrieval from the lens of evaluation. We introduce TrueMatch, a benchmark comprising bags of highly similar images that uses SR to assess the captioner's ability to capture subtle visual distinctions. We evaluate and compare several state-of-the-art open-source MLLMs on TrueMatch, and find that our SR approach outperforms them all by a significant margin (e.g. +4.8% - 7.1% over Cambrian) while having 1-2 orders of magnitude fewer parameters. We also outperform vanilla SR by +14.4% to +19.5%.

Abstract

A tripartite state is said to be a potential resource for secret sharing if in addition to being useful for the secret reconstruction, it imposes restrictions on the teleportation fidelity of the bipartite channels associated with three qubit states (dealer–reconstructor and dealer–assistant channels). It is important to ask the question: for a given class of states satisfying some constraint, which secret sharing resources will have the maximum possible reconstruction fidelity? Here we address this question for a pure three-qubit GHZ class of states (sometimes referred as Acin states). We are able to characterize the set of states with maximum possible reconstruction fidelity (called as Maximal Secret Reconstructible state [MSR]). Here, the constraint in characterizing the states is a fixed value of the maximum of the teleportation fidelity of both the bipartite (dealer–receivers) channels. In that spirit our result paves the way in setting the practical information transfer limit in a possible resource theoretic extension of secret sharing. Similarly for a value giving the maximum of Bell-CHSH value of both bipartite channels (dealer–reconstructor and dealer–assistant), we are able to find the maximum achievable reconstruction fidelity. Interestingly, we find that all secret shareable states satisfy Bell’s inequality in both the channels (dealer–reconstructor and dealer–assistant partitions). This brings out a new mutual exclusivity between secret shareable state and Bell’s inequality violation.

Abstract

In the Himalayan region, traditional buildings made of masonry have existed for centuries and still make up a sizable portion of the building stock. Many of these buildings have proven records of earthquake resilience. At the same time, the primary cause of fatalities from previous earthquakes is the increasing collapse of unreinforced masonry structures. In various Himalayan locations, local seismic culture has evolved over the past few centuries to improve the seismic capacity of stone constructions. These areas use wood or other materials with high tensile strength to reinforce their stone masonry. The post-earthquake reconnaissance surveys clearly demonstrate the superior performance of these timber-reinforced masonry constructions. Nevertheless, there is still a lack of scientific investigation, either through numerical modelling or laboratory-based studies, on the behaviour and mechanism of these structures. Furthermore, there are no explicit criteria for evaluating timber-reinforced masonry in the present Indian seismic code. This study examines several distinct traditional masonry building typologies found in the Himalayas, such as ‘Thathara’, ‘Kath-Kuni’ or ‘Koti-Banal’, ‘Newari’, ‘Dhajji Dewari’, ‘Ikra’ or ‘Assam-Type House’, ‘Bhatar’ or ‘Taq’, and ‘Dry-stone buildings’. For the majority of these typologies, aside from Dry-stone houses, the masonry walls have embedded horizontal timber bands or lacings that enhance box behaviour, thereby preventing premature failure. Through a thorough analysis of timber-reinforced masonry, including architectural details, earthquake-resilient & vulnerable features, and experimental and numerical investigations, the article presents a unique addition to our understanding of seismic performance and how it might best protect the Himalayan region’s traditional heritage. Additionally, the current study contributes to a better understanding of how wood elements give masonry structures greater seismic resilience. This understanding will help with several initiatives: (i) better conservation, preservation, and maintenance of traditional or heritage structures; (ii) seismic codes/standards providing details regarding the assessment of timber-reinforced structures; (iii) supporting and encouraging practitioners to design and build using techniques that have demonstrated superior performance, and (iv) as attempts to lessen the impact of building on our environment increases, provide a way to make safer structures utilizing low-carbon materials.

Abstract

Community detection is the problem of identifying natural divisions in networks. A relevant challenge in this problem is to find communities on rapidly evolving graphs. In this paper, we design efficient community detection algorithms in the batch dynamic setting. First, we present our parallel Dynamic Frontier approach. Given a batch update of edge deletions or insertions, this approach incrementally identifies an approximate set of affected vertices in the graph with minimal overhead. We apply this approach to both Louvain, a high quality, and Label Propagation Algorithm (LPA), a fast static community detection algorithm. Our approach achieves a mean speedup of 7.3× and 6.7×, when applied to Louvain and LPA respectively, compared to our parallel and optimized implementation of Δ-screening, a recently proposed state-of-the-art approach. Finally, we show how to combine Louvain and LPA with the Dynamic Frontier approach to arrive at a hybrid algorithm. This algorithm produces high-quality communities while being 14.6× faster than state-of-the-art, and identifying communities with the same quality score.

Abstract

One of the key tasks in graph learning is node classification. While Graph neural networks have been used for various applications, their adaptivity to reject option setting is not previously explored. In this paper, we propose NCwR, a novel approach to node classification in Graph Neural Networks (GNNs) with an integrated reject option, which allows the model to abstain from making predictions when uncertainty is high. We propose both cost-based and coverage-based methods for classification with abstention in node classification setting using GNNs. We perform experiments using our method on three standard citation network datasets Cora, Citeseer and Pubmed and compare with relevant baselines. We also model the Legal judgment prediction problem on ILDC dataset as a node classification problem where nodes represent legal cases and edges represent citations. We further interpret the model by analyzing the cases that the model abstains from predicting by visualizing which part of the input features influenced this decision.

Abstract

Automated segmentation of medical image volumes promises to reduce costly medical experts’ time for annotation. However, using machine learning for the task is challenging due to variations in imaging modalities and scarcity of patient data. While interactive image segmentation methods and foundational models incorporating user-provided prompts to refine segmentation masks have shown promise, they overlook crucial sequential information between the slices in 3D medical image volumes and videos, resulting in discontinuities in the segmentation results. This paper proposes a new framework that dynamically updates model parameters during inference in a test time training framework using user-provided scribbles. Our framework preserves acquired knowledge from the previous slices of the current medical volume and the training dataset via student-teacher learning. We evaluate our method on diverse CT, MRI, and microscopic cell datasets. Our framework significantly reduces user annotation time by a factor of 6.72×. Compared to other interactive segmentation methods, we reduce the time by a factor of 2.64×. Our method also outperforms prompting foundation models for segmentation by achieving a dice score of 0.9 in 3-4 interactions compared to 5-8 user interactions for the foundation model, significantly reducing annotation time for the CT and MRI volumes.

Abstract

This research utilises the capabilities of Google Earth Engine, a cloud-based computing platform, to conduct a comprehensive spatiotemporal assessment of the Coringa mangrove. Situated within the Coringa Wildlife Sanctuary in Andhra Pradesh, India, this mangrove – the country's second largest – is evaluated across various timeframes: 1999, 2002, 2007, 2013, 2017, and 2022. ML algorithms – Random Forest and Support Vector Machine with an RBF kernel – are employed. These algorithms analyze band composites derived from Landsat-7 ETM+ (1999, 2002, 2007), Landsat-8 (2013, 2017), and Sentinel-2 MSI (2022) satellite images. This analysis incorporates key spectral indices and utilises two spectral index thresholds for mangrove classification: one derived from established literature that identifies common thresholds at which mangroves typically occur (standard threshold), and the other is a customised threshold obtained from individual spectral index maps, tailored specifically to delineate mangrove areas in the study area (customized threshold). The results show that RF, particularly with the CT, outperforms all other methods, including RF with the ST and SVM with both thresholds, in terms of training and testing accuracy. These findings affirm the effectiveness of RF with the CT approach in accurately differentiating mangrove areas, emphasizing the critical role of threshold selection in enhancing the accuracy and competence of classification methods for mapping mangrove ecosystems.

Abstract

Understanding what makes a video memorable has important applications in advertising or education technology. Towards this goal, we investigate spatio-temporal attention mechanisms underlying video memorability. Different from previous works that fuse multiple features, we adopt a simple CNN+Transformer architecture that enables analysis of spatio-temporal attention while matching state-of-the-art (SoTA) performance on video memorability prediction. We compare model attention against human gaze fixations collected through a small-scale eye-tracking study where humans perform the video memory task. We uncover the following insights: (i) Quantitative saliency metrics show that our model, trained only to predict a memorability score, exhibits similar spatial attention patterns to human gaze, especially for more memorable videos. (ii) The model assigns greater importance to initial frames in a video, mimicking human attention patterns. (iii) Panoptic segmentation reveals that both (model and humans) assign a greater share of attention to things and less attention to stuff as compared to their occurrence probability.

Abstract

Existing research suggests that mountain and plain societies differ due to geographical factors and this study tests this hypothesis by examining the political dynamics of these two types of societies. We perform a quantitative analysis, followed by an exploration of possible qualitative explanations. Duverger’s Law states that single-member plurality electoral systems typically result in two-party dominance. However, India is a well-known exception in the literature due to strong regional parties as it deviates from this trend. For the quantitative analysis, central election data from the Election Commission of India from 1977 to 2014 is used to conduct a temporal analysis. Laakso and Taagepera’s Effective Number of Parties (ENP) metric is calculated by squaring each party’s share of votes or seats, summing these squares and taking the reciprocal. It is used to find the effective political parties that exist in a district considering both their number and vote share. According to Duverger’s Law, the ENP should ideally converge to 2 over time. This analysis reveals that in plains the ENP values are increasing over time (suggesting divergence) whereas mountain regions are gradually converging towards a two-party system. We conduct a one-way ANOVA for each election by grouping the ENP values for mountain and plain districts separately. A statistically significant difference between the ENP values of mountain and plain districts across all elections. For qualitative analysis, James Scott’s concept of Zomia along with different ideas of Zomia presented by Schendel, Schneiderman are discussed and how they might offer an explanation for the observation. Ultimately, the study sheds light on the socio-political distinctions between mountainous and plain regions in India, supporting historical and sociological theories that suggest mountain societies preserve unique political traits.