Search

Perspective distortion (PD) leads to substantial alterations in the shape, size, orientation, angles, and spatial relationships of visual elements in images. Accurately determining camera intrinsic and extrinsic parameters is challenging, making it hard to synthesize perspective distortion effectively. The current distortion correction methods involve removing distortion and learning vision tasks, thus making it a multi-step process, often compromising performance. Recent work leverages the M\"obius transform for mitigating perspective distortions (MPD) to synthesize perspective distortions without estimating camera parameters. M\"obius transform requires tuning multiple interdependent and interrelated parameters and involving complex arithmetic operations, leading to substantial computational complexity. To address these challenges, we propose Log Conformal Maps (LCM), a method leveraging the logarithmic function to approximate perspective distortions with fewer parameters and reduced computational complexity. We provide a detailed foundation complemented with experiments to demonstrate that LCM with fewer parameters approximates the MPD. We show that LCM integrates well with supervised and self-supervised representation learning, outperform standard models, and matches the state-of-the-art performance in mitigating perspective distortion over multiple benchmarks, namely Imagenet-PD, Imagenet-E, and Imagenet-X. Further LCM demonstrate seamless integration with person re-identification and improved the performance. Source code is made publicly available at https://github.com/meenakshi23/Log-Conformal-Maps., Comment: Accepted to Asian Conference on Computer Vision (ACCV2024)

The chirality-induced spin selectivity (CISS) effect has garnered significant interest in the field of molecular spintronics due to its potential for creating spin-polarized electrons without the need for a magnet. Recent studies devoted to CISS effects in various chiral materials demonstrate exciting prospects for spintronics, chiral recognition, and quantum information applications. Several experimental studies have confirmed the applicability of chiral molecules towards spin-filtering properties, influencing spin-polarized electron transport, and photoemission. Researchers aim to predict CISS phenomena and apply this concept to practical applications by compiling experimental results and enhancing understanding of the CISS effect. To expand the possibilities of spin manipulation and create new opportunities for spin-based technologies, researchers are diligently exploring different chiral organic and inorganic materials for probing the CISS effect. This ongoing research holds promise for developing novel spin-based technologies and advancing the understanding of the intricate relationship between chirality and electron spin. This review showcases the remarkable CISS effect and its impact on spintronics, as well as its relevance in various other scientific areas., Comment: 29 pages, 20 figures

Understanding electrical characteristics and corresponding transport models at single molecular junctions is crucial. There have been many reports on organic compounds-based single molecular junctions. However, organometallic compounds-based single molecular junctions have not been explored yet. Re(I) organometallic compounds are known to exhibit intriguing photophysical properties scrutinized for photocatalysis, and light-emitting diodes but have not been explored in molecular electronics. In this work, a theoretical model study on the I-V characteristics of two Re(I)-carbonyl complexes bearing Re-P and Re-N-N linkage has been meticulously chosen. Tunneling and hopping transport in Au/Re(I)-complex/Au single-molecule junctions are governed by Landauer-formalism and the Marcus theory, respectively. Interestingly, variations in molecular architecture culminate in notable variations in junction functionality and mechanism of charge conduction. Physical parameters influencing the device characteristics such as dipole moment, molecule-electrode coupling strength, voltage division factor, and temperature have been extensively studied which offers modulation of the characteristics and device design. The dominant hopping current in Re complex bearing bipyridine linkage was found to be responsible for the observed asymmetric electrical (I-V) behavior. Our work paves the way for constructing various organometallic compounds-based molecular junctions to understand electronic functions and the underlying transport mechanisms., Comment: 17 pages, 8 figures

The emergence of cognition requires a framework that bridges evolutionary principles with neurocomputational mechanisms. This paper introduces the novel "thoughtseed" framework, proposing that cognition arises from the dynamic interaction of self-organizing units of embodied knowledge called "thoughtseeds" within the Global Workspace of consciousness. Leveraging foundational concepts from evolutionary theory, neuronal packets, and free energy principle, we propose a hierarchical model of cognitive states, comprising Neuronal Packet Domains (NPDs), Knowledge Domains (KDs), the thoughtseed network, and meta-cognition. This hierarchical interplay, mediated by nested Markov blankets and reciprocal message passing, facilitates the emergence of thoughtseeds as coherent patterns of activity that guide perception, action, and learning. Thoughtseeds, posited as fundamental units of thought, compete for dominance within the Global Workspace, with the dominant thoughtseed shaping conscious experience and guiding behavior. We present a mathematical framework grounded in active inference and dynamical systems theory to model thoughtseed dynamics and their contribution to the unitary nature of consciousness. The thoughtseed framework offers a promising step towards a novel, biologically-grounded model for understanding the organizing principles and emergence of embodied cognition, offering a unified account of cognitive phenomena, with potential applications in understanding consciousness, attention, and decision-making., Comment: 2nd version. Reduced in size from 88 pages to 48 pages, to focus on the core framework. Items removed: Detailed discussions on Evolutionary Biology, contemplative traditions and computational theories of Mind. Replaced Inner Screen Model with Global Workspace Theory. Mathematical equations have been streamlined and is better organized. preprint arXiv:2408.15982

The challenge of Out-Of-Distribution (OOD) robustness remains a critical hurdle towards deploying deep vision models. Vision-Language Models (VLMs) have recently achieved groundbreaking results. VLM-based open-vocabulary object detection extends the capabilities of traditional object detection frameworks, enabling the recognition and classification of objects beyond predefined categories. Investigating OOD robustness in recent open-vocabulary object detection is essential to increase the trustworthiness of these models. This study presents a comprehensive robustness evaluation of the zero-shot capabilities of three recent open-vocabulary (OV) foundation object detection models: OWL-ViT, YOLO World, and Grounding DINO. Experiments carried out on the robustness benchmarks COCO-O, COCO-DC, and COCO-C encompassing distribution shifts due to information loss, corruption, adversarial attacks, and geometrical deformation, highlighting the challenges of the model's robustness to foster the research for achieving robustness. Project page: https://prakashchhipa.github.io/projects/ovod_robustness, Comment: Accepted at 2024 European Conference on Computer Vision Workshops (ECCVW). Project page - https://prakashchhipa.github.io/projects/ovod_robustness

Perspective distortion (PD) causes unprecedented changes in shape, size, orientation, angles, and other spatial relationships of visual concepts in images. Precisely estimating camera intrinsic and extrinsic parameters is a challenging task that prevents synthesizing perspective distortion. Non-availability of dedicated training data poses a critical barrier to developing robust computer vision methods. Additionally, distortion correction methods make other computer vision tasks a multi-step approach and lack performance. In this work, we propose mitigating perspective distortion (MPD) by employing a fine-grained parameter control on a specific family of M\"obius transform to model real-world distortion without estimating camera intrinsic and extrinsic parameters and without the need for actual distorted data. Also, we present a dedicated perspectively distorted benchmark dataset, ImageNet-PD, to benchmark the robustness of deep learning models against this new dataset. The proposed method outperforms existing benchmarks, ImageNet-E and ImageNet-X. Additionally, it significantly improves performance on ImageNet-PD while consistently performing on standard data distribution. Notably, our method shows improved performance on three PD-affected real-world applications crowd counting, fisheye image recognition, and person re-identification and one PD-affected challenging CV task: object detection. The source code, dataset, and models are available on the project webpage at https://prakashchhipa.github.io/projects/mpd., Comment: Accepted to European Conference on Computer Vision(ECCV2024). project page- https://prakashchhipa.github.io/projects/mpd

Medical question answer (QA) assistants respond to lay users' health-related queries by synthesizing information from multiple sources using natural language processing and related techniques. They can serve as vital tools to alleviate issues of misinformation, information overload, and complexity of medical language, thus addressing lay users' information needs while reducing the burden on healthcare professionals. QA systems, the engines of such assistants, have typically used either language models (LMs) or knowledge graphs (KG), though the approaches could be complementary. LM-based QA systems excel at understanding complex questions and providing well-formed answers, but are prone to factual mistakes. KG-based QA systems, which represent facts well, are mostly limited to answering short-answer questions with pre-created templates. While a few studies have jointly used LM and KG approaches for text-based QA, this was done to answer multiple-choice questions. Extant QA systems also have limitations in terms of automation and performance. We address these challenges by designing a novel, automated disease QA system which effectively utilizes both LM and KG techniques through a joint-reasoning approach to answer disease-related questions appropriate for lay users. Our evaluation of the system using a range of quality metrics demonstrates its efficacy over benchmark systems, including the popular ChatGPT., Comment: 36 pages, 6 figures

Fitting's Heyting-valued logic and Heyting-valued modal logic have already been studied from an algebraic viewpoint. In addition to algebraic axiomatizations with the completeness of Fitting's Heyting-valued logic and Heyting-valued modal logic, both topological and coalgebraic dualities have also been developed for algebras of Fitting's Heyting-valued modal logic. Bitopological methods have recently been employed to investigate duality for Fitting's Heyting-valued logic. However, the concepts of bitopology and biVietoris coalgebras are conspicuously absent from the development of dualities for Fitting's many-valued modal logic. With this study, we try to bridge that gap. We develop a bitopological duality for algebras of Fitting's Heyting-valued modal logic. We construct a bi-Vietoris functor on the category $PBS_{\mathcal{L}}$ of $\mathcal{L}$-valued ($\mathcal{L}$ is a Heyting algebra) pairwise Boolean spaces. Finally, we obtain a dual equivalence between categories of biVietoris coalgebras and algebras of Fitting's Heyting-valued modal logic. As a result, we conclude that Fitting's many-valued modal logic is sound and complete with respect to the coalgebras of a biVietoris functor. We discuss the application of this coalgebraic approach to bitopological duality.

Electrical current rectification is an interesting electronic feature, popularly known as a diode. Achieving a high rectification ratio in a molecular junction has been a long-standing goal in molecular electronics. The present work describes mimicking electrical current rectification with pi-stacked rhenium(I) compound sandwiched between two electrical contacts. Among the two mononuclear rhenium compounds studied here, [Re(CO)4(PPh3){(N)-saccharinate}] (1) and [Re(CO)3(phen){(N)-saccharinate}] (2), the latter show strong pi-pi interactions-induced high rectification ratio of ~ 4000 at 2.0 V at room temperature. Alternating current (AC)-based electrical measurements ensuring AC to DC electrical signal conversion at a frequency f of 1 KHz showing 2 can act as an excellent half-wave rectifier. Asymmetric charge injection barrier height at the electrode/Re(I) interfaces of the devices with a stacking configuration of p++-Si/Re compound31nm(2)/ITO originates the flow of electrical current unidirectionally. The charge transport mechanism governed by thermally activated hopping phenomena, and charge carrier propagation is explained through an energy profile considering the Fermi levels of two electrodes, and the energy of frontier molecular orbitals, HOMO, and LUMO, confirming rectification is of a molecular origin. The present work paves the way to combine different organometallic compounds as circuit elements in nanoelectronic devices to achieve numerous exciting electronic features., Comment: 16 pages, 5 figures

This article contributes to the new summation of Sz\'asz operators with the help of Appell polynomials of class $A^{2}$. We verified Bohman-Korovkin's theorem and prove the convergence results like Lipschitz-type space, Voronvaskaja-type asymptotic formula, and modulus of continuity using the given operators. Furthermore, we have shown the weighted modulus of continuity and the derivative of bounded variation.

Self-supervised learning in computer vision aims to leverage the inherent structure and relationships within data to learn meaningful representations without explicit human annotation, enabling a holistic understanding of visual scenes. Robustness in vision machine learning ensures reliable and consistent performance, enhancing generalization, adaptability, and resistance to noise, variations, and adversarial attacks. Self-supervised paradigms, namely contrastive learning, knowledge distillation, mutual information maximization, and clustering, have been considered to have shown advances in invariant learning representations. This work investigates the robustness of learned representations of self-supervised learning approaches focusing on distribution shifts and image corruptions in computer vision. Detailed experiments have been conducted to study the robustness of self-supervised learning methods on distribution shifts and image corruptions. The empirical analysis demonstrates a clear relationship between the performance of learned representations within self-supervised paradigms and the severity of distribution shifts and corruptions. Notably, higher levels of shifts and corruptions are found to significantly diminish the robustness of the learned representations. These findings highlight the critical impact of distribution shifts and image corruptions on the performance and resilience of self-supervised learning methods, emphasizing the need for effective strategies to mitigate their adverse effects. The study strongly advocates for future research in the field of self-supervised representation learning to prioritize the key aspects of safety and robustness in order to ensure practical applicability. The source code and results are available on GitHub., Comment: Accepted at 2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW). Corresponding author - prakash.chandra.chhipa@ltu.se

Bio-spinterfaces present numerous opportunities to study spintronics across the biomolecules attached to (ferro)magnetic electrodes. While it offers various exciting phenomena to investigate, it's simultaneously challenging to make stable bio-spinterfaces, as biomolecules are sensitive to many factors that it encounters during thin-film growth to device fabrication. The chirality-induced spin-selectivity (CISS) effect is an exciting discovery demonstrating an understanding that a specific electron's spin (either UP or DOWN) passes through a chiral molecule. The present work utilizes Ustilago maydis Rvb2 protein, an ATP-dependent DNA helicase (also known as Reptin) for the fabrication of bio-spintronic devices to investigate spin-selective electron transport through protein. Ferromagnetic materials are well-known for showing spin-polarization, which many chiral and biomolecules can mimic. We report spin-selective electron transmission through Rvb2 that exhibits 30% spin polarization at a low bias (+ 0.5 V) in a device configuration, Ni/Rvb2 protein/ITO measured under two different magnetic configurations. Our findings demonstrate that biomolecules can be put in circuit components without any expensive vacuum deposition for the top contact. Thus, it holds a remarkable potential to advance spin-selective electron transport in other biomolecules such as proteins, and peptides for biomedical applications., Comment: 14 pages, 5 figures

This work presents a novel label-efficient selfsupervised representation learning-based approach for classifying diabetic retinopathy (DR) images in cross-domain settings. Most of the existing DR image classification methods are based on supervised learning which requires a lot of time-consuming and expensive medical domain experts-annotated data for training. The proposed approach uses the prior learning from the source DR image dataset to classify images drawn from the target datasets. The image representations learned from the unlabeled source domain dataset through contrastive learning are used to classify DR images from the target domain dataset. Moreover, the proposed approach requires a few labeled images to perform successfully on DR image classification tasks in cross-domain settings. The proposed work experiments with four publicly available datasets: EyePACS, APTOS 2019, MESSIDOR-I, and Fundus Images for self-supervised representation learning-based DR image classification in cross-domain settings. The proposed method achieves state-of-the-art results on binary and multiclassification of DR images, even in cross-domain settings. The proposed method outperforms the existing DR image binary and multi-class classification methods proposed in the literature. The proposed method is also validated qualitatively using class activation maps, revealing that the method can learn explainable image representations. The source code and trained models are published on GitHub., Comment: Accepted to International Joint Conference on Neural Networks (IJCNN) 2023

This work presents a novel domain adaption paradigm for studying contrastive self-supervised representation learning and knowledge transfer using remote sensing satellite data. Major state-of-the-art remote sensing visual domain efforts primarily focus on fully supervised learning approaches that rely entirely on human annotations. On the other hand, human annotations in remote sensing satellite imagery are always subject to limited quantity due to high costs and domain expertise, making transfer learning a viable alternative. The proposed approach investigates the knowledge transfer of selfsupervised representations across the distinct source and target data distributions in depth in the remote sensing data domain. In this arrangement, self-supervised contrastive learning-based pretraining is performed on the source dataset, and downstream tasks are performed on the target datasets in a round-robin fashion. Experiments are conducted on three publicly available datasets, UC Merced Landuse (UCMD), SIRI-WHU, and MLRSNet, for different downstream classification tasks versus label efficiency. In self-supervised knowledge transfer, the proposed approach achieves state-of-the-art performance with label efficiency labels and outperforms a fully supervised setting. A more in-depth qualitative examination reveals consistent evidence for explainable representation learning. The source code and trained models are published on GitHub., Comment: Accepted in International Joint Conference on Neural Networks (IJCNN) 2023. First three authors shares equal contribution!

Nanoscale molecular junctions are celebrated nanoelectronic devices for mimicking several electronic functions including rectifiers, sensors, wires, switches, transistors, and memory but capacitive behavior is nearly unexplored. Capacitors are crucial energy storage devices that store energy in the form of electrical charges. A capacitor utilizes two electrical conductors separated by a dielectric material. However, many oxides-based dielectrics are well-studied for integrating capacitors, however, capacitors comprised of thin-film molecular layers are not well-studied. The present work describes electrochemically grafted thin films of benzimidazole (BENZ) grown on patterned ITO electrodes on which a 50 nm Al is deposited to fabricate large-scale (500 x 500 micron2) molecular junctions. The nitrogen and sulfur-containing molecular junctions, ITO/BENZ/Al act as a parallel-plate capacitor with a maximum capacitance of ~59.6 to 4.79 microFcm-2. The present system can be an excellent platform for molecular charge storage for future energy applications., Comment: 12 Pages, 5 Figures

The present era has seen tremendous demands for low-cost electrochromic materials for visible-region multicolor display technology, paper-based, flexible, and wearable electronic devices, smart windows, and optoelectronic applications. Towards this goal, we report large-scale polyelectrochromic devices fabricated on rigid to flexible ITO substrates comprising novel anthracene containing viologen, (1,1'-bis(anthracen-9-ylmethyl)-[4,4'-bipyridine]-1,1'-diium bromide, abbreviated as AnV2+), and polythiophene (P3HT). Inter-estingly, the devices show three states of reversible visible color in response to the applied bias, sub-second to second switching time (0.7 s/1.6 s), and high coloration efficiency (484 cm2/C), longer cycling stability up to 3000 s (103 switching cycles). Thanks to the anthracenes moieties introduced to viologen that inhibit formation of undesired dimer of cation radicals formed in response to the applied bias, other-wise it would hamper the devices reconfiguration. The devices are fully characterized, and electrochromic performances are ensured by bias-dependent UV-Vis, and Raman spectroscopy. The fabricated electro-chromic devices are tested with the commercially available low-cost cells to perform, which is highly de-sired for practical applications. The computational study facilitates the understanding of experimental re-sults. The alternating current (AC)-based electrical impedance spectroscopy reveals that P3HT facilitates reducing charge transfer resistance of the devices. Our work shows CMOS compatibility and one of the best-performing devices that could pave the way for developing cost-effective flexible, and wearable electrochromic devices., Comment: 13 Pages, 7 Figures

Due to the shorter channel length allowing faster ion/charge movement, nanoscale molecular thin films can be attractive electronic components for next-generation high-performing energy storage devices. However, controlling chemical functionalization and achieving stable electrode-molecule interfaces at the nanoscale via covalent functionalization for low-voltage operational, ultrafast charging/discharging remains a challenge. Herein, we present a simple, controllable, scalable, low-cost, and versatile electrochemical grafting approach to modulate chemical and electronic properties of graphite rods (GRs) that are extracted from low-cost EVEREADY cells (1.5 US $ for 10 cells of 1.5 V). On the ANT-modified GR (ANT/GR), the total capacitance unveils 350-fold enhancement as compared to an unmodified GR tested with 0.1 M H2SO4 electrolyte ensured by both potentiostatic and galvanostatic measurements. Such enhancement in capacitance is attributed to the contribution from the electrical double layer and Faradaic charge transfer. Due to higher conductivity, anthracene molecular layers possess more azo groups (-N=N-) over pyrene, and naphthalene molecular films during the electrochemical grafting, which is key to capacitance improvements. The ultra-low-loading nanofilms expose high surface area leading to extremely high energy density. The nanoscale molecular films (~ 23 nm thickness) show exceptional galvanostatic charge-discharge cycling stability (10,000) that operates at low potential. Electrochemical impedance spectroscopy was performed along with the DC measurements to unravel in-depth charge storage performances. Electrochemically grafted molecular films on GR show excellent balance in capacitance and electrical conductivity, high diffusion coefficient toward ferrocene, and can easily be synthesized in good yield on rigid to flexible electrodes., Comment: 18 pages, 6 Figures

This work investigates the unexplored usability of self-supervised representation learning in the direction of functional knowledge transfer. In this work, functional knowledge transfer is achieved by joint optimization of self-supervised learning pseudo task and supervised learning task, improving supervised learning task performance. Recent progress in self-supervised learning uses a large volume of data, which becomes a constraint for its applications on small-scale datasets. This work shares a simple yet effective joint training framework that reinforces human-supervised task learning by learning self-supervised representations just-in-time and vice versa. Experiments on three public datasets from different visual domains, Intel Image, CIFAR, and APTOS, reveal a consistent track of performance improvements on classification tasks during joint optimization. Qualitative analysis also supports the robustness of learnt representations. Source code and trained models are available on GitHub., Comment: Accepted at IEEE International Conference on Image Processing (ICIP 2023)