Deepu Rajan
YOU?
Author Swipe
View article: Fintech Disruption of Traditional Banking Services: A Comprehensive Analysis of Digital Transformation in the Financial Sector
Fintech Disruption of Traditional Banking Services: A Comprehensive Analysis of Digital Transformation in the Financial Sector Open
The financial services industry is experiencing unprecedented transformation as Financial Technology (Fintech) companies challenge traditional banking models through innovative digital solutions. This research paper examines the multifacet…
View article: IMoRe: Implicit Program-Guided Reasoning for Human Motion Q&A
IMoRe: Implicit Program-Guided Reasoning for Human Motion Q&A Open
Existing human motion Q\&A methods rely on explicit program execution, where the requirement for manually defined functional modules may limit the scalability and adaptability. To overcome this, we propose an implicit program-guided motion…
View article: Enhancing Wireless Networks for IoT with Large Vision Models: Foundations and Applications
Enhancing Wireless Networks for IoT with Large Vision Models: Foundations and Applications Open
Large vision models (LVMs) have emerged as a foundational paradigm in visual intelligence, achieving state-of-the-art performance across diverse visual tasks. Recent advances in LVMs have facilitated their integration into Internet of Thin…
View article: Large Language Models Meet Contrastive Learning: Zero-Shot Emotion Recognition Across Languages
Large Language Models Meet Contrastive Learning: Zero-Shot Emotion Recognition Across Languages Open
Multilingual speech emotion recognition aims to estimate a speaker's emotional state using a contactless method across different languages. However, variability in voice characteristics and linguistic diversity poses significant challenges…
View article: Enhancing Modality Representation and Alignment for Multimodal Cold-start Active Learning
Enhancing Modality Representation and Alignment for Multimodal Cold-start Active Learning Open
Training multimodal models requires a large amount of labeled data. Active\nlearning (AL) aim to reduce labeling costs. Most AL methods employ warm-start\napproaches, which rely on sufficient labeled data to train a well-calibrated\nmodel …
View article: Cross-Modality and Within-Modality Regularization for Audio-Visual DeepFake Detection
Cross-Modality and Within-Modality Regularization for Audio-Visual DeepFake Detection Open
Audio-visual deepfake detection scrutinizes manipulations in public video using complementary multimodal cues. Current methods, which train on fused multimodal data for multimodal targets face challenges due to uncertainties and inconsiste…
View article: Towards Balanced Active Learning for Multimodal Classification
Towards Balanced Active Learning for Multimodal Classification Open
Training multimodal networks requires a vast amount of data due to their\nlarger parameter space compared to unimodal networks. Active learning is a\nwidely used technique for reducing data annotation costs by selecting only\nthose samples…
View article: A Unified Framework for Guiding Generative AI with Wireless Perception in Resource Constrained Mobile Edge Networks
A Unified Framework for Guiding Generative AI with Wireless Perception in Resource Constrained Mobile Edge Networks Open
With the significant advancements in artificial intelligence (AI) technologies and powerful computational capabilities, generative AI (GAI) has become a pivotal digital content generation technique for offering superior digital services. H…
View article: UniS-MMC: Multimodal Classification via Unimodality-supervised Multimodal Contrastive Learning
UniS-MMC: Multimodal Classification via Unimodality-supervised Multimodal Contrastive Learning Open
Multimodal learning aims to imitate human beings to acquire complementary information from multiple modalities for various downstream tasks. However, traditional aggregation-based multimodal fusion methods ignore the inter-modality relatio…
View article: UniS-MMC: Multimodal Classification via Unimodality-supervised Multimodal Contrastive Learning
UniS-MMC: Multimodal Classification via Unimodality-supervised Multimodal Contrastive Learning Open
Multimodal learning aims to imitate human beings to acquire complementary information from multiple modalities for various downstream tasks. However, traditional aggregation-based multimodal fusion methods ignore the inter-modality relatio…
View article: Trust based anonymous intrusion detection for cloud assisted WSN-IOT
Trust based anonymous intrusion detection for cloud assisted WSN-IOT Open
A network system called Wireless Sensor Network is made up of wireless sensor node devices that are spread at random (WSN). WSNs are a critical paradigm for the Internet of Things' evolution (IoT). Strong security measures must be done to …
View article: Speech Emotion Recognition with Co-Attention based Multi-level Acoustic Information
Speech Emotion Recognition with Co-Attention based Multi-level Acoustic Information Open
Speech Emotion Recognition (SER) aims to help the machine to understand human's subjective emotion from only audio information. However, extracting and utilizing comprehensive in-depth audio information is still a challenging task. In this…
View article: Long and Strong Security using Reputation and ECC for Cloud Assisted Wireless Sensor Networks
Long and Strong Security using Reputation and ECC for Cloud Assisted Wireless Sensor Networks Open
Wireless sensor network plays a significant role in the construction of smart cities, and the social network includes the Internet of Things, etc. In general, networks are most vulnerable of all the wireless devices due to the massive dama…
View article: Are Object Detection Assessment Criteria Ready for Maritime Computer Vision?
Are Object Detection Assessment Criteria Ready for Maritime Computer Vision? Open
Maritime vessels equipped with visible and infrared cameras can complement other conventional sensors for object detection. However, application of computer vision techniques in maritime domain received attention only recently. The maritim…
View article: Free-Head Appearance-Based Eye Gaze Estimation on Mobile Devices
Free-Head Appearance-Based Eye Gaze Estimation on Mobile Devices Open
Eye gaze tracking plays an important role in human-computer interaction applications. In recent years, many research have been performed to explore gaze estimation methods to handle free-head movement, most of which focused on gaze directi…
View article: Are object detection assessment criteria ready for maritime computer vision?
Are object detection assessment criteria ready for maritime computer vision? Open
Maritime vessels equipped with visible and infrared cameras can complement other conventional sensors for object detection. However, application of computer vision techniques in maritime domain received attention only recently. The maritim…
View article: A learning-based approach for automatic image and video colorization
A learning-based approach for automatic image and video colorization Open
In this paper, we present a color transfer algorithm to colorize a broad range of gray images without any user intervention. The algorithm uses a machine learning-based approach to automatically colorize grayscale images. The algorithm use…
View article: MSCM-LiFe: Multi-scale cross modal linear feature for horizon detection in maritime images
MSCM-LiFe: Multi-scale cross modal linear feature for horizon detection in maritime images Open
This paper proposes a new method for horizon detection called the multi-scale cross modal linear feature. This method integrates three different concepts related to the presence of horizon in maritime images to increase the accuracy of hor…
View article: Video Processing from Electro-optical Sensors for Object Detection and Tracking in Maritime Environment: A Survey
Video Processing from Electro-optical Sensors for Object Detection and Tracking in Maritime Environment: A Survey Open
We present a survey on maritime object detection and tracking approaches, which are essential for the development of a navigational system for autonomous ships. The electro-optical (EO) sensor considered here is a video camera that operate…
View article: Weakly Supervised Top-down Salient Object Detection.
Weakly Supervised Top-down Salient Object Detection. Open
Top-down saliency models produce a probability map that peaks at target
locations specified by a task/goal such as object detection. They are usually
trained in a fully supervised setting involving pixel-level annotations of
objects. We pr…
View article: Challenges in video based object detection in maritime scenario using computer vision
Challenges in video based object detection in maritime scenario using computer vision Open
This paper discusses the technical challenges in maritime image processing and machine vision problems for video streams generated by cameras. Even well documented problems of horizon detection and registration of frames in a video are ver…