arXiv subjects

Raksha Sharma

Publications and source records attributed to Raksha Sharma.

8 recordsLinked to original sources

arXiv2026

NOPE-HYPE: A Structured Simulation Workflow for Robust Speech-to-Text Across Diverse Acoustic Environments

Robust speech-to-text translation systems should perform reliably across diverse acoustic conditions, yet practical pipelines lack controllable tools for systematic environment exploration. Large speech models remain sensitive to unseen acoustic conditions, as training data rarely cover the full range of real environments.We present NOPEHYPE, a structured training workflow that combines a controllable environment simulator, coverage-optimal environment reduction on Power Spectral Density (PSD) templates, and a small, interpretable hyperparameter search over simulator knobs. We show that simulator-generated noise achieves performance comparable to balanced realnoise training across Whisper and SeamlessM4T models, provide principled environment prototype sets, and identify practical default simulator configurations from a structured 27-run hyperparameter sweep.

cs.SD↗

arXiv2025

A Novel Lightweight Transformer with Edge-Aware Fusion for Remote Sensing Image Captioning

Transformer-based models have achieved strong performance in remote sensing image captioning by capturing long-range dependencies and contextual information. However, their practical deployment is hindered by high computational costs, especially in multi-modal frameworks that employ separate transformer-based encoders and decoders. In addition, existing remote sensing image captioning models primarily focus on high-level semantic extraction while often overlooking fine-grained structural features such as edges, contours, and object boundaries. To address these challenges, a lightweight transformer architecture is proposed by reducing the dimensionality of the encoder layers and employing a distilled version of GPT-2 as the decoder. A knowledge distillation strategy is used to transfer knowledge from a more complex teacher model to improve the performance of the lightweight network. Furthermore, an edge-aware enhancement strategy is incorporated to enhance image representation and object boundary understanding, enabling the model to capture fine-grained spatial details in remote sensing images. Experimental results demonstrate that the proposed approach significantly improves caption quality compared to state-of-the-art methods.

cs.CV↗

arXiv2025

Good Representation, Better Explanation: Role of Convolutional Neural Networks in Transformer-Based Remote Sensing Image Captioning

Remote Sensing Image Captioning (RSIC) is the process of generating meaningful descriptions from remote sensing images. Recently, it has gained significant attention, with encoder-decoder models serving as the backbone for generating meaningful captions. The encoder extracts essential visual features from the input image, transforming them into a compact representation, while the decoder utilizes this representation to generate coherent textual descriptions. Recently, transformer-based models have gained significant popularity due to their ability to capture long-range dependencies and contextual information. The decoder has been well explored for text generation, whereas the encoder remains relatively unexplored. However, optimizing the encoder is crucial as it directly influences the richness of extracted features, which in turn affects the quality of generated captions. To address this gap, we systematically evaluate twelve different convolutional neural network (CNN) architectures within a transformer-based encoder framework to assess their effectiveness in RSIC. The evaluation consists of two stages: first, a numerical analysis categorizes CNNs into different clusters, based on their performance. The best performing CNNs are then subjected to human evaluation from a human-centric perspective by a human annotator. Additionally, we analyze the impact of different search strategies, namely greedy search and beam search, to ensure the best caption. The results highlight the critical role of encoder selection in improving captioning performance, demonstrating that specific CNN architectures significantly enhance the quality of generated descriptions for remote sensing images. By providing a detailed comparison of multiple encoders, this study offers valuable insights to guide advances in transformer-based image captioning models.

cs.CV↗

arXiv2025

MsEdF: A Multi-stream Encoder-decoder Framework for Remote Sensing Image Captioning

Remote sensing images contain complex spatial patterns and semantic structures, which makes the captioning model difficult to accurately describe. Encoder-decoder architectures have become the widely used approach for RSIC by translating visual content into descriptive text. However, many existing methods rely on a single-stream architecture, which weakens the model to accurately describe the image. Such single-stream architectures typically struggle to extract diverse spatial features or capture complex semantic relationships, limiting their effectiveness in scenes with high intraclass similarity or contextual ambiguity. In this work, we propose a novel Multi-stream Encoder-decoder Framework (MsEdF) which improves the performance of RSIC by optimizing both the spatial representation and language generation of encoder-decoder architecture. The encoder fuses information from two complementary image encoders, thereby promoting feature diversity through the integration of multiscale and structurally distinct cues. To improve the capture of context-aware descriptions, we refine the input sequence's semantic modeling on the decoder side using a stacked GRU architecture with an element-wise aggregation scheme. Experiments on three benchmark RSIC datasets show that MsEdF outperforms several baseline models.

cs.CV↗

arXiv2024

A TextGCN-Based Decoding Approach for Improving Remote Sensing Image Captioning

Remote sensing images are highly valued for their ability to address complex real-world issues such as risk management, security, and meteorology. However, manually captioning these images is challenging and requires specialized knowledge across various domains. This letter presents an approach for automatically describing (captioning) remote sensing images. We propose a novel encoder-decoder setup that deploys a Text Graph Convolutional Network (TextGCN) and multi-layer LSTMs. The embeddings generated by TextGCN enhance the decoder's understanding by capturing the semantic relationships among words at both the sentence and corpus levels. Furthermore, we advance our approach with a comparison-based beam search method to ensure fairness in the search strategy for generating the final caption. We present an extensive evaluation of our approach against various other state-of-the-art encoder-decoder frameworks. We evaluated our method across three datasets using seven metrics: BLEU-1 to BLEU-4, METEOR, ROUGE-L, and CIDEr. The results demonstrate that our approach significantly outperforms other state-of-the-art encoder-decoder methods.

cs.LG↗

arXiv2022

Leveraging Dependency Grammar for Fine-Grained Offensive Language Detection using Graph Convolutional Networks

The last few years have witnessed an exponential rise in the propagation of offensive text on social media. Identification of this text with high precision is crucial for the well-being of society. Most of the existing approaches tend to give high toxicity scores to innocuous statements (e.g., "I am a gay man"). These false positives result from over-generalization on the training data where specific terms in the statement may have been used in a pejorative sense (e.g., "gay"). Emphasis on such words alone can lead to discrimination against the classes these systems are designed to protect. In this paper, we address the problem of offensive language detection on Twitter, while also detecting the type and the target of the offence. We propose a novel approach called SyLSTM, which integrates syntactic features in the form of the dependency parse tree of a sentence and semantic features in the form of word embeddings into a deep learning architecture using a Graph Convolutional Network. Results show that the proposed approach significantly outperforms the state-of-the-art BERT model with orders of magnitude fewer number of parameters.

cs.CL↗

arXiv2004

Magnetic properties of polypyrrole - coated iron oxide nanoparticles

Iron oxide nanoparticles were prepared by sol -gel process. Insitu polymerization of pyrrole monomer in the presence of oxygen in iron oxide ethanol suspension resulted in a iron oxide - polypyrrole nanocomposite. The structure and magnetic properties were investigated for varying pyrrole concentrations. The presence of the gamma - iron oxide phase and polypyrrole were confirmed by XRD and FTIR respectively. Agglomeration was found to be comparatively much reduced for the coated samples, as shown by TEM. AC susceptibility measurements confirmed the superparamagnetic behaviour. Numerical simulations performed for an interacting model system are performed to estimate the anisotropy and compare favourably with experimental results.

cond-mat.mtrl-sci↗

arXiv2004

Composition dependent magnetic properties of iron oxide - polyaniline nanoclusters

Gamma - Iron Oxide prepared by sol -gel process was used to produce nanocomposites with polyaniline of varying aniline concentrations. TEM shows the presence of chain like structure for lower polyaniline concentration. The room temperature hysteresis curves show finite coercivity of 160 Oe for all the composites while the saturation magnetization was found to decrease with increasing polymer content. ZFC - FC magnetisation measurements indicate high blocking temperatures. It is believed that this indicates a strongly interacting system, which is also shown by our TEM results. Monte Carlo simulations performed on a random anisotropy model with dipolar and exchange inteactions match well with experimental results.

cond-mat.mtrl-sci↗