activity
20242026
collaborators

5 papers

cs.CV2026

JSSFF: A Joint Structural-Semantic Fusion Framework for Remote Sensing Image Captioning

Swadhin Das, Vivek Yadav

The encoder-decoder framework has become widely popular nowadays. In this model, the encoder extracts informative visual features from an input image, and the decoder employs a seq…

cs.CV2025

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

Swadhin Das, Raksha Sharma

Remote sensing images contain complex spatial patterns and semantic structures, which makes the captioning model difficult to accurately describe. Encoder-decoder architectures hav…

cs.CV2025

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

Swadhin Das, Saarthak Gupta, Kamal Kumar +1

Remote Sensing Image Captioning (RSIC) is the process of generating meaningful descriptions from remote sensing images. Recently, it has gained significant attention, with encoder-…

cs.CV2025

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

Swadhin Das, Divyansh Mundra, Priyanshu Dayal +1

Transformer-based models have achieved strong performance in remote sensing image captioning by capturing long-range dependencies and contextual information. However, their practic…

cs.LG2024

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

Swadhin Das, Raksha Sharma

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 thes…