# Beyond RNNs: Benchmarking Attention-Based Image Captioning Models

Source: [Beyond RNNs: Benchmarking Attention-Based Image Captioning Models](<https://www.sota2.com/research/paper/68fa77291e209131cea717e7>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:48:55.617Z

Authors: Hemanth Teja Yanambakkam, Rahul Chinthala

Published: 2025-02-26T01:05:18.000Z

## Abstract

Image captioning is a challenging task at the intersection of computer vision and natural language processing, requiring models to generate meaningful textual descriptions of images. Traditional approaches rely on recurrent neural networks (RNNs), but recent advancements in attention mechanisms have demonstrated significant improvements. This study benchmarks the performance of attention-based image captioning models against RNN-based approaches using the MS-COCO dataset. We evaluate the effectiveness of Bahdanau attention in enhancing the alignment between image features and generated captions. The models are assessed using natural language processing metrics such as BLEU, METEOR, GLEU, and WER. Our results show that attention-based models outperform RNNs in generating more accurate and semantically rich captions, with better alignment to human evaluation. This work provides insights into the impact of attention mechanisms in image captioning and highlights areas for future improvements.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2502.18734>)

[PDF](<https://arxiv.org/pdf/2502.18734.pdf>)