activity
20182026
most citedMitigating Gradient-based Adversarial Attacks via Denoising and Compression

3 citations · 8 across the 8 of their papers we have counts for

collaborators

9 papers

cs.MM2026

Proactive Conversational Assistant for a Procedural Manual Task based on Audio and IMU

Rehana Mahfuz, Yinyi Guo, Erik Visser +1

Real-time conversational assistants for procedural manual tasks often depend on video input, which can be computationally expensive and compromise user privacy. For the first time,…

eess.AS2025

Aligning Audio Captions with Human Preferences

Kartik Hegde, Rehana Mahfuz, Yinyi Guo +1

Current audio captioning relies on supervised learning with paired audio-caption data, which is costly to curate and may not reflect human preferences in real-world scenarios. To a…

cs.MM2024★ 1 cited

Resource-Efficient Reference-Free Evaluation of Audio Captions

Rehana Mahfuz, Yinyi Guo, Erik Visser

To establish the trustworthiness of systems that automatically generate text captions for audio, images and video, existing reference-free metrics rely on large pretrained models w…

cs.CL2023

Parameter Efficient Audio Captioning With Faithful Guidance Using Audio-text Shared Latent Representation

Arvind Krishna Sridhar, Yinyi Guo, Erik Visser +1

There has been significant research on developing pretrained transformer architectures for multimodal-to-text generation tasks. Albeit performance improvements, such models are fre…

cs.MM2023

Detecting False Alarms and Misses in Audio Captions

Rehana Mahfuz, Yinyi Guo, Arvind Krishna Sridhar +1

Metrics to evaluate audio captions simply provide a score without much explanation regarding what may be wrong in case the score is low. Manual human intervention is needed to find…

cs.CR2021★ 3 cited

Mitigating Gradient-based Adversarial Attacks via Denoising and Compression

Rehana Mahfuz, Rajeev Sahay, Aly El Gamal

Gradient-based adversarial attacks on deep neural networks pose a serious threat, since they can be deployed by adding imperceptible perturbations to the test data of any network,…