What question did this study set out to answer?

Develop and evaluate VyAnG-Net, a multimodal architecture that detects conversational sarcasm by integrating visual, acoustic, and textual information.

May 4, 2025Intelligent Data Analysis

VyAnG-Net: A novel multi-modal sarcasm recognition model by uncovering visual, acoustic and glossary features

View Full Paper

Ask AI

Bookmark

Authors

APAnanya PandeyAmity University DVDinesh Kumar VishwakarmaDelhi Technological University

Discussion

Member takes

Implication

Machine learning study demonstrates enhanced sarcasm detection in conversational video dialogues, highlighting the value of fusing visual, acoustic, and textual cues.

Key Points

Develop and evaluate VyAnG-Net, a multimodal architecture that detects conversational sarcasm by integrating visual, acoustic, and textual information.
Integrated a lightweight depth attention module with a self-regulated convolutional network for visual frames and an attentional tokenizer for subtitle text.
Extracted utterance-level acoustic features and combined all modalities via a multi-headed attention feature fusion network.
Evaluated performance on the MUSTaRD benchmark across speaker-dependent and speaker-independent setups, followed by cross-dataset testing on MUStARD++.
Achieved an accuracy of 79.86% in the speaker-dependent configuration on the MUSTaRD benchmark dataset.
Achieved an accuracy of 76.94% in the speaker-independent configuration on MUSTaRD, outperforming baseline approaches.
Demonstrated cross-dataset generalization when tested against unseen conversational samples from the MUStARD++ dataset.

Cite This Study

Pandey et al. (2025) studied this question.

synapsesocial.com/papers/6a105d9710ed65f1d0fcbb54 https://doi.org/10.1177/1088467x251315637

View Full Paper

Ask AI

Bookmark

Implication

Machine learning study demonstrates enhanced sarcasm detection in conversational video dialogues, highlighting the value of fusing visual, acoustic, and textual cues.

VyAnG-Net: A novel multi-modal sarcasm recognition model by uncovering visual, acoustic and glossary features

Discussion

Member takes

Implication

Key Points

Cite This Study

VyAnG-Net: A novel multi-modal sarcasm recognition model by uncovering visual, acoustic and glossary features

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider