paper-with-me

Papers

Modelling Visual Semantics via Image Captioning to extract Enhanced Multi-Level Cross-Modal Semantic Incongruity Representation with Attention for Multimodal Sarcasm Detection

2024-08-05

Sarcasm is a type of irony, characterized by an inherent mismatch between the literal interpretation and the intended connotation. Though sarcasm detection in text has been extensively studied, there are situations in which textual input alone might be insufficient to perceive sarcasm. The inclusion of additional contextual cues, such as images, is essential to recognize sarcasm in social media data effectively. This study presents a novel framework for multimodal sarcasm detection that can process input triplets. Two components of these triplets comprise the input text and its associated image, as provided in the datasets. Additionally, a supplementary modality is introduced in the form of descriptive image captions. The motivation behind incorporating this visual semantic representation is to more accurately capture the discrepancies between the textual and visual content, which are fundamental to the sarcasm detection task. The primary contributions of this study are: (1) a robust textual feature extraction branch that utilizes a cross-lingual language model; (2) a visual feature extraction branch that incorporates a self-regulated residual ConvNet integrated with a lightweight spatially aware attention module; (3) an additional modality in the form of image captions generated using an encoder-decoder architecture capable of reading text embedded in images; (4) distinct attention modules to effectively identify the incongruities between the text and two levels of image representations; (5) multi-level cross-domain semantic incongruity representation achieved through feature fusion. Compared with cutting-edge baselines, the proposed model achieves the best accuracy of 92.89% and 64.48%, respectively, on the Twitter multimodal sarcasm and MultiBully datasets.

📄 PDF Abstract BibTeX arXiv:2408.02595

Code (0)

등록된 구현이 없습니다.

Tasks

DescriptiveImage CaptioningLanguage ModellingSarcasm Detection

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
AWARE We propose to theoretically and empirically examine the effect of incorporating weighting schemes into walk-aggregating GNNs. To this end, we propose a simple, interpretable, and…

Similar Papers 제목 키워드 기반

IcoCap: Improving Video Captioning by Compounding Images

2023-10-05 · IEEE Transactions on Multimedia 2023 10 · Yuanzhi Liang, Linchao Zhu, Xiaohan Wang, Yi Yang

Video captioning is a more challenging task compared to image captioning, primarily due to differences in content density. Video data contains redundant visual content, making it difficult for captioners to generalize di…

Image CaptioningVideo Captioning

Semantic Alignment for Multimodal Large Language Models

2024-08-23 · Tao Wu, Mengze Li, Jingyuan Chen, Wei Ji 외

Research on Multi-modal Large Language Models (MLLMs) towards the multi-image cross-modal instruction has received increasing attention and made significant progress, particularly in scenarios involving closely resemblin…

Large Language ModelVisual Storytelling

Scene-based Factored Attention for Image Captioning

2019-08-07 · Chen Shen, Rongrong Ji, Fuhai Chen, Xiaoshuai Sun 외

Image captioning has attracted ever-increasing research attention in the multimedia community. To this end, most cutting-edge works rely on an encoder-decoder framework with attention mechanisms, which have achieved rema…

Caption GenerationDecoderImage CaptioningSentence

Leveraging Textual Compositional Reasoning for Robust Change Captioning

2025-11-28 · Kyu Ri Park, Jiyoung Park, Seong Tae Kim, Hong Joo Lee 외 arxiv

Change captioning aims to describe changes between a pair of images. However, existing works rely on visual features alone, which often fail to capture subtle but meaningful changes because they lack the ability to repre…

Relational Reasoning

CapSal: Leveraging Captioning to Boost Semantics for Salient Object Detection

2019-06-01 · CVPR 2019 6 · Lu Zhang, Jianming Zhang, Zhe Lin, Huchuan Lu 외

Detecting salient objects in cluttered scenes is a big challenge. To address this problem, we argue that the model needs to learn discriminative semantic features for salient objects. To this end, we propose to leverage…

Image Captioningobject-detectionObject DetectionRGB Salient Object Detection+1