@inproceedings{zhang-etal-2024-visual,
title = "Visual Prompting in {LLM}s for Enhancing Emotion Recognition",
author = "Zhang, Qixuan and
Wang, Zhifeng and
Zhang, Dylan and
Niu, Wenjia and
Caldwell, Sabrina and
Gedeon, Tom and
Liu, Yang and
Qin, Zhenyue",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-main.257",
pages = "4484--4499",
abstract = "Vision Large Language Models (VLLMs) are transforming the intersection of computer vision and natural language processing; however, the potential of using visual prompts for emotion recognition in these models remains largely unexplored and untapped. Traditional methods in VLLMs struggle with spatial localization and often discard valuable global context. We propose a novel Set-of-Vision prompting (SoV) approach that enhances zero-shot emotion recognition by using spatial information, such as bounding boxes and facial landmarks, to mark targets precisely. SoV improves accuracy in face count and emotion categorization while preserving the enriched image context. Through comprehensive experimentation and analysis of recent commercial or open-source VLLMs, we evaluate the SoV model{'}s ability to comprehend facial expressions in natural environments. Our findings demonstrate the effectiveness of integrating spatial visual prompts into VLLMs for improving emotion recognition performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2024-visual">
<titleInfo>
<title>Visual Prompting in LLMs for Enhancing Emotion Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qixuan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhifeng</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dylan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjia</namePart>
<namePart type="family">Niu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sabrina</namePart>
<namePart type="family">Caldwell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Gedeon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhenyue</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Vision Large Language Models (VLLMs) are transforming the intersection of computer vision and natural language processing; however, the potential of using visual prompts for emotion recognition in these models remains largely unexplored and untapped. Traditional methods in VLLMs struggle with spatial localization and often discard valuable global context. We propose a novel Set-of-Vision prompting (SoV) approach that enhances zero-shot emotion recognition by using spatial information, such as bounding boxes and facial landmarks, to mark targets precisely. SoV improves accuracy in face count and emotion categorization while preserving the enriched image context. Through comprehensive experimentation and analysis of recent commercial or open-source VLLMs, we evaluate the SoV model’s ability to comprehend facial expressions in natural environments. Our findings demonstrate the effectiveness of integrating spatial visual prompts into VLLMs for improving emotion recognition performance.</abstract>
<identifier type="citekey">zhang-etal-2024-visual</identifier>
<location>
<url>https://aclanthology.org/2024.emnlp-main.257</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>4484</start>
<end>4499</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Visual Prompting in LLMs for Enhancing Emotion Recognition
%A Zhang, Qixuan
%A Wang, Zhifeng
%A Zhang, Dylan
%A Niu, Wenjia
%A Caldwell, Sabrina
%A Gedeon, Tom
%A Liu, Yang
%A Qin, Zhenyue
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F zhang-etal-2024-visual
%X Vision Large Language Models (VLLMs) are transforming the intersection of computer vision and natural language processing; however, the potential of using visual prompts for emotion recognition in these models remains largely unexplored and untapped. Traditional methods in VLLMs struggle with spatial localization and often discard valuable global context. We propose a novel Set-of-Vision prompting (SoV) approach that enhances zero-shot emotion recognition by using spatial information, such as bounding boxes and facial landmarks, to mark targets precisely. SoV improves accuracy in face count and emotion categorization while preserving the enriched image context. Through comprehensive experimentation and analysis of recent commercial or open-source VLLMs, we evaluate the SoV model’s ability to comprehend facial expressions in natural environments. Our findings demonstrate the effectiveness of integrating spatial visual prompts into VLLMs for improving emotion recognition performance.
%U https://aclanthology.org/2024.emnlp-main.257
%P 4484-4499
Markdown (Informal)
[Visual Prompting in LLMs for Enhancing Emotion Recognition](https://aclanthology.org/2024.emnlp-main.257) (Zhang et al., EMNLP 2024)
ACL
- Qixuan Zhang, Zhifeng Wang, Dylan Zhang, Wenjia Niu, Sabrina Caldwell, Tom Gedeon, Yang Liu, and Zhenyue Qin. 2024. Visual Prompting in LLMs for Enhancing Emotion Recognition. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 4484–4499, Miami, Florida, USA. Association for Computational Linguistics.