@inproceedings{seoh-goldwasser-2025-emogist,
title = "{E}mo{G}ist: Efficient In-Context Learning for Visual Emotion Understanding",
author = "Seoh, Ronald and
Goldwasser, Dan",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-emnlp.116/",
doi = "10.18653/v1/2025.findings-emnlp.116",
pages = "2171--2182",
ISBN = "979-8-89176-335-7",
abstract = "In this paper, we introduce EmoGist, a training-free, in-context learning method for performing visual emotion classification with LVLMs. The key intuition of our approach is that context-dependent definition of emotion labels could allow more accurate predictions of emotions, as the ways in which emotions manifest within images are highly context dependent and nuanced. EmoGist pre-generates multiple descriptions of emotion labels, by analyzing the clusters of example images belonging to each label. At test time, we retrieve a version of description based on the cosine similarity of test image to cluster centroids, and feed it together with the test image to a fast LVLM for classification. Through our experiments, we show that EmoGist allows up to 12 points improvement in micro F1 scores with the multi-label Memotion dataset, and up to 8 points in macro F1 in the multi-class FI dataset."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="seoh-goldwasser-2025-emogist">
<titleInfo>
<title>EmoGist: Efficient In-Context Learning for Visual Emotion Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ronald</namePart>
<namePart type="family">Seoh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Goldwasser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-335-7</identifier>
</relatedItem>
<abstract>In this paper, we introduce EmoGist, a training-free, in-context learning method for performing visual emotion classification with LVLMs. The key intuition of our approach is that context-dependent definition of emotion labels could allow more accurate predictions of emotions, as the ways in which emotions manifest within images are highly context dependent and nuanced. EmoGist pre-generates multiple descriptions of emotion labels, by analyzing the clusters of example images belonging to each label. At test time, we retrieve a version of description based on the cosine similarity of test image to cluster centroids, and feed it together with the test image to a fast LVLM for classification. Through our experiments, we show that EmoGist allows up to 12 points improvement in micro F1 scores with the multi-label Memotion dataset, and up to 8 points in macro F1 in the multi-class FI dataset.</abstract>
<identifier type="citekey">seoh-goldwasser-2025-emogist</identifier>
<identifier type="doi">10.18653/v1/2025.findings-emnlp.116</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.116/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>2171</start>
<end>2182</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T EmoGist: Efficient In-Context Learning for Visual Emotion Understanding
%A Seoh, Ronald
%A Goldwasser, Dan
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F seoh-goldwasser-2025-emogist
%X In this paper, we introduce EmoGist, a training-free, in-context learning method for performing visual emotion classification with LVLMs. The key intuition of our approach is that context-dependent definition of emotion labels could allow more accurate predictions of emotions, as the ways in which emotions manifest within images are highly context dependent and nuanced. EmoGist pre-generates multiple descriptions of emotion labels, by analyzing the clusters of example images belonging to each label. At test time, we retrieve a version of description based on the cosine similarity of test image to cluster centroids, and feed it together with the test image to a fast LVLM for classification. Through our experiments, we show that EmoGist allows up to 12 points improvement in micro F1 scores with the multi-label Memotion dataset, and up to 8 points in macro F1 in the multi-class FI dataset.
%R 10.18653/v1/2025.findings-emnlp.116
%U https://aclanthology.org/2025.findings-emnlp.116/
%U https://doi.org/10.18653/v1/2025.findings-emnlp.116
%P 2171-2182
Markdown (Informal)
[EmoGist: Efficient In-Context Learning for Visual Emotion Understanding](https://aclanthology.org/2025.findings-emnlp.116/) (Seoh & Goldwasser, Findings 2025)
ACL