@inproceedings{wazni-etal-2024-verbclip,
title = "{V}erb{CLIP}: Improving Verb Understanding in Vision-Language Models with Compositional Structures",
author = "Wazni, Hadi and
Lo, Kin Ian and
Sadrzadeh, Mehrnoosh",
editor = "Gu, Jing and
Fu, Tsu-Jui (Ray) and
Hudson, Drew and
Celikyilmaz, Asli and
Wang, William",
booktitle = "Proceedings of the 3rd Workshop on Advances in Language and Vision Research (ALVR)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.alvr-1.17",
doi = "10.18653/v1/2024.alvr-1.17",
pages = "195--201",
abstract = "Verbs describe the dynamics of interactions between people, objects, and their environments. They play a crucial role in language formation and understanding. Nonetheless, recent vision-language models like CLIP predominantly rely on nouns and have a limited account of verbs. This limitation affects their performance in tasks requiring action recognition and scene understanding. In this work, we introduce VerbCLIP, a verb-centric vision-language model which learns meanings of verbs based on a compositional approach to statistical machine learning. Our methods significantly outperform CLIP in zero-shot performance on the VALSE, VL-Checklist, and SVO-Probes datasets, with improvements of +2.38{\%}, +3.14{\%}, and +1.47{\%}, without fine-tuning. Fine-tuning resulted in further improvements, with gains of +2.85{\%} and +9.2{\%} on the VALSE and VL-Checklist datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wazni-etal-2024-verbclip">
<titleInfo>
<title>VerbCLIP: Improving Verb Understanding in Vision-Language Models with Compositional Structures</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hadi</namePart>
<namePart type="family">Wazni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kin</namePart>
<namePart type="given">Ian</namePart>
<namePart type="family">Lo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mehrnoosh</namePart>
<namePart type="family">Sadrzadeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 3rd Workshop on Advances in Language and Vision Research (ALVR)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Gu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tsu-Jui</namePart>
<namePart type="given">(Ray)</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Drew</namePart>
<namePart type="family">Hudson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asli</namePart>
<namePart type="family">Celikyilmaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Verbs describe the dynamics of interactions between people, objects, and their environments. They play a crucial role in language formation and understanding. Nonetheless, recent vision-language models like CLIP predominantly rely on nouns and have a limited account of verbs. This limitation affects their performance in tasks requiring action recognition and scene understanding. In this work, we introduce VerbCLIP, a verb-centric vision-language model which learns meanings of verbs based on a compositional approach to statistical machine learning. Our methods significantly outperform CLIP in zero-shot performance on the VALSE, VL-Checklist, and SVO-Probes datasets, with improvements of +2.38%, +3.14%, and +1.47%, without fine-tuning. Fine-tuning resulted in further improvements, with gains of +2.85% and +9.2% on the VALSE and VL-Checklist datasets.</abstract>
<identifier type="citekey">wazni-etal-2024-verbclip</identifier>
<identifier type="doi">10.18653/v1/2024.alvr-1.17</identifier>
<location>
<url>https://aclanthology.org/2024.alvr-1.17</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>195</start>
<end>201</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T VerbCLIP: Improving Verb Understanding in Vision-Language Models with Compositional Structures
%A Wazni, Hadi
%A Lo, Kin Ian
%A Sadrzadeh, Mehrnoosh
%Y Gu, Jing
%Y Fu, Tsu-Jui (Ray)
%Y Hudson, Drew
%Y Celikyilmaz, Asli
%Y Wang, William
%S Proceedings of the 3rd Workshop on Advances in Language and Vision Research (ALVR)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F wazni-etal-2024-verbclip
%X Verbs describe the dynamics of interactions between people, objects, and their environments. They play a crucial role in language formation and understanding. Nonetheless, recent vision-language models like CLIP predominantly rely on nouns and have a limited account of verbs. This limitation affects their performance in tasks requiring action recognition and scene understanding. In this work, we introduce VerbCLIP, a verb-centric vision-language model which learns meanings of verbs based on a compositional approach to statistical machine learning. Our methods significantly outperform CLIP in zero-shot performance on the VALSE, VL-Checklist, and SVO-Probes datasets, with improvements of +2.38%, +3.14%, and +1.47%, without fine-tuning. Fine-tuning resulted in further improvements, with gains of +2.85% and +9.2% on the VALSE and VL-Checklist datasets.
%R 10.18653/v1/2024.alvr-1.17
%U https://aclanthology.org/2024.alvr-1.17
%U https://doi.org/10.18653/v1/2024.alvr-1.17
%P 195-201
Markdown (Informal)
[VerbCLIP: Improving Verb Understanding in Vision-Language Models with Compositional Structures](https://aclanthology.org/2024.alvr-1.17) (Wazni et al., ALVR-WS 2024)
ACL