<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tsutsukawa-2026-insat">
    <titleInfo>
        <title>InsAT: Instance-aware Semantic Alignment and Transfer from Human–Object Keypoints for Zero-to-Few-shot Action Understanding</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Kazuki</namePart>
        <namePart type="family">Tsutsukawa</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Maria</namePart>
            <namePart type="family">Liakata</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Viviane</namePart>
            <namePart type="given">P</namePart>
            <namePart type="family">Moreira</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jiajun</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Jurgens</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, California, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-390-6</identifier>
    </relatedItem>
    <abstract>Keypoint-based action recognition offers robustness to appearance variations and provides privacy-preserving representation. However, existing zero-shot (ZS) approaches largely emphasize human motion while underutilizing contextual information, particularly human–object interactions. Moreover, extending keypoint-based ZS models to few-shot scenarios remains insufficiently explored. We propose Instance-aware Semantic Alignment and Transfer (InsAT), a unified framework for ZS recognition and zero-to-few-shot (Z2F) adaptation that leverages instance-level language descriptions. InsAT aligns textual descriptions of humans, objects, and their interactions with visual representations derived from human and object keypoints, enabling effective transfer of interaction knowledge from seen to unseen action classes. To support Z2F adaptation, we introduce Instance-level Visual Adaptation, a parameter-free mechanism that improves recognition by incorporating instance-level contextual cues without updating model weights. Extensive experiments demonstrate that InsAT substantially outperforms prior keypoint-based ZS methods and achieves competitive performance relative to large vision–language models, while remaining data-efficient and robust.</abstract>
    <identifier type="citekey">tsutsukawa-2026-insat</identifier>
    <location>
        <url>https://aclanthology.org/2026.acl-long.1690/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>36487</start>
            <end>36504</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T InsAT: Instance-aware Semantic Alignment and Transfer from Human–Object Keypoints for Zero-to-Few-shot Action Understanding
%A Tsutsukawa, Kazuki
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F tsutsukawa-2026-insat
%X Keypoint-based action recognition offers robustness to appearance variations and provides privacy-preserving representation. However, existing zero-shot (ZS) approaches largely emphasize human motion while underutilizing contextual information, particularly human–object interactions. Moreover, extending keypoint-based ZS models to few-shot scenarios remains insufficiently explored. We propose Instance-aware Semantic Alignment and Transfer (InsAT), a unified framework for ZS recognition and zero-to-few-shot (Z2F) adaptation that leverages instance-level language descriptions. InsAT aligns textual descriptions of humans, objects, and their interactions with visual representations derived from human and object keypoints, enabling effective transfer of interaction knowledge from seen to unseen action classes. To support Z2F adaptation, we introduce Instance-level Visual Adaptation, a parameter-free mechanism that improves recognition by incorporating instance-level contextual cues without updating model weights. Extensive experiments demonstrate that InsAT substantially outperforms prior keypoint-based ZS methods and achieves competitive performance relative to large vision–language models, while remaining data-efficient and robust.
%U https://aclanthology.org/2026.acl-long.1690/
%P 36487-36504

Markdown (Informal)

[InsAT: Instance-aware Semantic Alignment and Transfer from Human–Object Keypoints for Zero-to-Few-shot Action Understanding](https://aclanthology.org/2026.acl-long.1690/) (Tsutsukawa, ACL 2026)

• InsAT: Instance-aware Semantic Alignment and Transfer from Human–Object Keypoints for Zero-to-Few-shot Action Understanding (Tsutsukawa, ACL 2026)

ACL

• Kazuki Tsutsukawa. 2026. InsAT: Instance-aware Semantic Alignment and Transfer from Human–Object Keypoints for Zero-to-Few-shot Action Understanding. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 36487–36504, San Diego, California, United States. Association for Computational Linguistics.