@inproceedings{hou-etal-2026-language,
title = "Language-Guided Time-Series Event Detection with Zero-Shot Cross-Modal Grounding",
author = "Hou, Tianjun and
Chang, Xiqing and
Wan, Sky Chenwei",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.229/",
pages = "4813--4836",
ISBN = "979-8-89176-462-0",
abstract = "In this study, we address the language-guided time-series event detection problem: given a natural-language event description and a time series, the system returns event occurrences as temporal spans. Language-guided event detection leverages domain knowledge expressed in natural language to enable zero-shot detection without domain-specific fine-tuning. We introduce GroundingMOMENT, a zero-shot cross-modal grounding framework that aligns a time-series foundation model with a language model. GroundingMOMENT concurrently localizes both complex, high-level event occurrences and their constituent domain-agnostic structural primitives (e.g., spikes, plateaus). We further introduce GroundTSSyn, a scalable pipeline for generating synthetic time-series grounding data, and release GroundTSBench, the first open-source benchmark for language-guided time-series grounding. Trained exclusively on GroundTSBench, GroundingMOMENT outperforms time-series multimodal large language models and achieves fast and accurate event detection. Case studies further demonstrate its zero-shot generalizability to real-world data from diverse domains."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hou-etal-2026-language">
<titleInfo>
<title>Language-Guided Time-Series Event Detection with Zero-Shot Cross-Modal Grounding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tianjun</namePart>
<namePart type="family">Hou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiqing</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sky</namePart>
<namePart type="given">Chenwei</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>In this study, we address the language-guided time-series event detection problem: given a natural-language event description and a time series, the system returns event occurrences as temporal spans. Language-guided event detection leverages domain knowledge expressed in natural language to enable zero-shot detection without domain-specific fine-tuning. We introduce GroundingMOMENT, a zero-shot cross-modal grounding framework that aligns a time-series foundation model with a language model. GroundingMOMENT concurrently localizes both complex, high-level event occurrences and their constituent domain-agnostic structural primitives (e.g., spikes, plateaus). We further introduce GroundTSSyn, a scalable pipeline for generating synthetic time-series grounding data, and release GroundTSBench, the first open-source benchmark for language-guided time-series grounding. Trained exclusively on GroundTSBench, GroundingMOMENT outperforms time-series multimodal large language models and achieves fast and accurate event detection. Case studies further demonstrate its zero-shot generalizability to real-world data from diverse domains.</abstract>
<identifier type="citekey">hou-etal-2026-language</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.229/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>4813</start>
<end>4836</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Language-Guided Time-Series Event Detection with Zero-Shot Cross-Modal Grounding
%A Hou, Tianjun
%A Chang, Xiqing
%A Wan, Sky Chenwei
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F hou-etal-2026-language
%X In this study, we address the language-guided time-series event detection problem: given a natural-language event description and a time series, the system returns event occurrences as temporal spans. Language-guided event detection leverages domain knowledge expressed in natural language to enable zero-shot detection without domain-specific fine-tuning. We introduce GroundingMOMENT, a zero-shot cross-modal grounding framework that aligns a time-series foundation model with a language model. GroundingMOMENT concurrently localizes both complex, high-level event occurrences and their constituent domain-agnostic structural primitives (e.g., spikes, plateaus). We further introduce GroundTSSyn, a scalable pipeline for generating synthetic time-series grounding data, and release GroundTSBench, the first open-source benchmark for language-guided time-series grounding. Trained exclusively on GroundTSBench, GroundingMOMENT outperforms time-series multimodal large language models and achieves fast and accurate event detection. Case studies further demonstrate its zero-shot generalizability to real-world data from diverse domains.
%U https://aclanthology.org/2026.findings-emnlp.229/
%P 4813-4836
Markdown (Informal)
[Language-Guided Time-Series Event Detection with Zero-Shot Cross-Modal Grounding](https://aclanthology.org/2026.findings-emnlp.229/) (Hou et al., Findings 2026)
ACL