@inproceedings{liang-etal-2026-anom3w,
title = "{A}nom3{W}: A Unified Benchmark for Video Anomaly Grounding and Understanding",
author = "Liang, Liang and
Zhu, Yun and
Lin, Juekai and
Wang, Haoyang and
Li, Jinhui and
Zhou, Weilin and
Zhu, Yuehan and
Wu, Lijun and
Zhang, Wenqiao and
Xiao, Jun",
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.1973/",
pages = "42074--42092",
ISBN = "979-8-89176-462-0",
abstract = "Understanding anomalies in real-world videos requires reasoning about when events occur, where they happen, and what actions unfold. Existing benchmarks, however, largely ignore one or more of these dimensions, making it difficult to evaluate whether multimodal large models (MLLMs) truly understand abnormal events beyond simple detection. To address this gap, we introduce $\textbf{Anom3W}$, a benchmark designed to evaluate MLLMs across $\textbf{temporal, spatial, and semantic dimensions}$. Our semi-automatic pipeline consolidates heterogeneous anomaly resources into verified spatio-temporal annotations, enabling rigorous, reasoning-oriented evaluation. By treating spatial boxes and tubes as evidence cues, Anom3W challenges models to reason about entities, locations, and behaviors, rather than merely flag anomalies. Experiments demonstrate that even state-of-the-art MLLMs struggle, highlighting the critical importance of spatial grounding and semantic understanding. Anom3W establishes a new standard for interpretable, context-aware video anomaly reasoning."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liang-etal-2026-anom3w">
<titleInfo>
<title>Anom3W: A Unified Benchmark for Video Anomaly Grounding and Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Liang</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juekai</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haoyang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinhui</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weilin</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuehan</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lijun</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenqiao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Xiao</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>Understanding anomalies in real-world videos requires reasoning about when events occur, where they happen, and what actions unfold. Existing benchmarks, however, largely ignore one or more of these dimensions, making it difficult to evaluate whether multimodal large models (MLLMs) truly understand abnormal events beyond simple detection. To address this gap, we introduce Anom3W, a benchmark designed to evaluate MLLMs across temporal, spatial, and semantic dimensions. Our semi-automatic pipeline consolidates heterogeneous anomaly resources into verified spatio-temporal annotations, enabling rigorous, reasoning-oriented evaluation. By treating spatial boxes and tubes as evidence cues, Anom3W challenges models to reason about entities, locations, and behaviors, rather than merely flag anomalies. Experiments demonstrate that even state-of-the-art MLLMs struggle, highlighting the critical importance of spatial grounding and semantic understanding. Anom3W establishes a new standard for interpretable, context-aware video anomaly reasoning.</abstract>
<identifier type="citekey">liang-etal-2026-anom3w</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1973/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>42074</start>
<end>42092</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Anom3W: A Unified Benchmark for Video Anomaly Grounding and Understanding
%A Liang, Liang
%A Zhu, Yun
%A Lin, Juekai
%A Wang, Haoyang
%A Li, Jinhui
%A Zhou, Weilin
%A Zhu, Yuehan
%A Wu, Lijun
%A Zhang, Wenqiao
%A Xiao, Jun
%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 liang-etal-2026-anom3w
%X Understanding anomalies in real-world videos requires reasoning about when events occur, where they happen, and what actions unfold. Existing benchmarks, however, largely ignore one or more of these dimensions, making it difficult to evaluate whether multimodal large models (MLLMs) truly understand abnormal events beyond simple detection. To address this gap, we introduce Anom3W, a benchmark designed to evaluate MLLMs across temporal, spatial, and semantic dimensions. Our semi-automatic pipeline consolidates heterogeneous anomaly resources into verified spatio-temporal annotations, enabling rigorous, reasoning-oriented evaluation. By treating spatial boxes and tubes as evidence cues, Anom3W challenges models to reason about entities, locations, and behaviors, rather than merely flag anomalies. Experiments demonstrate that even state-of-the-art MLLMs struggle, highlighting the critical importance of spatial grounding and semantic understanding. Anom3W establishes a new standard for interpretable, context-aware video anomaly reasoning.
%U https://aclanthology.org/2026.findings-emnlp.1973/
%P 42074-42092
Markdown (Informal)
[Anom3W: A Unified Benchmark for Video Anomaly Grounding and Understanding](https://aclanthology.org/2026.findings-emnlp.1973/) (Liang et al., Findings 2026)
ACL
- Liang Liang, Yun Zhu, Juekai Lin, Haoyang Wang, Jinhui Li, Weilin Zhou, Yuehan Zhu, Lijun Wu, Wenqiao Zhang, and Jun Xiao. 2026. Anom3W: A Unified Benchmark for Video Anomaly Grounding and Understanding. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 42074–42092, Budapest, Hungary. Association for Computational Linguistics.