@inproceedings{li-etal-2026-breaking,
title = "Breaking Temporal Ambiguity: Linguistic Temporal Knowledge Transfer for Weakly-Supervised Action Localization",
author = "Li, Zhilin and
Wu, Shining and
Zhang, Yixin and
Cheng, Chuandong and
Wang, Zilei",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.1350/",
pages = "30771--30787",
ISBN = "979-8-89176-459-0",
abstract = "Weakly-supervised temporal action localization (WS-TAL) remains challenging due to the severe temporal ambiguity inherent in video-level supervision. Existing methods often overfit to highly discriminative snippets, struggling to capture the complete action extent. In this paper, we reconceptualize actions not as isolated events, but as multi-stage action evolutions. To alleviate temporal ambiguity, we propose a novel framework driven by Linguistic Temporal Knowledge Transfer (LTKT) Network, comprising three cohesive modules. First, Temporal Stage Grounding (TSG) leverages explicitly deconstructed LLM descriptions as cross-modal priors, guiding unconstrained visual snippets to anchor their specific evolutionary stages. Second, Temporal Transition Gating (TTG) enforces forward causality on the timeline. By mandating that an execution stage is flanked by historical preparation and future completion, TTG strictly filters static noise to yield refined temporal action scores. Finally, Linguistic Knowledge Transfer (LKT) integrates knowledge distillation and contrastive learning to embed this structural knowledge into the visual backbone. Extensive experiments on THUMOS14, ActivityNet1.2 and ActivityNet1.3 demonstrate that our method achieves state-of-the-art performance."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2026-breaking">
<titleInfo>
<title>Breaking Temporal Ambiguity: Linguistic Temporal Knowledge Transfer for Weakly-Supervised Action Localization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhilin</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shining</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yixin</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chuandong</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zilei</namePart>
<namePart type="family">Wang</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>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</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">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Weakly-supervised temporal action localization (WS-TAL) remains challenging due to the severe temporal ambiguity inherent in video-level supervision. Existing methods often overfit to highly discriminative snippets, struggling to capture the complete action extent. In this paper, we reconceptualize actions not as isolated events, but as multi-stage action evolutions. To alleviate temporal ambiguity, we propose a novel framework driven by Linguistic Temporal Knowledge Transfer (LTKT) Network, comprising three cohesive modules. First, Temporal Stage Grounding (TSG) leverages explicitly deconstructed LLM descriptions as cross-modal priors, guiding unconstrained visual snippets to anchor their specific evolutionary stages. Second, Temporal Transition Gating (TTG) enforces forward causality on the timeline. By mandating that an execution stage is flanked by historical preparation and future completion, TTG strictly filters static noise to yield refined temporal action scores. Finally, Linguistic Knowledge Transfer (LKT) integrates knowledge distillation and contrastive learning to embed this structural knowledge into the visual backbone. Extensive experiments on THUMOS14, ActivityNet1.2 and ActivityNet1.3 demonstrate that our method achieves state-of-the-art performance.</abstract>
<identifier type="citekey">li-etal-2026-breaking</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.1350/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>30771</start>
<end>30787</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Breaking Temporal Ambiguity: Linguistic Temporal Knowledge Transfer for Weakly-Supervised Action Localization
%A Li, Zhilin
%A Wu, Shining
%A Zhang, Yixin
%A Cheng, Chuandong
%A Wang, Zilei
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F li-etal-2026-breaking
%X Weakly-supervised temporal action localization (WS-TAL) remains challenging due to the severe temporal ambiguity inherent in video-level supervision. Existing methods often overfit to highly discriminative snippets, struggling to capture the complete action extent. In this paper, we reconceptualize actions not as isolated events, but as multi-stage action evolutions. To alleviate temporal ambiguity, we propose a novel framework driven by Linguistic Temporal Knowledge Transfer (LTKT) Network, comprising three cohesive modules. First, Temporal Stage Grounding (TSG) leverages explicitly deconstructed LLM descriptions as cross-modal priors, guiding unconstrained visual snippets to anchor their specific evolutionary stages. Second, Temporal Transition Gating (TTG) enforces forward causality on the timeline. By mandating that an execution stage is flanked by historical preparation and future completion, TTG strictly filters static noise to yield refined temporal action scores. Finally, Linguistic Knowledge Transfer (LKT) integrates knowledge distillation and contrastive learning to embed this structural knowledge into the visual backbone. Extensive experiments on THUMOS14, ActivityNet1.2 and ActivityNet1.3 demonstrate that our method achieves state-of-the-art performance.
%U https://aclanthology.org/2026.emnlp-main.1350/
%P 30771-30787
Markdown (Informal)
[Breaking Temporal Ambiguity: Linguistic Temporal Knowledge Transfer for Weakly-Supervised Action Localization](https://aclanthology.org/2026.emnlp-main.1350/) (Li et al., EMNLP 2026)
ACL