@inproceedings{tang-etal-2026-egomemory,
title = "{E}go{M}emory: Memory-Augmented Personalized Retrieval for Long-Context Egocentric Video",
author = "Tang, Yuanmin and
Zhang, Jue and
Qin, Xiaoting and
Yu, Jing and
Qiu, Meikang and
Gou, Gaopeng and
Xiong, Gang and
Lin, Qingwei and
Rajmohan, Saravan and
Zhang, Dongmei and
Wu, Qi",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.362/",
pages = "7317--7349",
ISBN = "979-8-89176-395-1",
abstract = "Recent advances in AI and wearable devices, such as augmented-reality glasses, have made it possible to augment human memory by retrieving personal experiences in response to natural language queries. However, existing egocentric video datasets fall short in supporting the personalization and long-context reasoning required for episodic memory retrieval. To address these limitations, we introduce EgoMemory, a benchmark derived from Ego4D, enriched with 165,795 user-specific object annotations over 245 videos from 45 participants, yielding 639 distinct, human-curated, and evaluated queries for rich and individualized episodic memory retrieval. Leveraging this resource, we present EgoRetriever, a novel, training-free retrieval framework that combines Multimodal Large Language Models with reflective Chain-of-Thought prompting. Our approach enables interpretive inference of user intent and generates detailed target video descriptions by leveraging contextualized personal memory for video retrieval. Extensive experiments on three benchmarks, including EgoMemory, EgoCVR, and EgoLife, demonstrate that EgoRetriever consistently and substantially outperforms state-of-the-art baselines, highlighting its strong generalizability and practical potential for personalized, long-context egocentric video retrieval."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tang-etal-2026-egomemory">
<titleInfo>
<title>EgoMemory: Memory-Augmented Personalized Retrieval for Long-Context Egocentric Video</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuanmin</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoting</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meikang</namePart>
<namePart type="family">Qiu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gaopeng</namePart>
<namePart type="family">Gou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gang</namePart>
<namePart type="family">Xiong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qingwei</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saravan</namePart>
<namePart type="family">Rajmohan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dongmei</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qi</namePart>
<namePart type="family">Wu</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>Findings of the Association for Computational Linguistics: ACL 2026</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">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>Recent advances in AI and wearable devices, such as augmented-reality glasses, have made it possible to augment human memory by retrieving personal experiences in response to natural language queries. However, existing egocentric video datasets fall short in supporting the personalization and long-context reasoning required for episodic memory retrieval. To address these limitations, we introduce EgoMemory, a benchmark derived from Ego4D, enriched with 165,795 user-specific object annotations over 245 videos from 45 participants, yielding 639 distinct, human-curated, and evaluated queries for rich and individualized episodic memory retrieval. Leveraging this resource, we present EgoRetriever, a novel, training-free retrieval framework that combines Multimodal Large Language Models with reflective Chain-of-Thought prompting. Our approach enables interpretive inference of user intent and generates detailed target video descriptions by leveraging contextualized personal memory for video retrieval. Extensive experiments on three benchmarks, including EgoMemory, EgoCVR, and EgoLife, demonstrate that EgoRetriever consistently and substantially outperforms state-of-the-art baselines, highlighting its strong generalizability and practical potential for personalized, long-context egocentric video retrieval.</abstract>
<identifier type="citekey">tang-etal-2026-egomemory</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.362/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>7317</start>
<end>7349</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T EgoMemory: Memory-Augmented Personalized Retrieval for Long-Context Egocentric Video
%A Tang, Yuanmin
%A Zhang, Jue
%A Qin, Xiaoting
%A Yu, Jing
%A Qiu, Meikang
%A Gou, Gaopeng
%A Xiong, Gang
%A Lin, Qingwei
%A Rajmohan, Saravan
%A Zhang, Dongmei
%A Wu, Qi
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F tang-etal-2026-egomemory
%X Recent advances in AI and wearable devices, such as augmented-reality glasses, have made it possible to augment human memory by retrieving personal experiences in response to natural language queries. However, existing egocentric video datasets fall short in supporting the personalization and long-context reasoning required for episodic memory retrieval. To address these limitations, we introduce EgoMemory, a benchmark derived from Ego4D, enriched with 165,795 user-specific object annotations over 245 videos from 45 participants, yielding 639 distinct, human-curated, and evaluated queries for rich and individualized episodic memory retrieval. Leveraging this resource, we present EgoRetriever, a novel, training-free retrieval framework that combines Multimodal Large Language Models with reflective Chain-of-Thought prompting. Our approach enables interpretive inference of user intent and generates detailed target video descriptions by leveraging contextualized personal memory for video retrieval. Extensive experiments on three benchmarks, including EgoMemory, EgoCVR, and EgoLife, demonstrate that EgoRetriever consistently and substantially outperforms state-of-the-art baselines, highlighting its strong generalizability and practical potential for personalized, long-context egocentric video retrieval.
%U https://aclanthology.org/2026.findings-acl.362/
%P 7317-7349
Markdown (Informal)
[EgoMemory: Memory-Augmented Personalized Retrieval for Long-Context Egocentric Video](https://aclanthology.org/2026.findings-acl.362/) (Tang et al., Findings 2026)
ACL
- Yuanmin Tang, Jue Zhang, Xiaoting Qin, Jing Yu, Meikang Qiu, Gaopeng Gou, Gang Xiong, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang, and Qi Wu. 2026. EgoMemory: Memory-Augmented Personalized Retrieval for Long-Context Egocentric Video. In Findings of the Association for Computational Linguistics: ACL 2026, pages 7317–7349, San Diego, California, United States. Association for Computational Linguistics.