[go: up one dir, main page]
More Web Proxy on the site http://driver.im/ skip to main content
10.1145/3592573.3593105acmconferencesArticle/Chapter ViewAbstractPublication PagesicmrConference Proceedingsconference-collections
research-article
Open access

lifeXplore at the Lifelog Search Challenge 2023

Published: 12 June 2023 Publication History

Abstract

Searching substantial data archives of lifeloggers is a challenging task. The Lifelog Search Challenge (LSC) is an annually held competition with the aim of encouraging international teams to develop interactive content retrieval systems capable of searching large lifelog databases. LSC takes place as a live event co-located with the ACM International Conference on Multimedia Retrieval (ICMR), where teams compete against each other by solving retrieval tasks issued by the lifelogger. This paper presents our newest version of lifeXplore, a lifelog retrieval system that has been participating in LSC since 2018. For this year, we significantly redesign the entire system (backend, middleware, and frontend) and integrate free text-search using embeddings from vision transformers trained with large sets of text-image pairs. We present a novel architecture for multi-source search, where results from image embeddings are used together with results from traditional content analysis (for objects, concepts, and recognized text). We also perform intensive analysis of vision transformer models in order to know which one fits best to the requirements of the LSC.

References

[1]
Naushad Alam, Yvette Graham, and Cathal Gurrin. 2021. Memento: A Prototype Lifelog Search Engine for LSC’21. In Proceedings of the 4th Annual on Lifelog Search Challenge. 53–58.
[2]
Ahmed Alateeq, Mark Roantree, and Cathal Gurrin. 2020. Voxento: a prototype voice-controlled interactive search engine for lifelogs. In Proceedings of the Third Annual Workshop on Lifelog Search Challenge. 77–81.
[3]
Youngmin Baek, Bado Lee, Dongyoon Han, Sangdoo Yun, and Hwalsuk Lee. 2019. Character region awareness for text detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 9365–9374.
[4]
Duc Tien Dang Nguyen Graham Healy Jakub Lokoc Liting Zhou Luca Rossetto Minh-Triet Tran Wolfgang Hürst Werner Bailer Klaus Schoeffmann Cathal Gurrin, Björn Þór Jónsson. 2023. Introduction to the Sixth Annual Lifelog Search Challenge, LSC’23. In Proc. International Conference on Multimedia Retrieval (ICMR’23)(ICMR ’23). New York, NY, USA.
[5]
Mehdi Cherti, Romain Beaumont, Ross Wightman, Mitchell Wortsman, Gabriel Ilharco, Cade Gordon, Christoph Schuhmann, Ludwig Schmidt, and Jenia Jitsev. 2022. Reproducible scaling laws for contrastive language-image learning. https://doi.org/10.48550/ARXIV.2212.07143
[6]
Aaron Duane and Bjorn Þór Jónsson. 2021. ViRMA: Virtual Reality Multimedia Analytics at LSC 2021. In Proceedings of the 4th Annual on Lifelog Search Challenge. 29–34.
[7]
Alexander Christian Faisst and Björn Þór Jónsson. 2021. LifeMon: A MongoDB-Based Lifelog Retrieval Prototype. In Proceedings of the 4th Annual on Lifelog Search Challenge. 75–80.
[8]
Silvan Heller, Ralph Gasser, Mahnaz Parian-Scherb, Sanja Popovic, Luca Rossetto, Loris Sauter, Florian Spiess, and Heiko Schuldt. 2021. Interactive multimodal lifelog retrieval with Vitrivr at LSC 2021. In Proceedings of the 4th Annual on Lifelog Search Challenge. 35–39.
[9]
Jeff Johnson, Matthijs Douze, and Hervé Jégou. 2019. Billion-scale similarity search with GPUs. IEEE Transactions on Big Data 7, 3 (2019), 535–547.
[10]
Omar Shahbaz Khan, Aaron Duane, Björn Þór Jónsson, Jan Zahálka, Stevan Rudinac, and Marcel Worring. 2021. Exquisitor at the Lifelog Search Challenge 2021: Relationships Between Semantic Classifiers. In Proceedings of the 4th Annual on Lifelog Search Challenge. 3–6.
[11]
Tu-Khiem Le, Van-Tu Ninh, Mai-Khiem Tran, Graham Healy, Cathal Gurrin, and Minh-Triet Tran. 2022. AVSeeker: An Active Video Retrieval Engine at VBS2022. In MultiMedia Modeling: 28th International Conference, MMM 2022, Phu Quoc, Vietnam, June 6–10, 2022, Proceedings, Part II. Springer, 537–542.
[12]
Andreas Leibetseder and Klaus Schoeffmann. 2021. lifexplore at the lifelog search challenge 2021. In Proceedings of the 4th Annual on Lifelog Search Challenge. 23–28.
[13]
Jakub Lokoč, František Mejzlik, Patrik Veselỳ, and Tomáš Souček. 2021. Enhanced SOMHunter for Known-item Search in Lifelog Data. In Proceedings of the 4th Annual on Lifelog Search Challenge. 71–73.
[14]
Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, 2021. Learning transferable visual models from natural language supervision. In International Conference on Machine Learning. PMLR, 8748–8763.
[15]
Konstantin Schall, Kai Uwe Barthel, Nico Hezel, and Klaus Jung. 2022. GPR1200: A Benchmark for General-Purpose Content-Based Image Retrieval. In International Conference on Multimedia Modeling. Springer, 205–216.
[16]
Christoph Schuhmann, Romain Beaumont, Richard Vencu, Cade Gordon, Ross Wightman, Mehdi Cherti, Theo Coombes, Aarush Katta, Clayton Mullis, Mitchell Wortsman, 2022. Laion-5b: An open large-scale dataset for training next generation image-text models. arXiv preprint arXiv:2210.08402 (2022).
[17]
Christoph Schuhmann, Richard Vencu, Romain Beaumont, Robert Kaczmarczyk, Clayton Mullis, Aarush Katta, Theo Coombes, Jenia Jitsev, and Aran Komatsuzaki. 2021. Laion-400m: Open dataset of clip-filtered 400 million image-text pairs. arXiv preprint arXiv:2111.02114 (2021).
[18]
Jihye Shin, Alexandra Waldau, Aaron Duane, and Björn Þór Jónsson. 2021. PhotoCube at the Lifelog Search Challenge 2021. In Proceedings of the 4th Annual on Lifelog Search Challenge. 59–63.
[19]
Florian Spiess and Heiko Schuldt. 2022. Multimodal Interactive Lifelog Retrieval with vitrivr-VR. In Proceedings of the 5th Annual on Lifelog Search Challenge. 38–42.
[20]
Mingxing Tan and Quoc Le. 2019. Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning. PMLR, 6105–6114.
[21]
Ly-Duyen Tran, Naushad Alam, Yvette Graham, Linh Khanh Vo, Nghiem Tuong Diep, Binh Nguyen, Liting Zhou, and Cathal Gurrin. 2022. An Exploration into the Benefits of the CLIP model for Lifelog Retrieval. In Proceedings of the 19th International Conference on Content-based Multimedia Indexing. 15–22.
[22]
Ly-Duyen Tran, Manh-Duy Nguyen, Duc-Tien Dang-Nguyen, Silvan Heller, Florian Spiess, Jakub Lokoč, Ladislav Peška, Thao-Nhu Nguyen, Omar Shahbaz Khan, Aaron Duane, 2023. Comparing Interactive Retrieval Approaches at the Lifelog Search Challenge 2021. IEEE Access (2023).
[23]
Ly-Duyen Tran, Manh-Duy Nguyen, Binh Nguyen, Hyowon Lee, Liting Zhou, and Cathal Gurrin. 2022. E-Myscéal: Embedding-based Interactive Lifelog Retrieval System for LSC’22. In Proceedings of the 5th Annual on Lifelog Search Challenge. 32–37.
[24]
Ly-Duyen Tran, Manh-Duy Nguyen, Nguyen Thanh Binh, Hyowon Lee, and Cathal Gurrin. 2021. Myscéal 2.0: A Revised Experimental Interactive Lifelog Retrieval System for LSC’21. In Proceedings of the 4th Annual on Lifelog Search Challenge. 11–16.
[25]
Chien-Yao Wang, Alexey Bochkovskiy, and Hong-Yuan Mark Liao. 2022. YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arXiv preprint arXiv:2207.02696 (2022).
[26]
Bolei Zhou, Agata Lapedriza, Aditya Khosla, Aude Oliva, and Antonio Torralba. 2018. Places: A 10 million Image Database for Scene Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 40, 6 (2018), 1452–1464. https://doi.org/10.1109/TPAMI.2017.2723009

Cited By

View all
  • (2024)Introduction to the Seventh Annual Lifelog Search Challenge, LSC'24Proceedings of the 2024 International Conference on Multimedia Retrieval10.1145/3652583.3658891(1334-1335)Online publication date: 30-May-2024
  • (2024)Searching Temporally Distant Activities in Lifelog Data With PraK Tool V2Proceedings of the 7th Annual ACM Workshop on the Lifelog Search Challenge10.1145/3643489.3661131(111-116)Online publication date: 10-Jun-2024
  • (2024)Voxento-Pro: An Advanced Voice Lifelog Retrieval Interaction for Multimodal LifelogsProceedings of the 7th Annual ACM Workshop on the Lifelog Search Challenge10.1145/3643489.3661130(105-110)Online publication date: 10-Jun-2024
  • Show More Cited By

Recommendations

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Conferences
LSC '23: Proceedings of the 6th Annual ACM Lifelog Search Challenge
June 2023
74 pages
This work is licensed under a Creative Commons Attribution International 4.0 License.

Sponsors

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 12 June 2023

Check for updates

Author Tags

  1. interactive image retrieval
  2. lifelogging
  3. multimedia indexing

Qualifiers

  • Research-article
  • Research
  • Refereed limited

Conference

ICMR '23
Sponsor:

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • Downloads (Last 12 months)319
  • Downloads (Last 6 weeks)31
Reflects downloads up to 07 Mar 2025

Other Metrics

Citations

Cited By

View all
  • (2024)Introduction to the Seventh Annual Lifelog Search Challenge, LSC'24Proceedings of the 2024 International Conference on Multimedia Retrieval10.1145/3652583.3658891(1334-1335)Online publication date: 30-May-2024
  • (2024)Searching Temporally Distant Activities in Lifelog Data With PraK Tool V2Proceedings of the 7th Annual ACM Workshop on the Lifelog Search Challenge10.1145/3643489.3661131(111-116)Online publication date: 10-Jun-2024
  • (2024)Voxento-Pro: An Advanced Voice Lifelog Retrieval Interaction for Multimodal LifelogsProceedings of the 7th Annual ACM Workshop on the Lifelog Search Challenge10.1145/3643489.3661130(105-110)Online publication date: 10-Jun-2024
  • (2024)MEMORIA: A Memory Enhancement and MOment RetrIeval Application at the LSC2024Proceedings of the 7th Annual ACM Workshop on the Lifelog Search Challenge10.1145/3643489.3661129(99-104)Online publication date: 10-Jun-2024
  • (2024)Memento 4.0: A Prototype Conversational Search System for LSC'24Proceedings of the 7th Annual ACM Workshop on the Lifelog Search Challenge10.1145/3643489.3661126(82-87)Online publication date: 10-Jun-2024
  • (2024)Libro - Lifelog Search BrowserProceedings of the 7th Annual ACM Workshop on the Lifelog Search Challenge10.1145/3643489.3661124(70-75)Online publication date: 10-Jun-2024
  • (2024)lifeXplore at the Lifelog Search Challenge 2024Proceedings of the 7th Annual ACM Workshop on the Lifelog Search Challenge10.1145/3643489.3661123(64-69)Online publication date: 10-Jun-2024
  • (2024)LifeSeeker 6.0: Leveraging the linguistic aspect of the lifelog system in LSC'24Proceedings of the 7th Annual ACM Workshop on the Lifelog Search Challenge10.1145/3643489.3661121(53-57)Online publication date: 10-Jun-2024
  • (2024)General Purpose Multimedia Retrieval with vitrivr at LSC'24Proceedings of the 7th Annual ACM Workshop on the Lifelog Search Challenge10.1145/3643489.3661120(47-52)Online publication date: 10-Jun-2024
  • (2024)T@Retrospect: A Journey Through TimeProceedings of the 7th Annual ACM Workshop on the Lifelog Search Challenge10.1145/3643489.3661118(36-40)Online publication date: 10-Jun-2024
  • Show More Cited By

View Options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

HTML Format

View this article in HTML Format.

HTML Format

Login options

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media