✍️ Web Science and Digital Libraries Research Group Trip Report from CIKM 2024 in Boise, ID is now published! ✨
Check out the highlights, brought to you by @Lesley, Gangani, and I: https://ws-dl.blogspot.com/2024/11/2024-11-15-33rd-acm-international.html
Big thanks to National Science Foundation (NSF) and Computer Science Graduate Society of Department of Computer Science at Old Dominion University for providing us with travel grants that made our attendance possible!🤝
Another contribution #CIKM2024 came from Axel Ngonga, who introduced "ExPrompt: Augmenting Prompts Using Examples as Modern Baseline for Stance Classification" by Umair Qudus, Michael Röder, Daniel Vollmers & Axel Ngonga.🤩 🤝
➡️ Have a look: https://papers.dice-research.org/2024/CIKM_ExPrompt/public.pdf
DICE is also represented twice at #CIKM2024 in Boise/Idaho 🇺🇸 this week: Rupesh Sapkota presented “EDGE: Evaluation Framework for Logical vs. Subgraph Explanations for Node Classifiers on Knowledge Graphs” by Rupesh Sapkota, Dominik Köhler & Stefan Heindorf.👏😊
Slides for our #cikm2024 presentation, "To Re-experience the Web: A Framework for the Transformation and Replay of Archived Web Pages" are now available at:
👉https://matkelly.com/cikm2024
Thanks to Himarsha Jayanetti & @Lesley for presenting our work in Boise! #WebArchiveWednesday #webarchiving
Excited to share that I'll be presenting our paper, "VHAKG: A Multi-modal Knowledge Graph Based on Synchronized Multi-view Videos of Daily Activities," at CIKM2024!
Looking forward to engaging in discussions on the fusion of multi-modal #KnowledgeGraphs and #LLMs in Boise, USA #CIKM2024
arXiv: https://arxiv.org/abs/2408.14895
Datasets: https://github.com/aistairc/vhakg
Tools: https://github.com/aistairc/vhakg-tools
Multi-modal knowledge graphs (MMKGs), which ground various non-symbolic data (e.g., images and videos) into symbols, have attracted attention as resources enabling knowledge processing and machine learning across modalities. However, the construction of MMKGs for videos consisting of multiple events, such as daily activities, is still in the early stages. In this paper, we construct an MMKG based on synchronized multi-view simulated videos of daily activities. Besides representing the content of daily life videos as event-centric knowledge, our MMKG also includes frame-by-frame fine-grained changes, such as bounding boxes within video frames. In addition, we provide support tools for querying our MMKG. As an application example, we demonstrate that our MMKG facilitates benchmarking vision-language models by providing the necessary vision-language datasets for a tailored task.
Our ACM Transactions on the Web article* has been invited to be presented at #CIKM2024 (https://www.cikm2024.org/). Looking forward to seeing folks in Boise this October! #webarchiving
Himarsha Jayanetti
DICE
SAIL Research Network
Mat Kelly
Alan Said
Shusaku Egami