Task Overview
NTCIR19-Lifelog is a core task of the NTCIR-19 conference, aiming to advance research in lifelog analytics and retrieval. The task consists of multiple sub-tasks focusing on semantic access and knowledge mining from lifelog data.
This challenge brings together researchers from around the world to develop innovative approaches for organizing, analyzing, and retrieving information from multimodal lifelog datasets, pushing the boundaries of personal information management and retrieval systems.
Sub-tasks
Lifelog Subtasks
- LSAT - Lifelog Semantic Access subTask is a known-item search task that can be undertaken in an interactive or automatic manner. A text, visual, or multimodal query is given, and participants must retrieve specific moments based on the query in a lifelogger’s life. Moments are defined as semantic events or activities.
CASTLE Subtasks
- CSAT - CASTLE Semantic Access subTask is a search-based task where participants retrieve key interactions or events from multi-modal data (e.g., audio, video, chat transcripts) based on a semantic query.
- CAST-Seg - CASTLE Conversation Segmentation subTask requires participants to segment collaborative sessions into meaningful conversational units, such as tasks, discussions, or decisions, to enable better analysis and retrieval.
- Recipe Generation - This subtask challenges participants to generate personal recipes or cooking procedures using multimodal lifelog data such as food images, eating times, nutrition tracking, and kitchen activity. It encourages creative modelling of lifestyle-driven meal preparation.