CuriosAI submits CASTLE Challenge paper with SVA and TMKG approaches

CuriosAI has submitted a paper detailing their approach to the CASTLE Challenge, which involves answering multiple-choice questions based on extensive egocentric video data. Their primary method, SVA (Search-Verify-Answer), employs a three-stage pipeline that refines potential answers using a Vision-Language Model (VLM) and an LLM judge, achieving an accuracy of 0.50. A secondary approach, TMKG (Temporal-Multimodal-Knowledge-Graph), builds a knowledge graph from the video data but achieved a lower accuracy of 0.35. AI

IMPACT This research explores novel methods for video understanding and question answering, potentially advancing multimodal AI capabilities.

RANK_REASON The cluster contains a research paper submission for a challenge, detailing novel approaches. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• CASTLE Challenge
• CuriosAI
• EgoVis 2026
• LLM
• TMKG
• VLM

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →