Scene graphs abstract visual information into <Subject \u2013 Relation \u2013 Object> triplets<\/strong>, enabling interpretable, relational reasoning over entities. While traditionally applied to static images, dynamic scene graphs extend this reasoning to videos, capturing both instantaneous interactions and longer-term activities.<\/p>\n\n\n\n By constructing scene graphs at multiple temporal resolutions \u2014 from frame-level interactions to action segments and overarching goal sequences \u2014 THSGs retain both short-term atomic actions and long-range intentions in a unified representation. This hierarchical structure not only supports efficient indexing and retrieval of relevant moments but also facilitates graph-based reasoning for VideoQA.<\/strong> When answering a question, the model can navigate the temporal hierarchy to identify pertinent entities and interactions, aggregate evidence across frames, and reason over both short-term and long-term dependencies to produce accurate and explainable answers.<\/p>\n\n\n\n Video Question Answering (VQA) requires models to understand long, complex videos and answer questions ranging from fine-grained object details to high-level temporal reasoning. Existing systems, however, are often constrained by short context windows and limited long-term memory, causing earlier events to be forgotten and weakening their temporal understanding. These limitations make it challenging to handle … <\/p>\n![\"\"](\"https:\/\/mscvprojects.ri.cmu.edu\/2025team17\/wp-content\/uploads\/sites\/124\/2025\/05\/image-6-1024x468.png\")