Reproduce “IAE-VTG: Interaction-Aligned Action-Entity Video Temporal Grounding” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Shiwen Zhao, Qi Zhang, Sezer Karaoglu, Theo Gevers, Martin R. Oswald
IAE-VTG improves video temporal grounding by checking whether a queried entity and action occur together. FDIM separates appearance and motion evidence to model clip-level binding, while ISA adds interaction consistency to training-time Hungarian matching. On QVHighlights test, it reports 52.91% Avg. mAP versus FlashVTG’s 52.00%, a benchmark result scoped to this comparison.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.