Interpretable Temporal Video Reasoning with EventGraph and EventField

arXiv:2609.13258v1 Announce Type: cross Abstract: We present a structured temporal video reasoning pipeline built around a discrete EventGraph, a continuous EventField, and a human-readable EventGlyph view. On a calibrated EPIC-KITCHENS subset of 10 videos and 50 temporal reasoning questions, EventField+Glyph achieves 0.98 overall accuracy, which is higher than the caption baseline by +0.40 (paired p = 1.1 imes 10^{-5}) and direct VLM-only QA by +0.20 (p = 0.0063) on this subset. We further evaluate annotation-source variations, including manual, heuristic, and heuristic+Gemini pipelines, and find that the best structured method stays above the caption baseline across settings. We also include cross-video pair benchmarking and an appendix gallery of glyph outputs for all studied videos. Overall, the results indicate that structured temporal representations can support both performance and inspectability by preserving symbolic structure, capturing temporal continuity, and providing human-readable diagnostics for video reasoning.

Related

• Multi-Agent Self-Improving Reinforcement Learning for Video Reasoning
• TRACE: Temporal Retrieval with Anchored and Convergent Evidence for Long-Horizon Video Understanding
• SocialReasonBench: A Video-QA Benchmark for Social Reasoning with Counterfactual Narrative Videos
• Predict, Then Retrieve: Cross-Instance Future-State Retrieval from Video Prefixes

Source: arXiv cs.CL | 2026-09-15