Interpretable Temporal Video Reasoning with EventGraph and EventField
- URL: http://arxiv.org/abs/2609.13258v1
- Date: Sun, 06 Sep 2026 07:33:44 GMT
- Title: Interpretable Temporal Video Reasoning with EventGraph and EventField
- Abstract summary: We present a structured temporal video reasoning pipeline built around a discrete EventGraph, a continuous EventField, and a human-readable EventGlyph view.<n>On a subset of 10 videos and 50 temporal reasoning questions, EventField+Glyph achieves 0.98 overall accuracy.<n>Results indicate that structured temporal representations can support both performance and inspectability.
- Score: 0.0
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- 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 \times 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 papers
- CapRiCorn-1K: A Comprehensive Benchmark for Video Captioning and Subject Referential Consistency Across Temporal Scales [41.187897807081875]
CapRiCorn-1K is a benchmark designed to evaluate both video captioning quality and subject referential consistency across long temporal horizons and diverse video domains.<n>Our benchmark supports both audiovisual and visual-only settings.<n>Our evaluation metrics exhibit strong correlations with the performance of downstream understanding and generation tasks conditioned on the generated captions.
arXiv Detail & Related papers (2026-06-20T08:37:32Z) - OmniVideo-100K: A Dataset for Audio-Visual Reasoning through Structured Scripts and Evidence Chains [50.186434778589415]
Current automated pipelines for audio-visual Question Answering (QA) generally adopt a video-caption-QA'' paradigm.<n>We propose an automated data engine featuring two mechanisms: textbfEntity-Anchored Video Scripting' and textbfClue-Guided QA Generation'
arXiv Detail & Related papers (2026-06-12T17:59:55Z) - BioVid: Autoregressive Video Generation with Biological Behavior Semantic Comprehension [0.0]
BioVid is a data-driven autoregressive video generation framework.<n>It learns the temporal structure of biological behaviors directly from training data.<n>It achieves a Wasserstein-1 distance of 1.24 against the ground truth.
arXiv Detail & Related papers (2026-06-07T15:23:49Z) - Foresee-to-Ground: From Predictive Temporal Perception to Evidence-Driven Reasoning for Video Temporal Grounding [86.37002814396674]
We propose Foresee-to-Ground (F2G) for Video Temporal Grounding.<n>F2G integrates Predictive Temporal Perception with Evidence-Driven Reasoning.<n>It consistently improves grounding accuracy across diverse benchmarks.
arXiv Detail & Related papers (2026-05-21T04:03:25Z) - Harnessing Synthetic Preference Data for Enhancing Temporal Understanding of Video-LLMs [54.502280390499756]
We propose TimeWarp to create a targeted synthetic temporal dataset to fine-tune the model's responses to encourage it to focus on the given input video.<n>We demonstrate that when our method is applied to existing models, it significantly improves performance on temporal understanding benchmarks.
arXiv Detail & Related papers (2025-10-04T21:48:40Z) - TimeLogic: A Temporal Logic Benchmark for Video QA [64.32208175236323]
We introduce the TimeLogic QA (TLQA) framework to automatically generate temporal logical questions.<n>We leverage 4 datasets, STAR, Breakfast, AGQA, and CrossTask, and generate 2k and 10k QA pairs for each category.<n>We assess the VideoQA model's temporal reasoning performance on 16 categories of temporal logic with varying temporal complexity.
arXiv Detail & Related papers (2025-01-13T11:12:59Z) - Constructing Holistic Spatio-Temporal Scene Graph for Video Semantic
Role Labeling [96.64607294592062]
Video Semantic Label Roleing (VidSRL) aims to detect salient events from given videos.
Recent endeavors have put forth methods for VidSRL, but they can be subject to two key drawbacks.
arXiv Detail & Related papers (2023-08-09T17:20:14Z) - Temporal Alignment Networks for Long-term Video [103.69904379356413]
We propose a temporal alignment network that ingests long term video sequences, and associated text sentences.
We train such networks from large-scale datasets, such as HowTo100M, where the associated text sentences have significant noise.
Our proposed model, trained on HowTo100M, outperforms strong baselines (CLIP, MIL-NCE) on this alignment dataset.
arXiv Detail & Related papers (2022-04-06T17:59:46Z) - Knowledge Graph Driven Approach to Represent Video Streams for
Spatiotemporal Event Pattern Matching in Complex Event Processing [5.220940151628734]
Complex Event Processing (CEP) is an event processing paradigm to perform real-time analytics over streaming data.
Video streams are complicated due to their unstructured data model and limit CEP systems to perform matching over them.
This work introduces a graph-based structure for continuous evolving video streams, which enables the CEP system to query complex video event patterns.
arXiv Detail & Related papers (2020-07-13T10:20:58Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.