Event-Causal RAG: A Retrieval-Augmented Generation Framework for Long Video Reasoning in Complex Scenarios
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913098776969216 |
|---|---|
| author | Yan, Peizheng Zhao, Yu Xie, Liang Qi, Juntong Wang, Mingming Yin, Erwei |
| author_facet | Yan, Peizheng Zhao, Yu Xie, Liang Qi, Juntong Wang, Mingming Yin, Erwei |
| contents | Recent large vision-language models have achieved strong performance on short- and medium-length video understanding, yet they remain inadequate for ultra-long or even infinite video reasoning, where models must preserve coherent memory over extended durations and infer causal dependencies across temporally distant events. Existing end-to-end video understanding methods are fundamentally limited by the $O(n^2)$ complexity of self-attention, while recent retrieval-augmented generation (RAG) approaches still suffer from fragmented clip-level memory, weak modeling of temporal and causal structure, and high storage and online inference costs. We present Event-Causal RAG, a lightweight retrieval-augmented framework for infinite long-video reasoning. Instead of indexing fixed-length clips, our method segments streaming videos into semantically coherent events and represents each event as a structured State-Event-State (SES) graph, capturing the event together with its surrounding state transitions. These graphs are merged into a global Event Knowledge Graph and stored in a dual-store memory that supports both semantic matching and causal-topological retrieval. On top of this memory, we design a bidirectional retrieval strategy to efficiently identify the most relevant event causal chains and provide them, together with the associated video evidence, to a backbone video foundation model for answer generation. Experiments on long-video understanding benchmarks demonstrate that Event-Causal RAG consistently outperforms strong clip-based retrieval baselines and long-context video models, particularly on questions requiring multi-event integration and causal inference across long temporal gaps, while also achieving improved memory efficiency and robust streaming performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_06185 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Event-Causal RAG: A Retrieval-Augmented Generation Framework for Long Video Reasoning in Complex Scenarios Yan, Peizheng Zhao, Yu Xie, Liang Qi, Juntong Wang, Mingming Yin, Erwei Artificial Intelligence Computer Vision and Pattern Recognition Recent large vision-language models have achieved strong performance on short- and medium-length video understanding, yet they remain inadequate for ultra-long or even infinite video reasoning, where models must preserve coherent memory over extended durations and infer causal dependencies across temporally distant events. Existing end-to-end video understanding methods are fundamentally limited by the $O(n^2)$ complexity of self-attention, while recent retrieval-augmented generation (RAG) approaches still suffer from fragmented clip-level memory, weak modeling of temporal and causal structure, and high storage and online inference costs. We present Event-Causal RAG, a lightweight retrieval-augmented framework for infinite long-video reasoning. Instead of indexing fixed-length clips, our method segments streaming videos into semantically coherent events and represents each event as a structured State-Event-State (SES) graph, capturing the event together with its surrounding state transitions. These graphs are merged into a global Event Knowledge Graph and stored in a dual-store memory that supports both semantic matching and causal-topological retrieval. On top of this memory, we design a bidirectional retrieval strategy to efficiently identify the most relevant event causal chains and provide them, together with the associated video evidence, to a backbone video foundation model for answer generation. Experiments on long-video understanding benchmarks demonstrate that Event-Causal RAG consistently outperforms strong clip-based retrieval baselines and long-context video models, particularly on questions requiring multi-event integration and causal inference across long temporal gaps, while also achieving improved memory efficiency and robust streaming performance. |
| title | Event-Causal RAG: A Retrieval-Augmented Generation Framework for Long Video Reasoning in Complex Scenarios |
| topic | Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.06185 |