# Towards Effective Long-Video Event Prediction via Multi-Level Event Semantics Mining

arXiv: https://arxiv.org/abs/2605.31069 · HTML: https://mlsanity.com/paper/2605.31069/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 33 references that are in the map.
- First posted on arXiv 29 May 2026.

## Builds on (most cited first, 15 of 15)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [WhisperX: Time-Accurate Speech Transcription of Long-Form Audio](https://mlsanity.com/paper/2303.00747/) (2023)
- [LongVILA: Scaling Long-Context Visual Language Models for Long Videos](https://mlsanity.com/paper/2408.10188/) (2024)
- [Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension](https://mlsanity.com/paper/2411.13093/) (2024)
- [Approaching Human-Level Forecasting with Language Models](https://mlsanity.com/paper/2402.18563/) (2024)
- [LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via a Hybrid Architecture](https://mlsanity.com/paper/2409.02889/) (2024)
- [Video-CCAM: Enhancing Video-Language Understanding with Causal Cross-Attention Masks for Short and Long Videos](https://mlsanity.com/paper/2408.14023/) (2024)
- [What is More Likely to Happen Next? Video-and-Language Future Event Prediction](https://mlsanity.com/paper/2010.07999/) (2020)
- [The Future is not One-dimensional: Complex Event Schema Induction by Graph Modeling for Event Prediction](https://mlsanity.com/paper/2104.06344/) (2021)
- [Goldfish: Vision-Language Understanding of Arbitrarily Long Videos](https://mlsanity.com/paper/2407.12679/) (2024)
- [StoryTeller: Improving Long Video Description through Global Audio-Visual Character Identification](https://mlsanity.com/paper/2411.07076/) (2024)
- [DreamFrame: Enhancing Video Understanding via Automatically Generated QA and Style-Consistent Keyframes](https://mlsanity.com/paper/2403.01422/) (2024)
- [Long Story Short: Story-level Video Understanding from 20K Short Films](https://mlsanity.com/paper/2406.10221/) (2024)
- [Generating Event-oriented Attribution for Movies via Two-Stage Prefix-Enhanced Multimodal LLM](https://mlsanity.com/paper/2409.09362/) (2024)

## Abstract (arXiv)

Accurately predicting future events is fundamental to content understanding and decision-making across various domains. While prior research has primarily focused on text or short-video scenarios, long-video event prediction, characterized by vast multimodal context and more complex narratives, remains underexplored. Meanwhile, although recent Long-Video Language Models (LVLMs), built on Large Language Models (LLMs) and Vision-Language Models (VLMs), have shown promise in long-video question answering and summarization, they struggle to generalize to event prediction, as they can neither precisely extract event-related details nor perform fine-grained analysis of event development. To address this gap, we propose VISTA, a multi-level event semantics mining framework for long-video event prediction. Initially, VISTA applies a character-centric visual prompt to precisely extract event-related visual details, enhancing detail-level semantics; subsequently, it employs a knowledge-enhanced iterative retrieval strategy, guiding the LLM to progressively construct logically coherent event chains, thereby improving event-level narratives; ultimately, VISTA adopts a human-like propose-then-retrieve strategy to generate diverse future-oriented proposals and integrate multi-level clues, producing robust and accurate predictions. Extensive experiments on real-world datasets validate the effectiveness of VISTA for long-video event prediction.