# Enhancing Scene Transition Awareness in Video Generation via Post-Training

arXiv: https://arxiv.org/abs/2507.18046 · HTML: https://mlsanity.com/paper/2507.18046/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 77 references that are in the map.
- First posted on arXiv 24 Jul 2025.

## Builds on (most cited first, 30 of 39)

- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval](https://mlsanity.com/paper/2104.00650/) (2021)
- [CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers](https://mlsanity.com/paper/2205.15868/) (2022)
- [HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips](https://mlsanity.com/paper/1906.03327/) (2019)
- [Conditional Image Generation with PixelCNN Decoders](https://mlsanity.com/paper/1606.05328/) (2016)
- [Dense-Captioning Events in Videos](https://mlsanity.com/paper/1705.00754/) (2017)
- [VideoGPT: Video Generation using VQ-VAE and Transformers](https://mlsanity.com/paper/2104.10157/) (2021)
- [GAIA-1: A Generative World Model for Autonomous Driving](https://mlsanity.com/paper/2309.17080/) (2023)
- [Towards Automatic Learning of Procedures from Web Instructional Videos](https://mlsanity.com/paper/1703.09788/) (2017)
- [Video Enhancement with Task-Oriented Flow](https://mlsanity.com/paper/1711.09078/) (2017)
- [StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets](https://mlsanity.com/paper/2202.00273/) (2022)
- [Unsupervised Learning of Video Representations using LSTMs](https://mlsanity.com/paper/1502.04681/) (2015)
- [Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers](https://mlsanity.com/paper/2402.19479/) (2024)
- [Latent Video Diffusion Models for High-Fidelity Long Video Generation](https://mlsanity.com/paper/2211.13221/) (2022)
- [A Short Note on the Kinetics-700 Human Action Dataset](https://mlsanity.com/paper/1907.06987/) (2019)
- [Deep Visual Foresight for Planning Robot Motion](https://mlsanity.com/paper/1610.00696/) (2016)
- [StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text](https://mlsanity.com/paper/2403.14773/) (2024)
- [Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer](https://mlsanity.com/paper/2204.03638/) (2022)
- [SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction](https://mlsanity.com/paper/2310.20700/) (2023)
- [Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions](https://mlsanity.com/paper/2111.10337/) (2021)
- [Moments in Time Dataset: one million videos for event understanding](https://mlsanity.com/paper/1801.03150/) (2018)
- [FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling](https://mlsanity.com/paper/2310.15169/) (2023)
- [NUWA-XL: Diffusion over Diffusion for eXtremely Long Video Generation](https://mlsanity.com/paper/2303.12346/) (2023)
- [MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captions](https://mlsanity.com/paper/2407.06358/) (2024)
- [VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planning](https://mlsanity.com/paper/2309.15091/) (2023)
- [Gen-L-Video: Multi-Text to Long Video Generation via Temporal Co-Denoising](https://mlsanity.com/paper/2305.18264/) (2023)
- [Video Pixel Networks](https://mlsanity.com/paper/1610.00527/) (2016)

## Built on by (most cited first, 1 of 1)

- [TransVLM: A Vision-Language Framework and Benchmark for Detecting Any Shot Transitions](https://mlsanity.com/paper/2604.27975/) (2026)

## Abstract (arXiv)

Recent advances in AI-generated video have shown strong performance on text-to-video tasks, particularly for short clips depicting a single scene. However, current models struggle to generate longer videos with coherent scene transitions, primarily because they cannot infer when a transition is needed from the prompt. Most open-source models are trained on datasets consisting of single-scene video clips, which limits their capacity to learn and respond to prompts requiring multiple scenes. Developing scene transition awareness is essential for multi-scene generation, as it allows models to identify and segment videos into distinct clips by accurately detecting transitions. To address this, we propose the Transition-Aware Video (TAV) dataset, which consists of preprocessed video clips with multiple scene transitions. Our experiment shows that post-training on the TAV dataset improves prompt-based scene transition understanding, narrows the gap between required and generated scenes, and maintains image quality.