Enhancing Scene Transition Awareness in Video Generation via Post-Training

• URL: http://arxiv.org/abs/2507.18046v1
• Date: Thu, 24 Jul 2025 02:50:26 GMT
• Title: Enhancing Scene Transition Awareness in Video Generation via Post-Training
• Authors: Hanwen Shen, Jiajie Lu, Yupeng Cao, Xiaonan Yang,
• Abstract summary: We propose the textbfTransition-Aware Video dataset, which consists of preprocessed video clips with multiple scene transitions.<n>Our experiment shows that post-training on the textbfTAV dataset improves prompt-based scene transition understanding, narrows the gap between required and generated scenes, and maintains image quality.
• Score: 0.4199844472131921
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advances in AI-generated video have shown strong performance on \emph{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 \textbf{Transition-Aware Video} (TAV) dataset, which consists of preprocessed video clips with multiple scene transitions. Our experiment shows that post-training on the \textbf{TAV} dataset improves prompt-based scene transition understanding, narrows the gap between required and generated scenes, and maintains image quality.

Related papers

• From Long Videos to Engaging Clips: A Human-Inspired Video Editing Framework with Multimodal Narrative Understanding [17.769963004697047]
  We propose a human-inspired automatic video editing framework (HIVE)<n>Our approach incorporates character extraction, dialogue analysis, and narrative summarization through multimodal large language models.<n>Our framework consistently outperforms existing baselines across both general and advertisement-oriented editing tasks.
  arXiv  Detail & Related papers  (2025-07-03T16:54:32Z)
• Long Context Tuning for Video Generation [63.060794860098795]
  Long Context Tuning (LCT) is a training paradigm that expands the context window of pre-trained single-shot video diffusion models.<n>Our method expands full attention mechanisms from individual shots to encompass all shots within a scene.<n>Experiments demonstrate coherent multi-shot scenes and exhibit emerging capabilities, including compositional generation and interactive shot extension.
  arXiv  Detail & Related papers  (2025-03-13T17:40:07Z)
• Contrastive Sequential-Diffusion Learning: Non-linear and Multi-Scene Instructional Video Synthesis [9.687215124767063]
  We propose a contrastive sequential video diffusion method that selects the most suitable previously generated scene to guide and condition the denoising process of the next scene.<n>Experiments with action-centered data from the real world demonstrate the practicality and improved consistency of our model compared to previous work.
  arXiv  Detail & Related papers  (2024-07-16T15:03:05Z)
• Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization [52.63845811751936]
  Video pre-training is challenging due to the modeling of its dynamics video. In this paper, we address such limitations in video pre-training with an efficient video decomposition. Our framework is both capable of comprehending and generating image and video content, as demonstrated by its performance across 13 multimodal benchmarks.
  arXiv  Detail & Related papers  (2024-02-05T16:30:49Z)
• VideoStudio: Generating Consistent-Content and Multi-Scene Videos [88.88118783892779]
  VideoStudio is a framework for consistent-content and multi-scene video generation. VideoStudio leverages Large Language Models (LLM) to convert the input prompt into comprehensive multi-scene script. VideoStudio outperforms the SOTA video generation models in terms of visual quality, content consistency, and user preference.
  arXiv  Detail & Related papers  (2024-01-02T15:56:48Z)
• SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction [93.26613503521664]
  This paper presents a short-to-long video diffusion model, SEINE, that focuses on generative transition and prediction. We propose a random-mask video diffusion model to automatically generate transitions based on textual descriptions. Our model generates transition videos that ensure coherence and visual quality.
  arXiv  Detail & Related papers  (2023-10-31T17:58:17Z)
• HierVL: Learning Hierarchical Video-Language Embeddings [108.77600799637172]
  HierVL is a novel hierarchical video-language embedding that simultaneously accounts for both long-term and short-term associations. We introduce a hierarchical contrastive training objective that encourages text-visual alignment at both the clip level and video level. Our hierarchical scheme yields a clip representation that outperforms its single-level counterpart as well as a long-term video representation that achieves SotA.
  arXiv  Detail & Related papers  (2023-01-05T21:53:19Z)
• AutoTransition: Learning to Recommend Video Transition Effects [20.384463765702417]
  We present the premier work on performing automatic video transitions recommendation (VTR) VTR is given a sequence of raw video shots and companion audio, recommend video transitions for each pair of neighboring shots. We propose a novel multi-modal matching framework which consists of two parts.
  arXiv  Detail & Related papers  (2022-07-27T12:00:42Z)
• Scene Consistency Representation Learning for Video Scene Segmentation [26.790491577584366]
  We propose an effective Self-Supervised Learning (SSL) framework to learn better shot representations from long-term videos. We present an SSL scheme to achieve scene consistency, while exploring considerable data augmentation and shuffling methods to boost the model generalizability. Our method achieves the state-of-the-art performance on the task of Video Scene.
  arXiv  Detail & Related papers  (2022-05-11T13:31:15Z)
• Beyond Short Clips: End-to-End Video-Level Learning with Collaborative Memories [56.91664227337115]
  We introduce a collaborative memory mechanism that encodes information across multiple sampled clips of a video at each training iteration. This enables the learning of long-range dependencies beyond a single clip. Our proposed framework is end-to-end trainable and significantly improves the accuracy of video classification at a negligible computational overhead.
  arXiv  Detail & Related papers  (2021-04-02T18:59:09Z)

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.