VidCLearn: A Continual Learning Approach for Text-to-Video Generation

• URL: http://arxiv.org/abs/2509.16956v1
• Date: Sun, 21 Sep 2025 07:34:19 GMT
• Title: VidCLearn: A Continual Learning Approach for Text-to-Video Generation
• Authors: Luca Zanchetta, Lorenzo Papa, Luca Maiano, Irene Amerini,
• Abstract summary: VidCLearn is a continual learning framework for text-to-video generation.<n>We introduce a novel temporal consistency loss to enhance motion smoothness and a video retrieval module to provide structural guidance at inference.<n>Our architecture is also designed to be more computationally efficient than existing models while retaining satisfactory generation performance.
• Score: 11.861060763379236
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Text-to-video generation is an emerging field in generative AI, enabling the creation of realistic, semantically accurate videos from text prompts. While current models achieve impressive visual quality and alignment with input text, they typically rely on static knowledge, making it difficult to incorporate new data without retraining from scratch. To address this limitation, we propose VidCLearn, a continual learning framework for diffusion-based text-to-video generation. VidCLearn features a student-teacher architecture where the student model is incrementally updated with new text-video pairs, and the teacher model helps preserve previously learned knowledge through generative replay. Additionally, we introduce a novel temporal consistency loss to enhance motion smoothness and a video retrieval module to provide structural guidance at inference. Our architecture is also designed to be more computationally efficient than existing models while retaining satisfactory generation performance. Experimental results show VidCLearn's superiority over baseline methods in terms of visual quality, semantic alignment, and temporal coherence.

Related papers

• VideoWeave: A Data-Centric Approach for Efficient Video Understanding [54.5804686337209]
  We present VideoWeave, a simple yet effective approach to improve data efficiency by constructing synthetic long-context training samples.<n>VideoWeave reorganizes available video-text pairs to expand temporal diversity within fixed compute.<n>Our results highlight that reorganizing training data, rather than altering architectures, may offer a simple and scalable path for training video-language models.
  arXiv  Detail & Related papers  (2026-01-09T20:55:26Z)
• Dual Learning with Dynamic Knowledge Distillation and Soft Alignment for Partially Relevant Video Retrieval [53.54695034420311]
  In practice, videos are typically untrimmed in long durations with much more complicated background content.<n>We propose a novel framework that distills generalization knowledge from a powerful large-scale vision-language pre-trained model.<n>Experiment results demonstrate that our proposed model achieves state-of-the-art performance on TVR, ActivityNet, and Charades-STA datasets.
  arXiv  Detail & Related papers  (2025-10-14T08:38:20Z)
• Raccoon: Multi-stage Diffusion Training with Coarse-to-Fine Curating Videos [15.781862060265519]
  CFC-VIDS-1M is a high-quality video dataset constructed through a systematic coarse-to-fine curation pipeline.<n>We develop RACCOON, a transformer-based architecture with decoupled spatial-temporal attention mechanisms.
  arXiv  Detail & Related papers  (2025-02-28T18:56:35Z)
• DREAM: Improving Video-Text Retrieval Through Relevance-Based Augmentation Using Large Foundation Models [12.393189634359064]
  We present a novel ViDeoText Retrieval Paradigm with RElevance-based AugMentation, namely DREAM.<n>We first adopt a simple augmentation method, which generates self-similar data by randomly duplicating or dropping subwords and frames.<n>To further enrich video and text information, we propose a relevance-based augmentation method, where LLMs and VGMs generate and integrate new relevant information into the original data.
  arXiv  Detail & Related papers  (2024-04-07T21:46:47Z)
• Video-Teller: Enhancing Cross-Modal Generation with Fusion and Decoupling [79.49128866877922]
  Video-Teller is a video-language foundation model that leverages multi-modal fusion and fine-grained modality alignment. Video-Teller boosts the training efficiency by utilizing frozen pretrained vision and language modules. It capitalizes on the robust linguistic capabilities of large language models, enabling the generation of both concise and elaborate video descriptions.
  arXiv  Detail & Related papers  (2023-10-08T03:35:27Z)
• In-Style: Bridging Text and Uncurated Videos with Style Transfer for Text-Video Retrieval [72.98185525653504]
  We propose a new setting, text-video retrieval with uncurated & unpaired data, that during training utilizes only text queries together with uncurated web videos. To improve generalization, we show that one model can be trained with multiple text styles. We evaluate our model on retrieval performance over multiple datasets to demonstrate the advantages of our style transfer framework.
  arXiv  Detail & Related papers  (2023-09-16T08:48:21Z)
• VideoGen: A Reference-Guided Latent Diffusion Approach for High Definition Text-to-Video Generation [73.54366331493007]
  VideoGen is a text-to-video generation approach, which can generate a high-definition video with high frame fidelity and strong temporal consistency. We leverage an off-the-shelf text-to-image generation model, e.g., Stable Diffusion, to generate an image with high content quality from the text prompt.
  arXiv  Detail & Related papers  (2023-09-01T11:14:43Z)
• Make-Your-Video: Customized Video Generation Using Textual and Structural Guidance [36.26032505627126]
  Recent advancements in text-to-video synthesis have unveiled the potential to achieve this with prompts only. In this paper, we explore customized video generation by utilizing text as context description and motion structure. Our method, dubbed Make-Your-Video, involves joint-conditional video generation using a Latent Diffusion Model.
  arXiv  Detail & Related papers  (2023-06-01T17:43:27Z)
• DirecT2V: Large Language Models are Frame-Level Directors for Zero-Shot Text-to-Video Generation [37.25815760042241]
  This paper introduces a new framework, dubbed DirecT2V, to generate text-to-video (T2V) videos. We equip a diffusion model with a novel value mapping method and dual-softmax filtering, which do not require any additional training. The experimental results validate the effectiveness of our framework in producing visually coherent and storyful videos.
  arXiv  Detail & Related papers  (2023-05-23T17:57:09Z)
• Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generation [55.36617538438858]
  We propose a novel approach that strengthens the interaction between spatial and temporal perceptions. We curate a large-scale and open-source video dataset called HD-VG-130M.
  arXiv  Detail & Related papers  (2023-05-18T11:06:15Z)
• Video Generation from Text Employing Latent Path Construction for Temporal Modeling [70.06508219998778]
  Video generation is one of the most challenging tasks in Machine Learning and Computer Vision fields of study. In this paper, we tackle the text to video generation problem, which is a conditional form of video generation. We believe that video generation from natural language sentences will have an important impact on Artificial Intelligence.
  arXiv  Detail & Related papers  (2021-07-29T06:28:20Z)
• TiVGAN: Text to Image to Video Generation with Step-by-Step Evolutionary Generator [34.7504057664375]
  We propose a novel training framework, Text-to-Image-to-Video Generative Adversarial Network (TiVGAN), which evolves frame-by-frame and finally produces a full-length video. Step-by-step learning process helps stabilize the training and enables the creation of high-resolution video based on conditional text descriptions.
  arXiv  Detail & Related papers  (2020-09-04T06:33:08Z)

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.