What Would You Click? Personalized Video Thumbnail Generation with Preference-aware Highlight Retrieval

• URL: http://arxiv.org/abs/2607.12882v1
• Date: Tue, 14 Jul 2026 15:30:09 GMT
• Title: What Would You Click? Personalized Video Thumbnail Generation with Preference-aware Highlight Retrieval
• Abstract summary: We introduce personalized video thumbnail generation, a novel task that aims to create thumbnails tailored to user-specific preferences.<n>We propose a two-stage framework that tightly couples preference-aware retrieval with controllable generation.<n> Experiments on two public datasets show our method delivers state-of-the-art performance compared with retrieval-based and generative baselines.
• Score: 42.25948839538674
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Video thumbnails are a key factor for attracting user clicks on video platforms, and are increasingly supported by automation. However, existing thumbnail generation methods typically produce generic results shared across users, overlooking the diversity of individual preferences. We therefore introduce personalized video thumbnail generation, a novel task that aims to create thumbnails tailored to user-specific preferences. It is challenging in two aspects: (i) identifying visual anchors (i.e., key frames) from each video to guide the generation, which requires a balance between personalization and informativeness that existing highlight detection methods fail to achieve; and (ii) generating personalized thumbnails that are both visually coherent and faithful to the original video. As a response, we propose a two-stage framework that tightly couples preference-aware retrieval with controllable generation. In the first stage, a personalized highlight retriever captures fine-grained user-video interactions and incorporates video semantics through summarization, enabling the selection of diverse visual anchors aligned with both user preferences and video contexts. In the second stage, a VLM-guided diffusion pipeline transforms these anchors into thumbnails by extracting and injecting semantically grounded visual cues, improving personalization while preserving visual coherence and fidelity. Experiments on two public datasets show our method delivers state-of-the-art performance compared with both retrieval-based and generative baselines. A user study further demonstrates improved click preference, highlighting its effectiveness in enhancing user engagement. The code is available at https://github.com/hezy18/PVTG.

Related papers

• EdgeVidSum: Real-Time Personalized Video Summarization at the Edge [3.102586911584193]
  EdgeVidSum is a method that generates personalized, fast-forward summaries of long-form videos directly on edge devices.<n>The framework employs a hierarchical analysis approach, where a lightweight 2D CNN model identifies user-preferred content from thumbnails.<n>Our interactive demo highlights the system's ability to create tailored video summaries for long-form videos, such as movies, sports events, and TV shows, based on individual user preferences.
  arXiv  Detail & Related papers  (2025-05-28T18:59:41Z)
• Multi-subject Open-set Personalization in Video Generation [110.02124633005516]
  We present Video Alchemist $-$ a video model with built-in multi-subject, open-set personalization capabilities.<n>Our model is built on a new Diffusion Transformer module that fuses each conditional reference image and its corresponding subject-level text prompt.<n>Our method significantly outperforms existing personalization methods in both quantitative and qualitative evaluations.
  arXiv  Detail & Related papers  (2025-01-10T18:59:54Z)
• Personalized Video Summarization by Multimodal Video Understanding [2.1372652192505703]
  We present a pipeline called Video Summarization with Language (VSL) for user-preferred video summarization. VSL is based on pre-trained visual language models (VLMs) to avoid the need to train a video summarization system on a large training dataset. We show that our method is more adaptable across different datasets compared to supervised query-based video summarization models.
  arXiv  Detail & Related papers  (2024-11-05T22:14:35Z)
• CustomVideo: Customizing Text-to-Video Generation with Multiple Subjects [74.61964363605632]
  Current approaches for personalizing text-to-video generation suffer from tackling multiple subjects.<n>We propose CustomVideo, a novel framework that can generate identity-preserving videos with the guidance of multiple subjects.
  arXiv  Detail & Related papers  (2024-01-18T13:23:51Z)
• Show Me What I Like: Detecting User-Specific Video Highlights Using Content-Based Multi-Head Attention [52.84233165201391]
  We propose a method to detect individualized highlights for users on given target videos based on their preferred highlight clips marked on previous videos they have watched. Our method explicitly leverages the contents of both the preferred clips and the target videos using pre-trained features for the objects and the human activities.
  arXiv  Detail & Related papers  (2022-07-18T02:32:48Z)
• Towards Micro-video Thumbnail Selection via a Multi-label Visual-semantic Embedding Model [0.0]
  The thumbnail, as the first sight of a micro-video, plays a pivotal role in attracting users to click and watch. We present a multi-label visual-semantic embedding model to estimate the similarity between the pair of each frame and the popular topics that users are interested in. We fuse the visual representation score and the popularity score of each frame to select the attractive thumbnail for the given micro-video.
  arXiv  Detail & Related papers  (2022-02-07T04:15:26Z)
• ASCNet: Self-supervised Video Representation Learning with Appearance-Speed Consistency [62.38914747727636]
  We study self-supervised video representation learning, which is a challenging task due to 1) a lack of labels for explicit supervision and 2) unstructured and noisy visual information. Existing methods mainly use contrastive loss with video clips as the instances and learn visual representation by discriminating instances from each other. In this paper, we observe that the consistency between positive samples is the key to learn robust video representations.
  arXiv  Detail & Related papers  (2021-06-04T08:44:50Z)
• Broaden Your Views for Self-Supervised Video Learning [97.52216510672251]
  We introduce BraVe, a self-supervised learning framework for video. In BraVe, one of the views has access to a narrow temporal window of the video while the other view has a broad access to the video content. We demonstrate that BraVe achieves state-of-the-art results in self-supervised representation learning on standard video and audio classification benchmarks.
  arXiv  Detail & Related papers  (2021-03-30T17:58:46Z)

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.