# PHD-GIFs: Personalized Highlight Detection for Automatic GIF Creation

arXiv: https://arxiv.org/abs/1804.06604 · HTML: https://mlsanity.com/paper/1804.06604/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Apr 2018.

## Built on by (most cited first, 19 of 19)

- [QVHighlights: Detecting Moments and Highlights in Videos via Natural Language Queries](https://mlsanity.com/paper/2107.09609/) (2021)
- [TR-DETR: Task-Reciprocal Transformer for Joint Moment Retrieval and Highlight Detection](https://mlsanity.com/paper/2401.02309/) (2024)
- [Task-Driven Exploration: Decoupling and Inter-Task Feedback for Joint Moment Retrieval and Highlight Detection](https://mlsanity.com/paper/2404.09263/) (2024)
- [Learning Pixel-Level Distinctions for Video Highlight Detection](https://mlsanity.com/paper/2204.04615/) (2022)
- [AssistSR: Task-oriented Video Segment Retrieval for Personal AI Assistant](https://mlsanity.com/paper/2111.15050/) (2021)
- [PR-Net: Preference Reasoning for Personalized Video Highlight Detection](https://mlsanity.com/paper/2109.01799/) (2021)
- [Video Summarization Overview](https://mlsanity.com/paper/2210.11707/) (2022)
- [Personal Salience: Highlighting Is Social, but Individuality Lives in Selection](https://mlsanity.com/paper/2606.09024/) (2026)
- [Selection, Not Salience: The Shape and Limits of Personalization in Social Highlighting](https://mlsanity.com/paper/2606.10398/) (2026)
- [HighlightMe: Detecting Highlights from Human-Centric Videos](https://mlsanity.com/paper/2110.01774/) (2021)
- [Show Me What I Like: Detecting User-Specific Video Highlights Using Content-Based Multi-Head Attention](https://mlsanity.com/paper/2207.08352/) (2022)
- [ContentCTR: Frame-level Live Streaming Click-Through Rate Prediction with Multimodal Transformer](https://mlsanity.com/paper/2306.14392/) (2023)
- [A Multimodal Transformer for Live Streaming Highlight Prediction](https://mlsanity.com/paper/2407.12002/) (2024)
- [Audiovisual Highlight Detection in Videos](https://mlsanity.com/paper/2102.05811/) (2021)
- [Exploring Domain Incremental Video Highlights Detection with the LiveFood Benchmark](https://mlsanity.com/paper/2209.05166/) (2022)
- [FedAPM: Federated Learning via ADMM with Partial Model Personalization](https://mlsanity.com/paper/2506.04672/) (2025)
- [Factions Within, Uncertain Across: Within-Document Reader Sub-Groups in Social Highlighting](https://mlsanity.com/paper/2606.11613/) (2026)
- [SVHighlights: Towards Extremely Long Sport Video Highlight Detection](https://mlsanity.com/paper/2606.06926/) (2026)
- [TRINITY: A Multi-Perspective Benchmark for Personal-Style Video Highlight Detection](https://mlsanity.com/paper/2608.29577/) (2026)

## Abstract (arXiv)

Highlight detection models are typically trained to identify cues that make visual content appealing or interesting for the general public, with the objective of reducing a video to such moments. However, the "interestingness" of a video segment or image is subjective. Thus, such highlight models provide results of limited relevance for the individual user. On the other hand, training one model per user is inefficient and requires large amounts of personal information which is typically not available. To overcome these limitations, we present a global ranking model which conditions on each particular user's interests. Rather than training one model per user, our model is personalized via its inputs, which allows it to effectively adapt its predictions, given only a few user-specific examples. To train this model, we create a large-scale dataset of users and the GIFs they created, giving us an accurate indication of their interests. Our experiments show that using the user history substantially improves the prediction accuracy. On our test set of 850 videos, our model improves the recall by 8% with respect to generic highlight detectors. Furthermore, our method proves more precise than the user-agnostic baselines even with just one person-specific example.