QVHighlights: Detecting Moments and Highlights in Videos via Natural Language Queries

By Jie Lei, Tamara L. Berg, Mohit Bansal. 2021

108 citations recorded by the source corpus.

Detecting customized moments and highlights from videos given natural language (NL) user queries is an important but under-studied topic. One of the challenges in pursuing this direction is the lack of annotated data. To address this issue, we present the Query-based Video Highlights (QVHIGHLIGHTS) dataset. It consists of over 10,000 YouTube videos, covering a wide range of topics, from everyday activities and travel in lifestyle vlog videos to social and political activities in news videos. Each video in the dataset is annotated with: (1) a human-written free-form NL query, (2) relevant moments in the video w.r.t. the query, and (3) five-point scale saliency scores for all query-relevant clips. This comprehensive annotation enables us to develop and evaluate systems that detect relevant moments as well as salient highlights for diverse, flexible user queries. We also present a strong baseline for this task, Moment-DETR, a transformer encoder-decoder model that views moment retrieval as a direct set prediction problem, taking extracted video and query representations as inputs and predicting moment coordinates and saliency scores end-to-end. While our model does not utilize any human prior, we show that it performs competitively when compared to well-engineered architectures. With weakly supervised pretraining using ASR captions, MomentDETR substantially outperforms previous methods. Lastly, we present several ablations and visualizations of Moment-DETR. Data and code is publicly available at https://github.com/jayleicn/moment_detr

Subfields: Computer Vision and Pattern Recognition, Multimodal Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Yu Qiao
2. Yali Wang
3. Limin Wang
4. Kunchang Li
5. Yi Wang
6. Luc Van Gool
7. Yinan He
8. Xiaoou Tang

In Multimodal Learning

1. Yu Qiao
2. Yali Wang
3. Yinan He
4. Yi Wang
5. Xu Sun
6. Limin Wang
7. Kunchang Li

Citations in the corpus

• TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding (2023, methodology): “Instead, human attention is consistently drawn to meaningful or highlighted visual segments such as essential steps in a cooking tutorial [60] or fantastic moments from sports events [15].”
• InternVideo2: Scaling Foundation Models for Multimodal Video Understanding (2024, methodology): “We evaluate InternVideo2 on two video temporal grounding (VTG) datasets: Qvhighlight [Lei et al., 2021], and Charade-STA [Gao et al., 2017].”