QVHighlights
QVHighlights is a video moment retrieval benchmark for detecting moments and highlights in videos via natural language queries. Given a query, the model must localize the start and end times of relevant moments in the video, evaluated using metrics such as Recall@1 at a 0.5 IoU threshold.
Nova 2 Lite from Amazon currently leads the QVHighlights leaderboard with a score of 0.772 across 3 evaluated AI models.
What QVHighlights measures
QVHighlights is a multimodal benchmark that evaluates large language models on video, vision, and multimodal tasks. LLM Stats tracks 3 models on this benchmark, with a maximum possible score of 1. Current average across reported models is 0.8, with the leader reaching 0.8.
Compare leaders on the best AI for video, best AI for vision and best AI for multimodal leaderboards.
Publication
- Paper
- QVHighlights: Detecting Moments and Highlights in Videos via Natural Language Queries
- Authors
- Jie Lei, Tamara L. Berg, Mohit Bansal
- Published
- arXiv
- 2107.09609
Abstract
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
Nova 2 Lite leads with 77.2%, followed by Nova 2 Omni at 76.7% and Nova 2 Pro at 76.7%.
Progress Over Time
Interactive timeline showing model performance evolution on QVHighlights
QVHighlights Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 | Amazon | — | 1.0M | $0.30 / $2.50 | ||
| 2 | Amazon | — | — | — | ||
| 2 | Amazon | — | — | — |
FAQ
Common questions about QVHighlights.
More evaluations to explore
Related benchmarks in the same category
Humanity's Last Exam (HLE) is a multi-modal academic benchmark with 2,500 questions across mathematics, humanities, and natural sciences, designed to test LLM capabilities at the frontier of human knowledge with unambiguous, verifiable solutions
MMMU (Massive Multi-discipline Multimodal Understanding) is a benchmark designed to evaluate multimodal models on college-level subject knowledge and deliberate reasoning. Contains 11.5K meticulously collected multimodal questions from college exams, quizzes, and textbooks, covering six core disciplines: Art & Design, Business, Science, Health & Medicine, Humanities & Social Science, and Tech & Engineering across 30 subjects and 183 subfields.
A more robust multi-discipline multimodal understanding benchmark that enhances MMMU through a three-step process: filtering text-only answerable questions, augmenting candidate options, and introducing vision-only input settings. Achieves significantly lower model performance (16.8-26.9%) compared to original MMMU, providing more rigorous evaluation that closely mimics real-world scenarios.
CharXiv-R is the reasoning component of the CharXiv benchmark, focusing on complex reasoning questions that require synthesizing information across visual chart elements. It evaluates multimodal large language models on their ability to understand and reason about scientific charts from arXiv papers through various reasoning tasks.
MathVista evaluates mathematical reasoning of foundation models in visual contexts. It consists of 6,141 examples derived from 28 existing multimodal datasets and 3 newly created datasets (IQTest, FunctionQA, and PaperQA), combining challenges from diverse mathematical and visual tasks to assess models' ability to understand complex figures and perform rigorous reasoning.
AI2D is a dataset of 4,903 illustrative diagrams from grade school natural sciences (such as food webs, human physiology, and life cycles) with over 15,000 multiple choice questions and answers. The benchmark evaluates diagram understanding and visual reasoning capabilities, requiring models to interpret diagrammatic elements, relationships, and structure to answer questions about scientific concepts represented in visual form.