Tamara Lee Berg — accepted AI-conference papers

2021

Detecting Moments and Highlights in Videos via Natural Language Queries

NeurIPS 2021poster

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)…

Cited by 297 Source ↗PDF ↗code ↗Scholar ↗

2021

VALUE: A Multi-Task Benchmark for Video-and-Language Understanding Evaluation

Linjie Li, Jie Lei, Zhe Gan, Licheng Yu, Yen-Chun Chen, Rohit Pillai +9

NeurIPS 2021poster

Most existing video-and-language (VidL) research focuses on a single dataset, or multiple datasets of a single task. In reality, a truly useful VidL system is expected to be easily generalizable to diverse tasks, domains, and datasets. To facilitate the evaluation of such systems, we introduce Video…

Cited by 123 Source ↗code ↗Scholar ↗