# Uncovering Temporal Context for Video Question and Answering

Source: [Uncovering Temporal Context for Video Question and Answering](<https://www.sota2.com/research/paper/68fa622a1e209131ce9f7c50>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:56:31.051Z

Authors: Linchao Zhu, Zhongwen Xu, Yi Yang, Alexander G. Hauptmann

Published: 2015-11-15T07:57:41.000Z

## Abstract

In this work, we introduce Video Question Answering in temporal domain to infer the past, describe the present and predict the future. We present an encoder-decoder approach using Recurrent Neural Networks to learn temporal structures of videos and introduce a dual-channel ranking loss to answer multiple-choice questions. We explore approaches for finer understanding of video content using question form of "fill-in-the-blank", and managed to collect 109,895 video clips with duration over 1,000 hours from TACoS, MPII-MD, MEDTest 14 datasets, while the corresponding 390,744 questions are generated from annotations. Extensive experiments demonstrate that our approach significantly outperforms the compared baselines.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1511.04670>)

[PDF](<https://arxiv.org/pdf/1511.04670.pdf>)
