English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Video Question Answering (VideoQA) is a challenging task that entails complexmulti-modal reasoning. In contrast to multiple-choice VideoQA which aims topredict the answer given several options, the goal of open-ended VideoQA is toanswer questions without restricting candidate answers. However, the majorityof previous VideoQA models formulate open-ended VideoQA as a classificationtask to classify the video-question pairs into a fixed answer set, i.e.,closed-vocabulary, which contains only frequent answers (e.g., top-1000answers). This leads the model to be biased toward only frequent answers andfail to generalize on out-of-vocabulary answers. We hence propose a newbenchmark, Open-vocabulary Video Question Answering (OVQA), to measure thegeneralizability of VideoQA models by considering rare and unseen answers. Inaddition, in order to improve the model's generalization power, we introduce anovel GNN-based soft verbalizer that enhances the prediction on rare and unseenanswers by aggregating the information from their similar words. Forevaluation, we introduce new baselines by modifying the existing(closed-vocabulary) open-ended VideoQA models and improve their performances byfurther taking into account rare and unseen answers. Our ablation studies andqualitative analyses demonstrate that our GNN-based soft verbalizer furtherimproves the model performance, especially on rare and unseen answers. We hopethat our benchmark OVQA can serve as a guide for evaluating thegeneralizability of VideoQA models and inspire future research. Code isavailable at https://github.com/mlvlab/OVQA.

Open-vocabulary Video Question Answering: A New Benchmark for Evaluating the Generalizability of Video Question Answering Models