# VIBIKNet: Visual Bidirectional Kernelized Network for Visual Question Answering

Source: [VIBIKNet: Visual Bidirectional Kernelized Network for Visual Question Answering](<https://www.sota2.com/research/paper/68fa62ff1e209131ce9fc2a8>)

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

Data updated: 2025-10-25T20:30:18.740Z

Authors: Marc Bola\\~nos, \\'Alvaro Peris, Francisco Casacuberta, Petia Radeva

Published: 2016-12-12T11:41:46.000Z

## Abstract

In this paper, we address the problem of visual question answering by proposing a novel model, called VIBIKNet. Our model is based on integrating Kernelized Convolutional Neural Networks and Long-Short Term Memory units to generate an answer given a question about an image. We prove that VIBIKNet is an optimal trade-off between accuracy and computational load, in terms of memory and time consumption. We validate our method on the VQA challenge dataset and compare it to the top performing methods in order to illustrate its performance and speed.

## 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/1612.03628>)

[PDF](<https://arxiv.org/pdf/1612.03628.pdf>)