Simple Baseline for Visual Question Answering

2015/12/07 by Bolei Zhou, Yuandong Tian, Zhou, Bolei +7 · 292 citations
Computer Science · #Advanced Image and Video Retrieval Techniques #Artificial intelligence #Baseline (sea) #Code (set theory) #Computation and Language (cs.CL) #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Convolutional neural network #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Information retrieval #Linguistics #Machine learning #Multimodal Machine Learning Applications #Natural language processing #Open source #Programming language #Question answering #Simple (philosophy) #Software #Source code #Word (group theory) #cs.CL #cs.CV

paper · pdf · doi:10.48550/arxiv.1512.02167

published in arXiv (Cornell University) (Cornell University) · One comparison method's scores are put into the correct column, and a new experiment of generating attention map is added

openalex publication_date 2015/12/07 · arxiv created 2015/12/15 · arxiv updated 2015/12/16 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We describe a very simple bag-of-words baseline for visual question answering. This baseline concatenates the word features from the question and CNN features from the image to predict the answer. When evaluated on the challenging VQA dataset [2], it shows comparable performance to many recent approaches using recurrent neural networks. To explore the strength and weakness of the trained model, we also provide an interactive web demo and open-source code. .

Citations

• Are You Talking to a Machine? Dataset and Methods for Multilingual Image Question Answering
• Ask, Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question Answering
• Learning Deep Features for Discriminative Localization
• VQA: Visual Question Answering

Cited by

• Visual Question Answering: A Survey of Methods and Datasets
• Scene Graph Generation from Objects, Phrases and Region Captions
• The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes
• Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding
• Leveraging Visual Question Answering for Image-Caption Ranking
• Dual Encoding for Zero-Example Video Retrieval
• Person Search with Natural Language Description
• The Amazing Mysteries of the Gutter: Drawing Inferences Between Panels in Comic Book Narratives
• Dual Attention Networks for Multimodal Reasoning and Matching
• Experimental Standards for Deep Learning in Natural Language Processing Research
• Ways of Conditioning Generative Adversarial Networks
• Two-Stage Synthesis Networks for Transfer Learning in Machine Comprehension
• Scene Graph Reasoning with Prior Visual Relationship for Visual Question Answering
• cvpaper.challenge in 2016: Futuristic Computer Vision through 1,600 Papers Survey
• Transfer Learning in Visual and Relational Reasoning
• Multi-modal Factorized Bilinear Pooling with Co-Attention Learning for Visual Question Answering
• Pay Attention to Those Sets! Learning Quantification from Images
• ProTo: Program-Guided Transformer for Program-Guided Tasks
• Deep Modular Co-Attention Networks for Visual Question Answering
• Identity-Aware Textual-Visual Matching with Latent Co-attention
• Visual Question Answering with Memory-Augmented Networks
• Deep Bayesian Active Learning for Multiple Correct Outputs
• Visual Referring Expression Recognition: What Do Systems Actually Learn?
• Will Multi-modal Data Improves Few-shot Learning?
• A Revised Generative Evaluation of Visual Dialogue
• Visual Question Answering with Prior Class Semantics
• Trying Bilinear Pooling in Video-QA
• Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answering
• Text classification with pixel embedding
• Survey of Visual Question Answering: Datasets and Techniques
• Creativity: Generating Diverse Questions using Variational Autoencoders
• The VQA-Machine: Learning How to Use Existing Vision Algorithms to Answer New Questions
• Learning Visual Knowledge Memory Networks for Visual Question Answering
• Recurrent and Contextual Models for Visual Question Answering
• MarioQA: Answering Questions by Watching Gameplay Videos
• Visual Question Generation as Dual Task of Visual Question Answering
• Matching Images and Text with Multi-modal Tensor Fusion and Re-ranking
• Beyond Bilinear: Generalized Multimodal Factorized High-Order Pooling for Visual Question Answering
• After All, Only The Last Neuron Matters: Comparing Multi-modal Fusion\n Functions for Scene Graph Generation

Related

• Show, Ask, Attend, and Answer: A Strong Baseline For Visual Question Answering
• Visual Question Answering: A Survey of Methods and Datasets
• Visual Question Answering using Deep Learning: A Survey and Performance\n Analysis
• Tips and Tricks for Visual Question Answering: Learnings from the 2017 Challenge
• Open-Ended Visual Question-Answering