Latent Variable Models for Visual Question Answering
Not on the map. Why?
Abstract (arXiv)
Current work on Visual Question Answering (VQA) explore deterministic approaches conditioned on various types of image and question features. We posit that, in addition to image and question pairs, other modalities are useful for teaching machine to carry out question answering. Hence in this paper, we propose latent variable models for VQA where extra information (e.g. captions and answer categories) are incorporated as latent variables, which are observed during training but in turn benefit question-answering performance at test time. Experiments on the VQA v2.0 benchmarking dataset demonstrate the effectiveness of our proposed models: they improve over strong baselines, especially those that do not rely on extensive language-vision pre-training.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 34 of its 42 references that are in the map. First posted on arXiv 16 Jan 2021.
Builds on
34 of 42 references.
References · 34
- 2017Attention Is All You Needcited by 60,361
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2014Microsoft COCO: Common Objects in Contextcited by 17,608
- 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
- 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,656
- 2016Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answeringcited by 2,516
- 2015VQA: Visual Question Answeringcited by 2,506
- 2019ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Taskscited by 2,222
- 2019LXMERT: Learning Cross-Modality Encoder Representations from Transformerscited by 1,553
- 2016Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translationcited by 1,475
- 2017Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answeringcited by 1,312
22 more
- 2019VisualBERT: A Simple and Performant Baseline for Vision and Languagecited by 1,296
- 2020Oscar: Object-Semantics Aligned Pre-training for Vision-Language Taskscited by 1,214
- 2014Deep Visual-Semantic Alignments for Generating Image Descriptionscited by 968
- 2019VL-BERT: Pre-training of Generic Visual-Linguistic Representationscited by 954
- 2019Unified Vision-Language Pre-Training for Image Captioning and VQAcited by 494
- 2019Deep Modular Co-Attention Networks for Visual Question Answeringcited by 339
- 2018Bilinear Attention Networkscited by 280
- 2015Stacked Attention Networks for Image Question Answeringcited by 273
- 2020In Defense of Grid Features for Visual Question Answeringcited by 155
- 2020Counterfactual Samples Synthesizing for Robust Visual Question Answeringcited by 153
- 2018Dynamic Fusion with Intra- and Inter- Modality Attention Flow for Visual Question Answeringcited by 114
- 2015Neural Variational Inference for Text Processingcited by 111
- 2017Tips and Tricks for Visual Question Answering: Learnings from the 2017 Challengecited by 76
- 2015Where To Look: Focus Regions for Visual Question Answeringcited by 64
- 2020MUTANT: A Training Paradigm for Out-of-Distribution Generalization in Visual Question Answeringcited by 63
- 2019Information Maximizing Visual Question Generationcited by 40
- 2019Probabilistic Neural-symbolic Models for Interpretable Visual Question Answeringcited by 38
- 2017Show, Ask, Attend, and Answer: A Strong Baseline For Visual Question Answeringcited by 31
- 2019Multi-modality Latent Interaction Network for Visual Question Answeringcited by 23
- 2019Generating Question Relevant Captions to Aid Visual Question Answeringcited by 10
- 2020Deep Bayesian Network for Visual Question Generationcited by 7
- 2019Improving Visual Question Answering by Referring to Generated Paragraph Captionscited by 6
Built on by
Citing papers per year: 2021: 1; 2022: 1.
2 papers.