paper-with-me

Papers

Compact Trilinear Interaction for Visual Question Answering

2019-09-26 · ICCV 2019 10 · Tuong Do, Thanh-Toan Do, Huy Tran, Erman Tjiputra, Quang D. Tran

In Visual Question Answering (VQA), answers have a great correlation with question meaning and visual contents. Thus, to selectively utilize image, question and answer information, we propose a novel trilinear interaction model which simultaneously learns high level associations between these three inputs. In addition, to overcome the interaction complexity, we introduce a multimodal tensor-based PARALIND decomposition which efficiently parameterizes trilinear interaction between the three inputs. Moreover, knowledge distillation is first time applied in Free-form Opened-ended VQA. It is not only for reducing the computational cost and required memory but also for transferring knowledge from trilinear interaction model to bilinear interaction model. The extensive experiments on benchmarking datasets TDIUC, VQA-2.0, and Visual7W show that the proposed compact trilinear interaction model achieves state-of-the-art results when using a single model on all three datasets.

📄 PDF Abstract BibTeX arXiv:1909.11874

Code (1)

aioz-ai/ICCV19_VQA-CTI 공식 구현 pytorch

Tasks

BenchmarkingKnowledge DistillationQuestion AnsweringVisual Question AnsweringVisual Question Answering (VQA)

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

MIRTT: Learning Multimodal Interaction Representations from Trilinear Transformers for Visual Question Answering

2021-11-01 · Findings (EMNLP) 2021 11 · Junjie Wang, Yatai Ji, Jiaqi Sun, Yujiu Yang 외

In Visual Question Answering (VQA), existing bilinear methods focus on the interaction between images and questions. As a result, the answers are either spliced into the questions or utilized as labels only for classific…

multimodal interactionMultiple-choiceQuestion AnsweringVisual Question Answering+1

Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding

2016-06-06 · EMNLP 2016 11 · Akira Fukui, Dong Huk Park, Daylen Yang, Anna Rohrbach 외

Modeling textual or visual information with vector representations trained from large language or visual datasets has been successfully explored in recent years. However, tasks such as visual question answering require c…

Phrase GroundingVisual GroundingVisual Question AnsweringVisual Question Answering (VQA)

Kernel Pooling for Convolutional Neural Networks

2017-07-01 · CVPR 2017 7 · Yin Cui, Feng Zhou, Jiang Wang, Xiao Liu 외

Convolutional Neural Networks (CNNs) with Bilinear Pooling, initially in their full form and later using compact representations, have yielded impressive performance gains on a wide range of visual tasks, including fine-…

Face RecognitionFine-Grained Visual CategorizationQuestion AnsweringVisual Question Answering+1

Bridge to Answer: Structure-aware Graph Interaction Network for Video Question Answering

2021-04-29 · CVPR 2021 1 · Jungin Park, Jiyoung Lee, Kwanghoon Sohn

This paper presents a novel method, termed Bridge to Answer, to infer correct answers for questions about a given video by leveraging adequate graph interactions of heterogeneous crossmodal graphs. To realize this, we le…

Question AnsweringVideo Question Answering

Compact Tensor Pooling for Visual Question Answering

2017-06-20 · Yang Shi, Tommaso Furlanello, Anima Anandkumar

Performing high level cognitive tasks requires the integration of feature maps with drastically different structure. In Visual Question Answering (VQA) image descriptors have spatial structures, while lexical inputs inhe…

Question AnsweringVisual Question AnsweringVisual Question Answering (VQA)