Mood-aware visual question answering

N Ruwa, Q Mao, L Wang, J Gou, M Dong - Neurocomputing, 2019 - Elsevier
Abstract The concept of Visual Question Answering (VQA) has recently attracted the
attention of many researchers in the field of machine learning. Different attention models …

[PDF][PDF] Visual question answering research on multi-layer attention mechanism based on image target features

D Cao, X Ren, M Zhu, W Song - Human-centric Computing and …, 2021 - hcisj.com
Visual question answering (VQA) aims to output a natural language answer based on a
picture and a related question in order to achieve machine language understanding …

Topological spatial verification for instance search

W Zhang, CW Ngo - IEEE Transactions on Multimedia, 2015 - ieeexplore.ieee.org
This paper proposes an elastic spatial verification method for Instance Search, particularly
for dealing with non-planar and non-rigid queries exhibiting complex spatial transformations …

Searching visual instances with topology checking and context modeling

W Zhang, CW Ngo - Proceedings of the 3rd ACM conference on …, 2013 - dl.acm.org
Instance Search (INS) is a realistic problem initiated by TRECVID, which is to retrieve all
occurrences of the querying object, location, or person from a large video collection. It is a …

Scalable visual instance mining with threads of features

W Zhang, H Li, CW Ngo, SF Chang - Proceedings of the 22nd ACM …, 2014 - dl.acm.org
We address the problem of visual instance mining, which is to extract frequently appearing
visual instances automatically from a multimedia collection. We propose a scalable mining …

Vireo@ trecvid 2014: instance search and semantic indexing

W Zhang, H Zhang, T Yao, Y Lu, J Chen, CW Ngo - 2014 - ink.library.smu.edu.sg
Vireo @ TRecViD 2014: Instance search and semantic indexing Page 1 Singapore
Management University Institutional Knowledge at Singapore Management University Research …

Triple attention network for sentimental visual question answering

N Ruwa, Q Mao, H Song, H Jia, M Dong - Computer Vision and Image …, 2019 - Elsevier
Abstract Visual Question Answering (VQA) and Visual Sentiment Analysis (VSA) are recently
popular research fields in multimedia analysis using deep learning, but little effort has been …

Second-order configuration of local features for geometrically stable image matching and retrieval

X Wu, K Kashino - IEEE Transactions on Circuits and Systems …, 2014 - ieeexplore.ieee.org
Local features offer high repeatability, which supports efficient matching between images,
but they do not provide sufficient discriminative power. Imposing a geometric coherence …

MatchDR: Image correspondence by leveraging distance ratio constraint

R Wang, D Liang, W Zhang, X Cao - Proceedings of the 24th ACM …, 2016 - dl.acm.org
Image correspondence is to establish the connections between coherent images, which can
be quite challenging due to the visual and geometric deformations. This paper proposes a …

Opinion question answering by sentiment clip localization

L Pang, CW Ngo - ACM Transactions on Multimedia Computing …, 2015 - dl.acm.org
This article considers multimedia question answering beyond factoid and how-to questions.
We are interested in searching videos for answering opinion-oriented questions that are …