19.4.3.3.1 Visual Question Answering, Datasets, Benchmarks, Surveys

Chapter Contents (Back)
Question Answer. Visual Q-A. VQA.

VQA: Visual Question Answering,
dataset containing open-ended questions about images WWW Link.
Dataset, Visual Question Answering.
See also VQA: Visual Question Answering.

Visual Genome,
Visual Genome is a dataset, a knowledge base, an ongoing effort to connect structured image concepts to language. WWW Link.

WWW Link. Dataset, Visual Question Answering.

Kafle, K.[Kushal], Kanan, C.[Christopher],
Visual question answering: Datasets, algorithms, and future challenges,
CVIU(163), No. 1, 2017, pp. 3-20.
Elsevier DOI 1712
Image understanding BibRef

Wu, Q.[Qi], Teney, D.[Damien], Wang, P.[Peng], Shen, C.H.[Chun-Hua], Dick, A.[Anthony], van den Hengel, A.J.[Anton J.],
Visual question answering: A survey of methods and datasets,
CVIU(163), No. 1, 2017, pp. 21-40.
Elsevier DOI 1712
Survey, Visual Question Answering. Visual question answering BibRef

Teney, D.[Damien], Wu, Q., van den Hengel, A.J.[Anton J.],
Visual Question Answering: A Tutorial,
SPMag(34), No. 6, November 2017, pp. 63-75.
IEEE DOI 1712
Survey, Visual Question Answering. Bioinformatics, Genomics, Machine learning, Visualization BibRef

Teney, D.[Damien], Liu, L., van den Hengel, A.J.[Anton J.],
Graph-Structured Representations for Visual Question Answering,
CVPR17(3233-3241)
IEEE DOI 1711
Feature extraction, Knowledge discovery, Neural networks, Syntactics, Training, Visualization BibRef

Teney, D.[Damien], van den Hengel, A.J.[Anton J.],
Visual Question Answering as a Meta Learning Task,
ECCV18(XV: 229-245).
Springer DOI 1810
BibRef

Teney, D.[Damien], Abbasnejad, E.[Ehsan], van den Hengel, A.J.[Anton J.],
Unshuffling Data for Improved Generalization in Visual Question Answering,
ICCV21(1397-1407)
IEEE DOI 2203
Training, Visualization, Annotations, Computational modeling, Genomics, Training data, Vision + language, BibRef

Wu, Q.[Qi], Shen, C.H.[Chun-Hua], Wang, P.[Peng], Dick, A.[Anthony], van den Hengel, A.J.[Anton J.],
Image Captioning and Visual Question Answering Based on Attributes and External Knowledge,
PAMI(40), No. 6, June 2018, pp. 1367-1381.
IEEE DOI 1805
BibRef
Earlier: A1, A3, A2, A4, A5:
Ask Me Anything: Free-Form Visual Question Answering Based on Knowledge from External Sources,
CVPR16(4622-4630)
IEEE DOI 1612
Computational modeling, Knowledge based systems, Knowledge discovery, Resource description framework, Semantics, visual question answering BibRef

Tommasi, T.[Tatiana], Mallya, A.[Arun], Plummer, B.A.[Bryan A.], Lazebnik, S.[Svetlana], Berg, A.C.[Alexander C.], Berg, T.L.[Tamara L.],
Combining Multiple Cues for Visual Madlibs Question Answering,
IJCV(127), No. 1, January 2019, pp. 38-60.
Springer DOI 1901
BibRef
Earlier:
Solving Visual Madlibs with Multiple Cues,
BMVC16(xx-yy).
HTML Version. 1805
BibRef

Yu, L.C.[Li-Cheng], Park, E.[Eunbyung], Berg, A.C.[Alexander C.], Berg, T.L.[Tamara L.],
Visual Madlibs: Fill in the Blank Description Generation and Question Answering,
ICCV15(2461-2469)
IEEE DOI 1602
dataset consisting of 360,001 focused natural language descriptions for 10,738 images BibRef

Patil, C.[Charulata], Patwardhan, M.[Manasi],
Visual Question Generation: The State of the Art,
Surveys(53), No. 3, May 2020, pp. xx-yy.
DOI Link 2007
Image understanding, question generation BibRef

He, F.J.[Fei-Juan], Wang, Y.X.[Ya-Xian], Miao, X.L.[Xiang-Lin], Sun, X.[Xia],
Interpretable visual reasoning: A survey,
IVC(112), 2021, pp. 104194.
Elsevier DOI 2107
Visual question answering, Visual reasoning, Interpretability, Datasets, Survey BibRef

Sharma, H.[Himanshu], Jalal, A.S.[Anand Singh],
A survey of methods, datasets and evaluation metrics for visual question answering,
IVC(116), 2021, pp. 104327.
Elsevier DOI 2112
Natural language processing, Deep neural networks, World knowledge, Attention BibRef

Yang, L.[Lu], Jiang, H.[He], Song, Q.[Qing], Guo, J.[Jun],
A Survey on Long-Tailed Visual Recognition,
IJCV(130), No. 7, July 2022, pp. 1837-1872.
Springer DOI 2207
Deep learning usually does the common well, not the rare.
See also YouTube-8M Dataset. BibRef

Zhao, W.[Wenliang], Rao, Y.M.[Yong-Ming], Tang, Y.[Yansong], Zhou, J.[Jie], Lu, J.W.[Ji-Wen],
VideoABC: A Real-World Video Dataset for Abductive Visual Reasoning,
IP(31), 2022, pp. 6048-6061.
IEEE DOI 2209
Cognition, Visualization, Task analysis, Benchmark testing, Question answering (information retrieval), Machine vision, instruction video BibRef

Lahouti, F.[Farshad], Kostina, V.[Victoria], Hassibi, B.[Babak],
How to Query an Oracle? Efficient Strategies to Label Data,
PAMI(44), No. 11, November 2022, pp. 7597-7609.
IEEE DOI 2210
Labeling, Erbium, Dogs, Crowdsourcing, Reliability, Decoding, Databases, Machine learning, labeling datasets, clustering, classification, entity resolution BibRef


Zhu, L.[Liuwan], Ning, R.[Rui], Li, J.[Jiang], Xin, C.S.[Chun-Sheng], Wu, H.Y.[Hong-Yi],
Most and Least Retrievable Images in Visual-Language Query Systems,
ECCV22(XXXVII:1-18).
Springer DOI 2211
BibRef

Salewski, L.[Leonard], Emde, C.[Cornelius], Do, V.[Virginie], Akata, Z.[Zeynep], Lukasiewicz, T.[Thomas],
e-ViL: A Dataset and Benchmark for Natural Language Explanations in Vision-Language Tasks,
ICCV21(1224-1234)
IEEE DOI 2203
Measurement, Codes, Computational modeling, Natural languages, Benchmark testing, Predictive models, Explainable AI, Vision + language BibRef

Gupta, V.[Vivek], Patro, B.N.[Badri N.], Parihar, H.[Hemant], Namboodiri, V.P.[Vinay P.],
VQuAD: Video Question Answering Diagnostic Dataset,
Novelty22(282-291)
IEEE DOI 2202
Correlation, Codes, Conferences, Bit error rate, Cognition, Task analysis BibRef

Nishimura, T.[Taichi], Sakoda, K.[Kojiro], Hashimoto, A.[Atsushi], Ushiku, Y.[Yoshitaka], Tanaka, N.[Natsuko], Ono, F.[Fumihito], Kameko, H.[Hirotaka], Mori, S.[Shinsuke],
Egocentric Biochemical Video-and-Language Dataset,
CLVL21(3122-3126)
IEEE DOI 2112
Visualization, Protocols, Annotations, Biological system modeling, Data collection BibRef

Zhang, M.[Mingda], Maidment, T.[Tristan], Diab, A.[Ahmad], Kovashka, A.[Adriana], Hwa, R.[Rebecca],
Domain-robust VQA with diverse datasets and methods but no target labels,
CVPR21(7042-7052)
IEEE DOI 2111
Visualization, Adaptation models, Computational modeling, Semantics, Linguistics, Syntactics BibRef

Mathew, M.[Minesh], Karatzas, D.[Dimosthenis], Jawahar, C.V.,
DocVQA: A Dataset for VQA on Document Images,
WACV21(2199-2208)
IEEE DOI
WWW Link. 2106
Dataset, Visual Q-A. Visualization, Text analysis, Image recognition, Image analysis, Layout BibRef

Patel, D.[Devshree], Parikh, R.[Ratnam], Shastri, Y.[Yesha],
Recent Advances in Video Question Answering: A Review of Datasets and Methods,
VTIUR20(339-356).
Springer DOI 2103
BibRef

Fan, C.,
EgoVQA: An Egocentric Video Question Answering Benchmark Dataset,
EPIC19(4359-4366)
IEEE DOI 2004
question answering (information retrieval), video signal processing, EgoVQA dataset, visual question, dataset BibRef

Hudson, D.A.[Drew A.], Manning, C.D.[Christopher D.],
GQA: A New Dataset for Real-World Visual Reasoning and Compositional Question Answering,
CVPR19(6693-6702).
IEEE DOI 2002
BibRef

Yang, G.R.[Guangyu Robert], Ganichev, I.[Igor], Wang, X.J.[Xiao-Jing], Shlens, J.[Jonathon], Sussillo, D.[David],
A Dataset and Architecture for Visual Reasoning with a Working Memory,
ECCV18(X: 729-745).
Springer DOI 1810
BibRef

Gan, C., Li, Y., Li, H., Sun, C., Gong, B.,
VQS: Linking Segmentations to Questions and Answers for Supervised Attention in VQA and Question-Focused Semantic Segmentation,
ICCV17(1829-1838)
IEEE DOI 1802
image annotation, image segmentation, multilayer perceptrons, question answering (information retrieval), COCO, VQA dataset, Visualization BibRef

Maharaj, T., Ballas, N., Rohrbach, A., Courville, A., Pal, C.,
A Dataset and Exploration of Models for Understanding Video Data through Fill-in-the-Blank Question-Answering,
CVPR17(7359-7368)
IEEE DOI 1711
Computational modeling, Motion pictures, Natural languages, Training, Visualization, Voltage, control BibRef

Chapter on Implementations and Applications, Databases, QBIC, Video Analysis, Hardware and Software, Inspection continues in
Visual Dialog .


Last update:Nov 28, 2022 at 16:32:47