Answer Grounding
Answer Grounding is a computational framework in Visual Question Answering that explicitly links predicted answers to specific regions or elements in an image, thereby providing interpretable justifications for the answers by associating them with corresponding visual evidence.
24
Publications
1.7K
Citations
87
Authors
39
Institutions
Publications per year
2017–2026
19
Parents
24
Visual7W: Grounded Question Answering in Images
Yuke Zhu, Oliver Groth, Michael S. Bernstein et al. · 2016 · 799 citations
TVQA+: Spatio-Temporal Grounding for Video Question Answering
Jie Lei, Licheng Yu, Tamara L. Berg et al. · 2020 · 175 citations · Full text
Automatic Generation of Grounded Visual Questions
Shijie Zhang, Lizhen Qu, Shaodi You et al. · 2017 · 71 citations · Full text
Grounding and Solving in Answer Set Programming
Benjamin Kaufmann, Nicola Leone, Simona Perri et al. · AI Magazine · 2016 · 67 citations · Full text
1–5 of 24
87
2
h-index
2
h-index
2
h-index
2
h-index
2
h-index
1–5 of 87
39
National University of Singapore
Singapore, Singapore
3 h-index
8 publications
315 citations
Laboratoire d'Informatique de Paris-Nord
Villetaneuse, France
2 h-index
5 publications
979 citations

Xi'an Jiaotong University
Xi'an, China
2 h-index
12 publications
506 citations
Georgia Institute of Technology
Atlanta, United States
2 h-index
4 publications
137 citations

Nankai University
Tianjin, China
2 h-index
2 publications
82 citations

Australian National University
Canberra, Australia
2 h-index
4 publications
164 citations
Technische Universität Dresden
Dresden, Germany
2 h-index
2 publications
844 citations
Stanford University
Stanford, United States
2 h-index
6 publications
2.5K citations
1–8 of 39
Repository · 6 publications · 143 citations
6
h-index
TPAMI · 2 publications · 72 citations
2
h-index
1 publications · 67 citations
1
h-index
1 publications · 11 citations
1
h-index
1 publications · 12 citations
1
h-index
1–5