Inverse Visual Question Answering : A New Benchmark and VQA Diagnosis Tool
In recent years, visual question answering (VQA) has become topical. The premise of VQA's significance as a benchmark in AI, is that both the image and textual question need to be well understood and mutually grounded in order to infer the correct answer. However, current VQA models perhaps �...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 42(2020), 2 vom: 12. Feb., Seite 460-474
|
|---|
| 1. Verfasser: |
Liu, Feng
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Xiang, Tao,
Hospedales, Timothy M,
Yang, Wankou,
Sun, Changyin |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2020
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
|---|
| Schlagworte: | Journal Article
Research Support, Non-U.S. Gov't |
|---|