Abstract | ||
---|---|---|
•A novel framework VD-PCR to improve visual dialog models with pronoun coreference.•The joint training helps visual dialog models understand pronouns better.•The history pruning with pronoun coreference prevents overfitting to dialog history.•VD-PCR achieves state-of-the-art results on the VisDial dataset. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1016/j.patcog.2022.108540 | Pattern Recognition |
Keywords | DocType | Volume |
Vision and language,Visual dialog,Pronoun coreference resolution | Journal | 125 |
Issue | ISSN | Citations |
1 | 0031-3203 | 0 |
PageRank | References | Authors |
0.34 | 13 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xintong Yu | 1 | 0 | 2.03 |
Hongming Zhang | 2 | 10 | 8.34 |
Ruixin Hong | 3 | 0 | 1.01 |
Yangqiu Song | 4 | 2045 | 103.29 |
Changshui Zhang | 5 | 5506 | 323.40 |