Audio-Visual Scene-Aware Dialog on AVSD (test)
1.605CIDErVX2TEXT
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| VX2TEXTUse Caption?=Yes2021.01 | 1.605 | 0.154 | 0.197 | 0.26 | 0.361 | 0.393 | 0.178 | |
| VX2TEXTUse Caption?=No2021.01 | 1.357 | 0.127 | 0.166 | 0.222 | 0.317 | 0.356 | 0.152 | |
| MTN-TMTUse Caption?=Yes2021.01 | 1.357 | 0.142 | — | — | — | 0.371 | 0.171 | |
| MTNUse Caption?=Yes2021.01 | 1.249 | 0.128 | 0.173 | 0.241 | 0.357 | 0.355 | 0.162 | |
| COST0-shot=false2023.12 | 1.085 | — | — | — | — | — | — | |
| MTN0-shot=false2023.12 | 0.985 | — | — | — | — | — | — | |
| SimpleUse Caption?=No2021.01 | 0.905 | 0.095 | 0.13 | 0.183 | 0.279 | 0.303 | 0.122 | |
| FA+HRED0-shot=false2023.12 | 0.843 | — | — | — | — | — | — | |
| ChatBridge-13B0-shot=true2023.12 | 0.754 | — | — | — | — | — | — | |
| OneLLM-7B0-shot=true2023.12 | 0.745 | — | — | — | — | — | — | |
| MA-VDSUse Caption?=No2021.01 | 0.727 | 0.078 | 0.109 | 0.161 | 0.256 | 0.277 | 0.113 |