![]() | ![]() | ![]() | ![]() | ![]() |
![]() | ![]() | ![]() | ![]() | ![]() |
![]() | ![]() | ![]() | ![]() | ![]() |
| Main Focus | Confidence | Explanation |
|---|---|---|
| Separate Object | 4 | The red region mainly focuses on the soup inside the predicted object, rather than the predicted object itself. |
| Main Object | 5 | The red areas focus on the food that is in the hot pot. |
| Main Object | 5 | The focus is on the soup in the hot pot. |
| Main Object | 2 | The red region in the highlighted visual attributes focuses on the part of a hotpot. |
| Separate Object | 5 | The focus of the red region in the highlighted visual attributes is on the dish is not part of a hotpot. |