Video Object Tracking On Cater
평가 지표
L1
Top 1 Accuracy
Top 5 Accuracy
평가 결과
이 벤치마크에서 각 모델의 성능 결과
비교 표
| 모델 이름 | L1 | Top 1 Accuracy | Top 5 Accuracy |
|---|---|---|---|
| hopper-multi-hop-transformer-for-1 | 0.85 | 73.2 | 93.8 |
| inferno-inferring-object-centric-3d-scene | - | 71.7 | 88.9 |
| tfcnet-temporal-fully-connected-networks-for | 0.47 | 79.7 | 95.5 |
| quo-vadis-action-recognition-a-new-model-and | 1.2 | 60.2 | 81.8 |
| learning-what-and-where-unsupervised | 0.14 | 90.7 | 98.5 |
| learning-object-permanence-from-video | 0.54 | 74.8 | - |
| object-based-attention-for-spatio-temporal | 0.44 | 74.0 | 94.0 |