Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Cross-Modal Scene Retrieval (Image to Description) on 3RScan
Loading...
8.72
Scene Matching Recall @1
Inst. Baseline
1.0448
3.0374
5.03
7.0226
Feb 20, 2025
Scene Matching Recall @1
Scene Matching Recall @5
Scene Matching Recall @10
Scene Matching Recall @20
Temporal Recall @1
Temporal Recall @5
Temporal Recall @10
Updated 3d ago
Evaluation Results
Method
Method
Links
Scene Matching Recall @1
Scene Matching Recall @5
Scene Matching Recall @10
Scene Matching Recall @20
Temporal Recall @1
Temporal Recall @5
Temporal Recall @10
Inst. Baseline
Modality Pair=I → R
2025.02
8.72
40.94
57.05
69.8
6.38
38.3
63.83
CrossOver
Modality Pair=I → R
2025.02
6.04
26.85
42.28
62.42
2.13
34.04
63.83
ULIP-2
Modality Pair=I → R
2025.02
2.01
4.7
7.38
14.77
2.13
6.38
12.77
PointBind
Modality Pair=I → R
2025.02
1.34
4.77
6.71
13.42
2.13
6.38
14.89
Feedback
Search any
task
Search any
task