DeCafNet-50% (no NaQ)

Reported on 5 benchmarks across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing5 results

Natural Language QueriesonEgo4D
R@1 IoU=0.3· 2025-05-22
18.1
best: 28.05 (EgoVideo)
DeCafNet: Delegate and Conquer for Efficient Temporal Grounding in Long Videos arXiv:2505.16376
Natural Language QueriesonEgo4D
R@1 IoU=0.5· 2025-05-22
12.55
best: 19.31 (EgoVideo)
DeCafNet: Delegate and Conquer for Efficient Temporal Grounding in Long Videos arXiv:2505.16376
Natural Language QueriesonEgo4D
R@1 Mean(0.3 and 0.5)· 2025-05-22
15.32
best: 23.68 (EgoVideo)
DeCafNet: Delegate and Conquer for Efficient Temporal Grounding in Long Videos arXiv:2505.16376
Natural Language QueriesonEgo4D
R@5 IoU=0.3· 2025-05-22
38.85
best: 45.63 (DeCafNet-100%)
DeCafNet: Delegate and Conquer for Efficient Temporal Grounding in Long Videos arXiv:2505.16376
Natural Language QueriesonEgo4D
R@5 IoU=0.5· 2025-05-22
28.27
best: 33.93 (DeCafNet-100%)
DeCafNet: Delegate and Conquer for Efficient Temporal Grounding in Long Videos arXiv:2505.16376