Weakly Supervised Temporal Sentence Grounding With Gaussian-Based Contrastive Proposal Learning

Open paper
Benchmark Model Rank Results
temporal-sentence-grounding-on-charades-staCPL (Weak, MViT-K400-Pretrain-feature, evaluated by AdaFocus)#4R1@0.7: 21.8R1@0.5: 47.8R5@0.7: 50.4R5@0.5: 84.6
temporal-sentence-grounding-on-charades-staCPL (Weak, I3D-K400-Pretrain-feature, evaluated by AdaFocus)#7R1@0.7: 18.6R1@0.5: 39.6R5@0.7: 49.2R5@0.5: 81.4

Rank counts only results with a code link.