CR-CLIP adds cross-modal attention and multi-scale test augmentation to an AVION baseline, reporting 66.8% mAP and 82.1% nDCG, first place on EPIC-KITCHENS-100 multi-instance retrieval 2025.
Visual to text: Survey of image and video captioning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ContextRefine-CLIP for EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 2025
CR-CLIP adds cross-modal attention and multi-scale test augmentation to an AVION baseline, reporting 66.8% mAP and 82.1% nDCG, first place on EPIC-KITCHENS-100 multi-instance retrieval 2025.