ZeroSight supplies a video-derived dataset and evaluation protocol for genuine zero-shot composed image retrieval plus the SC4CIR consistency method, demonstrating that prior benchmarks inflate reported performance across 27 tested approaches.
Zero-shot composed text-image retrieval,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Introduces DFHR task, DFHR-Bench with over 180K triplets, and MFHC framework for mixed-modality dual face-hair retrieval.
citing papers explorer
-
Never Seen Before: Benchmarking Genuine Zero-Shot Composed Image Retrieval with Consistent Video-Sourced Datasets
ZeroSight supplies a video-derived dataset and evaluation protocol for genuine zero-shot composed image retrieval plus the SC4CIR consistency method, demonstrating that prior benchmarks inflate reported performance across 27 tested approaches.
-
Mixed-Modality Dual Face-Hair Retrieval
Introduces DFHR task, DFHR-Bench with over 180K triplets, and MFHC framework for mixed-modality dual face-hair retrieval.