InterPartAbility adds an open-vocabulary patch-phrase interaction module and a perturbation-based interpretability protocol to TI-ReID, claiming SOTA explainability scores with competitive retrieval accuracy on three benchmarks.
arXiv preprint arXiv:2101.03036 (2021) 3, 15
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
CRST improves ultra-low-resolution text-to-image person retrieval by 5.7% Rank-1 and 5.3% mAP on average across three datasets while stabilizing mixed-resolution galleries.
ROGLE introduces automated pseudo region-sentence pairs via RSM and multi-granular learning to boost fine-grained alignment in text-based person search, plus the P-VLG benchmark with over 100k annotated regions.
citing papers explorer
-
InterPartAbility: Phrase-Region Grounding for Interpretable Text-to-Image Person Re-Identification
InterPartAbility adds an open-vocabulary patch-phrase interaction module and a perturbation-based interpretability protocol to TI-ReID, claiming SOTA explainability scores with competitive retrieval accuracy on three benchmarks.
-
Cross-Resolution Semantic Transfer for Robust Text-to-Image Retrieval in Low-Resolution Surveillance
CRST improves ultra-low-resolution text-to-image person retrieval by 5.7% Rank-1 and 5.3% mAP on average across three datasets while stabilizing mixed-resolution galleries.
-
ROGLE: Robust Global-Local Alignment with Automated Region Supervision for Text-Based Person Search
ROGLE introduces automated pseudo region-sentence pairs via RSM and multi-granular learning to boost fine-grained alignment in text-based person search, plus the P-VLG benchmark with over 100k annotated regions.