Achieving Text-based Person Retrieval with Any Granularity
Ranking
Overall
55
Content
60
Popularity
45
Observed public metrics from 1 member.
Merged summary
TL;DR - This paper introduces a benchmark, dataset, and framework for text-based person retrieval across five query-granularity levels. It matters because coarse descriptions can validly match multiple people, requiring uncertainty-aware alignment and evaluation.
- UFine6926-MG provides multi-grained annotations spanning all five granularity levels.
- MG-Eval uses progressively detailed descriptions, cross-identity labels, and tailored metrics.
- CMAM combines orthogonal experts, probabilistic many-to-many alignment, and granularity-consistent reasoning.
- Experiments report state-of-the-art performance across every evaluated granularity level.
Sources (1)
Achieving Text-based Person Retrieval with Any Granularity
Public signals
OpenAlex citations 0
TL;DR - This paper introduces a benchmark, dataset, and framework for text-based person retrieval across five query-granularity levels. It matters because coarse descriptions can validly match multiple people, requiring uncertainty-aware alignment and evaluation.
- UFine6926-MG provides multi-grained annotations spanning all five granularity levels.
- MG-Eval uses progressively detailed descriptions, cross-identity labels, and tailored metrics.
- CMAM combines orthogonal experts, probabilistic many-to-many alignment, and granularity-consistent reasoning.
- Experiments report state-of-the-art performance across every evaluated granularity level.