CMLReID uses dynamic text prompts and dual-path prototypes to improve lifelong person re-identification in hybrid clothing states, reporting gains of about 5 mAP over four baselines.
In: Advances in Computer Graphics - 39th Computer Graphics International Confer- ence, CGI 2022, Virtual Event, September 12-16
1 Pith paper cite this work, alongside 2 external citations. Polarity classification is still indexing.
1
Pith paper citing it
2
external citations · OpenAlex
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Contextualized Multimodal Lifelong Person Re-Identification in Hybrid Clothing States
CMLReID uses dynamic text prompts and dual-path prototypes to improve lifelong person re-identification in hybrid clothing states, reporting gains of about 5 mAP over four baselines.