PoseLLM swaps LocLLM's linear vision-language projector for a two-layer MLP with GELU, reporting +0.4 AP on COCO (77.8) with comparable zero-shot transfer.
Advances in neural information processing systems 35, 23716–23736 (2022)
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
-
PoseLLM: Enhancing Language-Guided Human Pose Estimation with MLP Alignment
PoseLLM swaps LocLLM's linear vision-language projector for a two-layer MLP with GELU, reporting +0.4 AP on COCO (77.8) with comparable zero-shot transfer.