2 papers
cs.CL2024
Cobra Effect in Reference-Free Image Captioning Metrics
Zheng Ma, Changxin Wang, Yawen Ouyang +4
Evaluating the compatibility between textual descriptions and corresponding images represents a core endeavor within multi-modal research. In recent years, a proliferation of refer…
cs.CV2023
Bounding and Filling: A Fast and Flexible Framework for Image Captioning
Zheng Ma, Changxin Wang, Bo Huang +2
Most image captioning models following an autoregressive manner suffer from significant inference latency. Several models adopted a non-autoregressive manner to speed up the proces…