A vision-language model that encodes panoptic image segments with graph attention and spiking neurons reports competitive or better results on VQA, VE, NLVR2, and retrieval benchmarks.
In de- fense of grid features for visual question answering,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Improving vision-language alignment with graph spiking hybrid Networks
A vision-language model that encodes panoptic image segments with graph attention and spiking neurons reports competitive or better results on VQA, VE, NLVR2, and retrieval benchmarks.