A vision-language model trained on a new 260K-pair real infrared-text dataset beats general VLMs on a 9-task infrared Q&A benchmark, but the benchmark is in-distribution.
Internvl: Scaling up vision foundation mod- els and aligning for generic visual-linguistic tasks
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
-
IRGPT: Understanding Real-world Infrared Image with Bi-cross-modal Curriculum on Large-scale Benchmark
A vision-language model trained on a new 260K-pair real infrared-text dataset beats general VLMs on a 9-task infrared Q&A benchmark, but the benchmark is in-distribution.