Lorenzo Bianchi

Hi! Thank you for appreciating our work! Benchmarks, training sets, and validation sets are generated in the same way following the procedure described in the paper. The differences are the...

Thank you for bringing this issue to my attention! You're correct; there is indeed a mistake that would affect the vocabulary length, and I will fix it :) . However,...

Thank you for bringing this to our attention! Could you please share how much of an improvement you're observing in the R@1, R@5, and R@10 metrics compared to the results...

Hi! Thank you for your interest in our work! When running evaluate_map.py, it is correct that these parameters should be set to their default values: - **simplify_errors**: The default value...