Dave Z. Chen
Dave Z. Chen
Paper name: ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language Paper link: [https://arxiv.org/abs/1912.08830](https://arxiv.org/abs/1912.08830) Code link: [https://github.com/daveredrum/ScanRefer](https://github.com/daveredrum/ScanRefer) Paper name: ReferIt3D: Neural Listeners for Fine-Grained 3D Object Identification in Real-World...
I'm pretty confused because there's no loss calculated in validation phase. Normally there should be some validation loss/accuracy/perplexity, especially for CV tasks. However there's only some NLP metrics for captions...
Hey there, I made some small changes to the code and let the scripts work under the python 3.x environment. The code is already tested on Ubuntu 16.04 LTS &...
I'm pretty confused because there's no loss calculated in validation phase. Normally there should be some validation loss/accuracy/perplexity. Do we really need to calculate validation loss for the generated captions?