Rohun

[BUG] Segmentation Fault in proposal.cc

1

The code breaks if the proposal.cc is used to run NMS. This issue comes up when running the detection_test.py on the cpu. On using a GPU, the code runs successfully,...

Thanks for your great work! Have you experimented with arccos based normal loss. Does the performance vary when using arccos instead of (1 - normalized inner product)? The code I...

The NLP NER example only predicts correct Os

2

Hi, the NER example has an accuracy of 0.82 or 0.78 after running for 10 epochs on the toy 10 values dataset. I was using this code to startup a...

Can you share the numbers on the performance of the model? I am curious whether the audio signal improves the Video VQA at all

Dataset generated with the ShareCaptioner-Video

1

Hi, Thanks for the great work. I am interested in the set of video used for training the text to video models. Have you shared the captions of the 4.8M...

Hi, Thanks for the great work. I am interested in which set of videos were used for the evaluation of the ShareCaptionerVideo vs. GPT4V. In table 7 in the paper,...

Hi, Thanks for sharing this solid model. In the paper, there is mention of pooling ablations in section X. I believe thats in the appendix. But the arxiv version does...