Xiaolong Liu

Hi @frajem I have finished the experiment. I got an accuracy of 94.24% on the UCF11 test set and 39.5% on the HMDB51 split1. How are your results?

Hi @GerardoHH @kracwarlock I randomly selected samples for training and testing on the UCF11 dataset. I noticed that many samples in the UCF11 set actually came from one long video....

Hi @rishabh135 h5 is the filename extension for HDF5 database, which is designed to store and organize large amounts of data. You need to create .h5 files yourself. [This link](https://github.com/kracwarlock/action-recognition-visual-attention/issues/1)...

@rishabh135 if you don't have enough RAM, you should use h5create and h5write to create h5 files. In that case, I guess 4GB RAM is enough. I ran the code...

Hi, I have released the code of TadTR. E2E-TAD is based on TadTR and relies on a few extra modules. I plan to release the code in this weekend.

Hi @bnu-wangxun I have released the inference code of E2E-TAD. I am still checking the training code. Will add it soon.

Hi, thanks for your interest in our work. To reproduce our results with **TSP features** on ActivityNet, some parameters need to be modified. For example, num_queries should be 50, set_cost_class...

Hi @takfate, here is my response to your questions: Soft-NMS is beneficial on ActivityNet but harmful on THUMOS14, and HACS, according to my experience. The code already includes the implementation...

Hi, I have received many emails recently. I don't know which one is yours. Can you leave your email address?

Yes. And I only reply to an email that indicates the real name and affiliation of the sender. I am afraid your email does not belong to this kind and...