Minhyuk Choi
@Andy1621 I can't find question annotations, as well as options you mentioned. I navigated the datasets, but the question annotations were not in the original datasets. At least It seems...
@Andy621 Could you provide the prompt for MovieNet and VLN-CE?
For example in scene_transition, ``` "video": "Top006_08310.mp4", "question": "Which choice matches the scene changes in the video?", "candidates": [ "From the kitchen to the dining room.", "From the staircase to...
In addition, It seems that MovieNet currently does not provide video data due to copyright issue. Where did you get videos like Top006_08310.mp4?
I see. It seems the dataset hasn't released yet. Is there any plan to release it? Or could you provide me with the dataset?
In action sequence task of STAR dataset, the paper states that it directly adopts QA of original dataset. However, annotation is quite different from the original one. In the annotation...
@guanjunwu I'm also curious about implementation of function smooth_camera_poses ``` def smooth_camera_poses(cameras, num_interpolations=5): """对一系列相机位姿进行平滑处理，通过在每对位姿之间插入额外的位姿""" smoothed_cameras = [] smoothed_times = [] total_poses = len(cameras) - 1 + (len(cameras) - 1) *...
@muximuxi It seems that he didn't take into account shs_deform weights because the original gs4d turns it off by default. You can ignore it by passing strict=False to load_state_dict function
@antithing same here
@jamesjjk Maybe I have to compare the code with the original one before authors reply the issue