LGI4temporalgrounding

LGI4temporalgrounding copied to clipboard

Hi. Jonghwan. All links for data and pretrained model downloading are broken. Could you please update the links? It would be really helpful. Thank you very much. Best regards, Damon

damon-demon

About I3D feature

5

Hi, thanks for releasing your code! I have a question about how you extract the feature in Charades dataset with I3D model. Could you help me with it? Thanks in...

xljh0520

hi, i meet this issue, do you know how to fix it ? the log is as followings: ``` File "/data1/chentongbao/single_moment_retrieval/LGI4temporalgrounding/src/utils/eval_utils.py", line 57, in eval_instance cur_tiou = compute_tiou(loc, gt) File...

tongbaochen

in compute_tiou return float(intersection) / union ZeroDivisionError: float division by zero

2

The data at this time is： pred[0]=35.27944378733635 pred[1]=33.94881270647049 gt[0]=34.77 gt[1]=34.77

nickheat8830

hi, the rule to get_fixed_length_feat is ambiguous to me, especially the spos ,random_end ,and s setting . besides,the length of s ==num_segment? or s > num_segment ? thanks for you...

TAY-985

the useage of self.count

3

hello, in train.py and test() function , they all call the function save_results() , i can not understand self.count very well . What is the role of self.count ?What to...

TAY-985

"video_masks" and "grounding_att_masks"

2

hello, May i ask you a question? what is the difference between "video_masks" and "grounding_att_masks", i know the "grounding_att_masks", but i do not understand "video_masks" ? how it is used?

TAY-985

do you use the pre_trained glove feature?

4

Hello, I see glove_path is none. Didn't you use glove during training? 

TAY-985

lower evaluation metrics with pretrained model

8

Hi, I evaluate the provided pretrained model on ActivityNet. However, the result seems much inferior than your: [Test] -1 epoch 0 iter, R1-0.1 = 0.5197, R1-0.3 = 0.3310, R1-0.5 =...

peijunbao

Hi, can you provide the running time on each video? Thank you

liudaizong