ltc

ltc copied to clipboard

Extraction of flow based features

2

Hi, I am trying to understand your code line by line but I did not work with lua torch so I am facing some difficulties to execute it. I am...

znbmalik

Splitting channels with t frames

3

For example, I have a 210 frames video and t = 20 then input is created such that each input is made of 58x58x20 but the last one will be...

raaghavradhakrishnan

Need Network architecture explanation

2

I am new to this field and wanted an explanation of what network architecture has been used in the given paper. The paper explains the architecture but it is not...

ajay9022

What does the paper mean by different temporal extent being used on 60f network?

7

I was reading the paper `Long-term Temporal Convolutions for Action Recognition` and read that they have tried different temporal extent `t ∈{20,40,60,80,100}` on the 60f Network. I didn't get the...

ajay9022

How long it takes to compute optical flow for UCF101 dataset?

2

@gulvarol Hi, I want to compute optical flow for UCF101 datasets. Do you remember how long it takes? Thanks for your help.

LongLong-Jing

What are the different data augmentation techniques followed in the paper?

1

In the paper, accuracy for different data-augmentation techniques have been such as **1. Random-clipping 2. Multiscale-cropping** I didn't understand what they mean. I read something on `Random-clipping` but it wasn't...

ajay9022

Error while running main.lua

3

Hello, Your work is detailed and the effort you have put into this is awesome. I am trying to reproduce this work for a mini project. I am experimenting on...

lkpvignesh

convert_model_caffe_torch

1

Thanks for your nice code and wonderful works! @gulvarol I noticed that you converted the C3D caffemodel into torch model. Could you please share the code that convert the torch...

3DMM-ICME2023