Xinpeng.Chen

go get -v github.com/huichen/sego latest ...

@xinghedyc Hi, sorry for my late response. I use the default aspect ratios, and turn the filp option as True. For your problem, I recommend this paper that may help...

@albertyou2 You can train on the chinese text dataset, then have a try. I haven't done this work.

@V1ns0n Sorry for replying so late. I have uploaded the ICDAR2011 on the Google Drive. You can download the from [the link](https://drive.google.com/open?id=0B65vBUruA6N4cXJkV283bEdjTU0)

@hhxxttxsh Hi, thank you for your question. I only use the pre-trained VGG-16 layers model to extract features. I don't back-propagate gradients both for efficiency and also to prevent overfitting....

@hhxxttxsh And, this is my understanding and explanation. By the way, in the paper: [A Hierarchical Approach for Generating Descriptive Image Paragraphs](http://cs.stanford.edu/people/ranjaykrishna/im2p/index.html), the authors also processed the images like me....

@hhxxttxsh Hi, I think you may be misunderstanding about the original code. In the original code [model.py](https://github.com/jazzsaxmafia/video_to_sequence/blob/master/model.py#L244): ```python index = list(train_data.index) np.random.shuffle(index) train_data = train_data.ix[index] ``` He only shuffled the...

@hhxxttxsh Hi, I know what you mean... In the [original paper](https://arxiv.org/abs/1505.00487), S. Venugopalan et al. have done an experiment about the shuffled frames. In section **4.3. Experimental details of our...

@hhxxttxsh Hi, I also have tested the source code by [S. Venugopalan et al](https://github.com/vsubhashini/caffe/blob/recurrent/examples/s2vt/). And the generation sentences is reasonable. I haven't trained the model by myself, just use the...

@hhxxttxsh Hi, When I only use RGB features which extracted on the VGG model, I got 28.1 of METEOR score. You can see in the **README.md** of my code. And...