VLSP2021 vieCap4H Challenge: Automatic image caption generation for healthcare domains in Vietnamese Forum

Go back to competition Back to thread list Post in this thread

> [Announcement] Register pre-trained models

Dear participants,

This is a gentle reminder that pre-trained models are allowed to be used, but you need to register them before 15/10/2021.
To register, please list out in this thread the pre-trained models used by your team with detailed information such as model version/link.

Please also remember to submit the user agreement form by 20/10/2021.

For more information about the important dates and instructions, please refer to the challenge's website: https://vlsp.org.vn/vlsp2021/eval/vieCap4H

If you have any inquires, feel free to contact us (privately) at [email protected] or publicly at https://groups.google.com/g/viecap4h-organizers.

Thank you.

VLSP 2021 - vieCap4H Challenge Organizers

Posted by: viecap4h-organizers @ Oct. 7, 2021, 9:14 a.m.

My team is using the pretrained Imagenet model

Posted by: coder_phuho @ Oct. 10, 2021, 10:21 a.m.

This is the pre-trained model list that we used for this competition:
- Faster R-CNN ResNet101 Pretrained on Genome Dataset
- Using pretrained ResNet152 on COCO dataset
- Resnet101 pretrain on COCO dataset

Posted by: tiendv @ Oct. 14, 2021, 1:51 p.m.

Below we list our pre-trained models:
1. ResNeXt-101 and ResNeXt-152 for extracting image features.
2. vinai/phobert-base, vinai/phobert-large, vinai/bartpho-syllable, vinai/bartpho-word for extracting sequence features.
3. VnCoreNLP, trankit for text segmentation.

Posted by: caodoanhuit @ Oct. 14, 2021, 6:37 p.m.

In this competition we used:
- Faster RCNN pretrained on Visual Genome
- Bert-base-multilingual, vinai/phobert-base
- VnCoreNLP
- Style Augmented Translation model

Posted by: sonhua3010 @ Oct. 15, 2021, 1:19 p.m.

here is the pre-trained model list my team used:
- Faster R-CNN Pretrained on Genome Dataset,
- resnet101 pretrain on COCO, Imagenet dataset
- vinai/phobert-base, VnCoreNLP

Posted by: cuongng.m @ Oct. 15, 2021, 3:32 p.m.

I want to list our pretrained models used in detail than before:
Swin-Transformer, ViT Transformer, Efficientnet pretrained on Imagenet.
word2vec_vi_words_300dims pretrained model
cc.vi.300.vec.gz pretrained model

Posted by: coder_phuho @ Oct. 16, 2021, 1:17 a.m.

The pretrained models we used are:
- ViT32
- imthanhlv/gpt2news

Posted by: gpt-team @ Oct. 16, 2021, 10:32 a.m.
Post in this thread