GitHub

Visual Commonsense-aware Representation Network for Video Captioning

The repository contains the code of "Visual Commonsense-aware Representation Network for Video Captioning".

More details such as features of the image and text will be provided soon. Please wait patiently.

Conda env: link code:4odz

Name		Name	Last commit message	Last commit date
Latest commit History 3 Commits
caption-eval		caption-eval
log_msrvtt		log_msrvtt
models		models
models_baseline		models_baseline
models_hierarchy		models_hierarchy
utils		utils
.gitignore		.gitignore
README.md		README.md
evaluate&test_for_cluster.py		evaluate&test_for_cluster.py
evaluate.py		evaluate.py
hierarchy_cluster.py		hierarchy_cluster.py
readme.md		readme.md
requirements.txt		requirements.txt
run.sh		run.sh
run_test_msr_vtt.sh		run_test_msr_vtt.sh
run_test_msvd.sh		run_test_msvd.sh
run_train_msr_vtt.sh		run_train_msr_vtt.sh
run_train_msvd.sh		run_train_msvd.sh
run_train_vatex.sh		run_train_vatex.sh
sample.py		sample.py
train.py		train.py
train_for_cluster_feature+cluster_trainvaltest.py		train_for_cluster_feature+cluster_trainvaltest.py