├── .gitignore ├── README.md ├── __pycache__ └── eval_metrics.cpython-37.pyc ├── data ├── csv_files │ ├── test.csv │ ├── train.csv │ └── val.csv ├── hdf5s ├── pickles │ └── words_list.p └── video_features ├── data_handling ├── __init__.py ├── __pycache__ │ ├── __init__.cpython-37.pyc │ ├── __init__.cpython-39.pyc │ ├── audiocaps_dataset.cpython-37.pyc │ ├── audiocaps_dataset.cpython-39.pyc │ ├── audiocaps_video_dataset.cpython-37.pyc │ └── video_transform.cpython-37.pyc ├── audiocaps_dataset.py ├── audiocaps_video_dataset.py └── video_transform.py ├── data_prep.py ├── data_unzip.sh ├── environment.yml ├── eval_metrics.py ├── models ├── AudioTransformer.py ├── I3D.py ├── S3D.py ├── S3D_labels.txt ├── SpecAugment.py ├── TransModel.py ├── __init__.py └── __pycache__ │ ├── AudioTransformer.cpython-37.pyc │ ├── I3D.cpython-37.pyc │ ├── S3D.cpython-37.pyc │ ├── SpecAugment.cpython-37.pyc │ ├── TransModel.cpython-37.pyc │ └── __init__.cpython-37.pyc ├── settings └── settings.yaml ├── submit_run.sh ├── tools ├── __init__.py ├── __pycache__ │ ├── __init__.cpython-37.pyc │ ├── __init__.cpython-39.pyc │ ├── beam.cpython-37.pyc │ ├── config_loader.cpython-37.pyc │ ├── dataset.cpython-37.pyc │ ├── dataset.cpython-39.pyc │ ├── file_io.cpython-37.pyc │ ├── file_io.cpython-39.pyc │ └── utils.cpython-37.pyc ├── beam.py ├── config_loader.py ├── dataset.py ├── file_io.py └── utils.py └── train.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/.gitignore -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/README.md -------------------------------------------------------------------------------- /__pycache__/eval_metrics.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/__pycache__/eval_metrics.cpython-37.pyc -------------------------------------------------------------------------------- /data/csv_files/test.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/data/csv_files/test.csv -------------------------------------------------------------------------------- /data/csv_files/train.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/data/csv_files/train.csv -------------------------------------------------------------------------------- /data/csv_files/val.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/data/csv_files/val.csv -------------------------------------------------------------------------------- /data/hdf5s: -------------------------------------------------------------------------------- 1 | /fsx/xuboliu/data/AudioCaps/hdf5s -------------------------------------------------------------------------------- /data/pickles/words_list.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/data/pickles/words_list.p -------------------------------------------------------------------------------- /data/video_features: -------------------------------------------------------------------------------- 1 | /fsx/xuboliu/data/AudioCaps/video_features/ -------------------------------------------------------------------------------- /data_handling/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/data_handling/__init__.py -------------------------------------------------------------------------------- /data_handling/__pycache__/__init__.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/data_handling/__pycache__/__init__.cpython-37.pyc -------------------------------------------------------------------------------- /data_handling/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/data_handling/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /data_handling/__pycache__/audiocaps_dataset.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/data_handling/__pycache__/audiocaps_dataset.cpython-37.pyc -------------------------------------------------------------------------------- /data_handling/__pycache__/audiocaps_dataset.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/data_handling/__pycache__/audiocaps_dataset.cpython-39.pyc -------------------------------------------------------------------------------- /data_handling/__pycache__/audiocaps_video_dataset.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/data_handling/__pycache__/audiocaps_video_dataset.cpython-37.pyc -------------------------------------------------------------------------------- /data_handling/__pycache__/video_transform.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/data_handling/__pycache__/video_transform.cpython-37.pyc -------------------------------------------------------------------------------- /data_handling/audiocaps_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/data_handling/audiocaps_dataset.py -------------------------------------------------------------------------------- /data_handling/audiocaps_video_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/data_handling/audiocaps_video_dataset.py -------------------------------------------------------------------------------- /data_handling/video_transform.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/data_handling/video_transform.py -------------------------------------------------------------------------------- /data_prep.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/data_prep.py -------------------------------------------------------------------------------- /data_unzip.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/data_unzip.sh -------------------------------------------------------------------------------- /environment.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/environment.yml -------------------------------------------------------------------------------- /eval_metrics.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/eval_metrics.py -------------------------------------------------------------------------------- /models/AudioTransformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/models/AudioTransformer.py -------------------------------------------------------------------------------- /models/I3D.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/models/I3D.py -------------------------------------------------------------------------------- /models/S3D.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/models/S3D.py -------------------------------------------------------------------------------- /models/S3D_labels.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/models/S3D_labels.txt -------------------------------------------------------------------------------- /models/SpecAugment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/models/SpecAugment.py -------------------------------------------------------------------------------- /models/TransModel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/models/TransModel.py -------------------------------------------------------------------------------- /models/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/models/__init__.py -------------------------------------------------------------------------------- /models/__pycache__/AudioTransformer.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/models/__pycache__/AudioTransformer.cpython-37.pyc -------------------------------------------------------------------------------- /models/__pycache__/I3D.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/models/__pycache__/I3D.cpython-37.pyc -------------------------------------------------------------------------------- /models/__pycache__/S3D.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/models/__pycache__/S3D.cpython-37.pyc -------------------------------------------------------------------------------- /models/__pycache__/SpecAugment.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/models/__pycache__/SpecAugment.cpython-37.pyc -------------------------------------------------------------------------------- /models/__pycache__/TransModel.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/models/__pycache__/TransModel.cpython-37.pyc -------------------------------------------------------------------------------- /models/__pycache__/__init__.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/models/__pycache__/__init__.cpython-37.pyc -------------------------------------------------------------------------------- /settings/settings.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/settings/settings.yaml -------------------------------------------------------------------------------- /submit_run.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/submit_run.sh -------------------------------------------------------------------------------- /tools/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/tools/__init__.py -------------------------------------------------------------------------------- /tools/__pycache__/__init__.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/tools/__pycache__/__init__.cpython-37.pyc -------------------------------------------------------------------------------- /tools/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/tools/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /tools/__pycache__/beam.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/tools/__pycache__/beam.cpython-37.pyc -------------------------------------------------------------------------------- /tools/__pycache__/config_loader.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/tools/__pycache__/config_loader.cpython-37.pyc -------------------------------------------------------------------------------- /tools/__pycache__/dataset.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/tools/__pycache__/dataset.cpython-37.pyc -------------------------------------------------------------------------------- /tools/__pycache__/dataset.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/tools/__pycache__/dataset.cpython-39.pyc -------------------------------------------------------------------------------- /tools/__pycache__/file_io.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/tools/__pycache__/file_io.cpython-37.pyc -------------------------------------------------------------------------------- /tools/__pycache__/file_io.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/tools/__pycache__/file_io.cpython-39.pyc -------------------------------------------------------------------------------- /tools/__pycache__/utils.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/tools/__pycache__/utils.cpython-37.pyc -------------------------------------------------------------------------------- /tools/beam.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/tools/beam.py -------------------------------------------------------------------------------- /tools/config_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/tools/config_loader.py -------------------------------------------------------------------------------- /tools/dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/tools/dataset.py -------------------------------------------------------------------------------- /tools/file_io.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/tools/file_io.py -------------------------------------------------------------------------------- /tools/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/tools/utils.py -------------------------------------------------------------------------------- /train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liuxubo717/V-ACT/HEAD/train.py --------------------------------------------------------------------------------