Home

Awesome

perception_test_iccv2023

Champion Solutions repository for Perception Test challenges in ICCV2023 workshop.

Introduction

We achieves the best performance in Temporal Sound Localisation task and runner-up in Temporal Action Localisation task. In this repository, we provide the pretrained video&audio features, checkpoints, and codes for feature extraction, training, and inference.

Get Started

Please refer to INSTALL.md to install the prerequisite packages.

Feature Extraction

TAL

For the video features, we use the UMT large model pre-trained on Something Something-V2 and the VideoMAE model pre-trained on Ego4D-Verb dataset. The weights of Ego4d can be found here. These two features are concatenated before putting into the ActionFormer model during both training and inference stages.

For the audio features, we use the BEATs model as feature extractor and adopt its iter3+ checkpoints pre-trained on the AudioSet-2M dataset. we provide scripts to extract BEATs and CAV-MAE (although not used), please use python audio_feat_extract.py to extract audio features.

TSL

For the video feature, we use the UMT large model pre-trained on Something Something-V2 and fine-tuned on the perception test temporal action localisation training set.

For the audio features, we use the BEATs model as feature extractor and adopt its iter3+ checkpoints pre-trained on the AudioSet-2M dataset. we provide scripts to extract BEATs and CAV-MAE (although not used), please use python audio_feat_extract.py to extract audio features.

Download

FeaturesModalityTaskDownload Link
BEATs_iter2AudioTAL&TSLDownload
Ego4d_verbVideoTALDownload
UMT-L Sth Sth-V2VideoTALDownload
UMT-L Sth Sth-V2 ftVideoTSLDownload

Temporal Sound Localisation

Training

cd ./tsl/

python train.py configs/perception_tsl_multi_train.yaml

Inference

Inference on the validation set:

cd ./tsl/

python eval.py configs/perception_tsl_multi_valid.yaml ./ckpt/XXX -epoch=XX

Inference on the test set:

cd ./tsl/

python eval.py configs/perception_tsl_multi_test.yaml ./ckpt/XXX -epoch=XX --saveonly

Temporal Action Localisation

cd ./tal/

python train.py configs/perception_tal_multi_train.yaml

Inference

Inference on the validation set:

cd ./tal/

python eval.py configs/perception_tal_multi_valid.yaml ./ckpt/XXX -epoch=XX

Inference on the test set:

cd ./tal/

python eval.py configs/perception_tal_multi_test.yaml ./ckpt/XXX -epoch=XX --saveonly

Checkpoints

We release the checkpoint in the below table.

MethodTaskmAP (Valid)Download
BEATs + UMTtsl26.70ckpt
BEATs + UMT fttsl39.25ckpt
BEATs + UMTtal44.14ckpt
BEATs + UMT&VideoMAEtal46.75ckpt

Contact

If you have any questions, please contact Jiashuo Yu and Guo Chen