Learnable Pooling Methods for Video Classification

October 01, 2018 · Entered Twilight · 🏛 ECCV Workshops

"Last commit was 7.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: .gitignore, LICENSE, README.md, __init__.py, aggregation_modules.py, attention_modules.py, average_precision_calculator.py, eval.py, eval_util.py, export_model.py, frame_level_models.py, inference.py, losses.py, mean_average_precision_calculator.py, model_utils.py, models.py, module_utils.py, modules.py, paper, pathmagic.py, readers.py, rnn_modules.py, scripts, train.py, transformer_utils.py, utils.py, video_level_models.py, video_pooling_modules.py

Authors Sebastian Kmiec, Juhan Bae, Ruijian An arXiv ID 1810.00530 Category cs.CV: Computer Vision Citations 12 Venue ECCV Workshops Repository https://github.com/pomonam/LearnablePoolingMethods ⭐ 38 Last Checked 1 month ago

Abstract

We introduce modifications to state-of-the-art approaches to aggregating local video descriptors by using attention mechanisms and function approximations. Rather than using ensembles of existing architectures, we provide an insight on creating new architectures. We demonstrate our solutions in the "The 2nd YouTube-8M Video Understanding Challenge", by using frame-level video and audio descriptors. We obtain testing accuracy similar to the state of the art, while meeting budget constraints, and touch upon strategies to improve the state of the art. Model implementations are available in https://github.com/pomonam/LearnablePoolingMethods.