TY - DATA T1 - Code underlying the publication: "Video BagNet: short temporal receptive fields increase robustness in long-term action recognition" PY - 2024/05/24 AU - Ombretta Strafforello AU - Xin Liu AU - Jan van Gemert AU - Klamer Schutte UR - DO - 10.4121/dc5e2fb8-6005-40cd-9afa-ff03c57d0a23.v1 KW - Computer vision KW - Action recognition KW - 3D-CNN KW - BagNet KW - Temporal receptive field N2 -
Previous work on long-term video action recognition relies on deep 3D-convolutional models that have a large temporal receptive field (RF). We argue that these models are not always the best choice for temporal modeling in videos. A large temporal receptive field allows the model to encode the exact sub-action order of a video, which causes a performance decrease when testing videos have a different sub-action order. In this work, we investigate whether we can improve the model robustness to the sub-action order by shrinking the temporal receptive field of action recognition models. For this, we design Video BagNet, a variant of the 3D ResNet-50 model with the temporal receptive field size limited to 1, 9, 17 or 33 frames. We analyze Video Bag-Net on synthetic and real-world video datasets and experimentally compare models with varying temporal receptive fields. We find that short receptive fields are robust to sub-action order changes, while larger temporal receptive fields are sensitive to the sub-action order. In this repository, we provide our code, including the implementation of Video Bag-Net.
ER -