TY  - JOUR
AU  - Javier Selva
AU  - Anders S. Johansen
AU  - Sergio Escalera
AU  - Kamal Nasrollahi
AU  - Thomas B. Moeslund
AU  - Albert Clapes
PY  - 2023//
TI  - Video transformers: A survey
T2  - TPAMI
JO  - IEEE Transactions on Pattern Analysis and Machine Intelligence
SP  - 12922
EP  - 12943
VL  - 45
IS  - 11
KW  - Artificial Intelligence
KW  - Computer Vision
KW  - Self-Attention
KW  - Transformers
KW  - Video Representations
N2  - Transformer models have shown great success handling long-range interactions, making them a promising tool for modeling video. However, they lack inductive biases and scale quadratically with input length. These limitations are further exacerbated when dealing with the high dimensionality introduced by the temporal dimension. While there are surveys analyzing the advances of Transformers for vision, none focus on an in-depth analysis of video-specific designs. In this survey, we analyze the main contributions and trends of works leveraging Transformers to model video. Specifically, we delve into how videos are handled at the input level first. Then, we study the architectural changes made to deal with video more efficiently, reduce redundancy, re-introduce useful inductive biases, and capture long-term temporal dynamics. In addition, we provide an overview of different training regimes and explore effective self-supervised learning strategies for video. Finally, we conduct a performance comparison on the most common benchmark for Video Transformers (i.e., action classification), finding them to outperform 3D ConvNets even with less computational complexity.
UR  - http://dx.doi.org/10.1109/TPAMI.2023.3243465
N1  - HUPBA; no menciona
ID  - Javier Selva2023
ER  -