Dynamic Inference: A New Approach Toward Efficient Video Action Recognition
By João Carreira, Karen Simonyan, Brian Zhang, Chloe Hillier, Sudheendra Vijayanarasimhan, Fabio Viola. 2020
Subfields: Computer Vision and Pattern Recognition, Efficiency & Compression
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Trevor Darrell
- Dacheng Tao
- Xiaogang Wang
- Alan L. Yuille
- Jitendra Malik
- Andrew Zisserman
- Andrea Vedaldi
In Efficiency & Compression
- Rameswar Panda
- Shiji Song
- Gao Huang
- Kate Saenko
- Aude Oliva
- Yulin Wang
- Rogério Schmidt Feris
- Boqing Gong
Citations in the corpus
- MoViNets: Mobile Video Networks for Efficient Video Recognition (2021, background): “Other works aim to improve 2D CNNs’ accuracy using temporal aggregation [48, 23, 82, 51, 22], however their limited inter-frame interactions reduce these models’ abilities to adequately model long-range temporal dependencies like 3D CNNs.”
- Adaptive Focus for Efficient Video Recognition (2021, background): “Since f L only needs to process a series of relatively small regions instead of the full images, this stage also enjoys high efficiency.”
- AdaFuse: Adaptive Temporal Fusion Network for Efficient Action Recognition (2021, background): “Best viewed in color. proposed that add decision branches to different layers of CNNs to learn whether to exit the network for faster inference (Figurnov et al., 2017; McGill & Perona, 2017; Wu et al., 2020).”