Dynamic neural networks: A survey
Dynamic neural network is an emerging research topic in deep learning. Compared to static
models which have fixed computational graphs and parameters at the inference stage …
models which have fixed computational graphs and parameters at the inference stage …
X3d: Expanding architectures for efficient video recognition
C Feichtenhofer - Proceedings of the IEEE/CVF conference …, 2020 - openaccess.thecvf.com
This paper presents X3D, a family of efficient video networks that progressively expand a
tiny 2D image classification architecture along multiple network axes, in space, time, width …
tiny 2D image classification architecture along multiple network axes, in space, time, width …
A dynamic multi-scale voxel flow network for video prediction
The performance of video prediction has been greatly boosted by advanced deep neural
networks. However, most of the current methods suffer from large model sizes and require …
networks. However, most of the current methods suffer from large model sizes and require …
Survey: Exploiting data redundancy for optimization of deep learning
Data redundancy is ubiquitous in the inputs and intermediate results of Deep Neural
Networks (DNN). It offers many significant opportunities for improving DNN performance and …
Networks (DNN). It offers many significant opportunities for improving DNN performance and …
Blockdrop: Dynamic inference paths in residual networks
Very deep convolutional neural networks offer excellent recognition results, yet their
computational expense limits their impact for many real-world applications. We introduce …
computational expense limits their impact for many real-world applications. We introduce …
Listen to look: Action recognition by previewing audio
In the face of the video data deluge, today's expensive clip-level classifiers are increasingly
impractical. We propose a framework for efficient action recognition in untrimmed video that …
impractical. We propose a framework for efficient action recognition in untrimmed video that …
Sst: Single-stream temporal action proposals
Our paper presents a new approach for temporal detection of human actions in long,
untrimmed video sequences. We introduce Single-Stream Temporal Action Proposals (SST) …
untrimmed video sequences. We introduce Single-Stream Temporal Action Proposals (SST) …
Adaframe: Adaptive frame selection for fast video recognition
We present AdaFrame, a framework that adaptively selects relevant frames on a per-input
basis for fast video recognition. AdaFrame contains a Long Short-Term Memory network …
basis for fast video recognition. AdaFrame contains a Long Short-Term Memory network …
Skip rnn: Learning to skip state updates in recurrent neural networks
Recurrent Neural Networks (RNNs) continue to show outstanding performance in sequence
modeling tasks. However, training RNNs on long sequences often face challenges like slow …
modeling tasks. However, training RNNs on long sequences often face challenges like slow …
Adapting Neural Networks at Runtime: Current Trends in At-Runtime Optimizations for Deep Learning
Adaptive optimization methods for deep learning adjust the inference task to the current
circumstances at runtime to improve the resource footprint while maintaining the model's …
circumstances at runtime to improve the resource footprint while maintaining the model's …