# AR-Net: Adaptive Frame Resolution for Efficient Action Recognition

arXiv: https://arxiv.org/abs/2007.15796 · HTML: https://mlsanity.com/paper/2007.15796/

## Key facts

- Cited by 88 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Jul 2020.

## Built on by (most cited first, 30 of 88)

- [Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives](https://mlsanity.com/paper/2311.18259/) (2023)
- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [AdaViT: Adaptive Vision Transformers for Efficient Image Recognition](https://mlsanity.com/paper/2111.15668/) (2021)
- [IA-RED2: Interpretability-Aware Redundancy Reduction for Vision Transformers](https://mlsanity.com/paper/2106.12620/) (2021)
- [Selective Structured State-Spaces for Long-Form Video Understanding](https://mlsanity.com/paper/2303.14526/) (2023)
- [An Image is Worth 16x16 Words, What is a Video Worth?](https://mlsanity.com/paper/2103.13915/) (2021)
- [Adaptive Focus for Efficient Video Recognition](https://mlsanity.com/paper/2105.03245/) (2021)
- [FrameExit: Conditional Early Exiting for Efficient Video Recognition](https://mlsanity.com/paper/2104.13400/) (2021)
- [MGSampler: An Explainable Sampling Strategy for Video Action Recognition](https://mlsanity.com/paper/2104.09952/) (2021)
- [Contrast and Mix: Temporal Contrastive Video Domain Adaptation with Background Mixing](https://mlsanity.com/paper/2110.15128/) (2021)
- [AdaFuse: Adaptive Temporal Fusion Network for Efficient Action Recognition](https://mlsanity.com/paper/2102.05775/) (2021)
- [AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning](https://mlsanity.com/paper/2412.03248/) (2024)
- [AdaFocus V2: End-to-End Training of Spatial Dynamic Networks for Video Recognition](https://mlsanity.com/paper/2112.14238/) (2021)
- [AdaMML: Adaptive Multi-Modal Learning for Efficient Video Recognition](https://mlsanity.com/paper/2105.05165/) (2021)
- [Dynamic Network Quantization for Efficient Video Inference](https://mlsanity.com/paper/2108.10394/) (2021)
- [Skip-Convolutions for Efficient Video Processing](https://mlsanity.com/paper/2104.11487/) (2021)
- [EgoDistill: Egocentric Head Motion Distillation for Efficient Video Understanding](https://mlsanity.com/paper/2301.02217/) (2023)
- [MAR: Masked Autoencoders for Efficient Action Recognition](https://mlsanity.com/paper/2207.11660/) (2022)
- [Coarse-Fine Networks for Temporal Activity Detection in Videos](https://mlsanity.com/paper/2103.01302/) (2021)
- [Task2Sim : Towards Effective Pre-training and Transfer from Synthetic Data](https://mlsanity.com/paper/2112.00054/) (2021)
- [OCSampler: Compressing Videos to One Clip with Single-step Sampling](https://mlsanity.com/paper/2201.04388/) (2022)
- [AdaSGN: Adapting Joint Number and Model Size for Efficient Skeleton-Based Action Recognition](https://mlsanity.com/paper/2103.11770/) (2021)
- [Can An Image Classifier Suffice For Action Recognition?](https://mlsanity.com/paper/2106.14104/) (2021)
- [Training a Large Video Model on a Single Machine in a Day](https://mlsanity.com/paper/2309.16669/) (2023)
- [DyFADet: Dynamic Feature Aggregation for Temporal Action Detection](https://mlsanity.com/paper/2407.03197/) (2024)
- [Efficient Deep Visual and Inertial Odometry with Adaptive Visual Modality Selection](https://mlsanity.com/paper/2205.06187/) (2022)
- [AdaFocusV3: On Unified Spatial-temporal Dynamic Video Recognition](https://mlsanity.com/paper/2209.13465/) (2022)
- [SpotEM: Efficient Video Search for Episodic Memory](https://mlsanity.com/paper/2306.15850/) (2023)
- [VA-RED2: Video Adaptive Redundancy Reduction](https://mlsanity.com/paper/2102.07887/) (2021)
- [Gate-Shift-Fuse for Video Action Recognition](https://mlsanity.com/paper/2203.08897/) (2022)

## Abstract (arXiv)

Action recognition is an open and challenging problem in computer vision. While current state-of-the-art models offer excellent recognition results, their computational expense limits their impact for many real-world applications. In this paper, we propose a novel approach, called AR-Net (Adaptive Resolution Network), that selects on-the-fly the optimal resolution for each frame conditioned on the input for efficient action recognition in long untrimmed videos. Specifically, given a video frame, a policy network is used to decide what input resolution should be used for processing by the action recognition model, with the goal of improving both accuracy and efficiency. We efficiently train the policy network jointly with the recognition model using standard back-propagation. Extensive experiments on several challenging action recognition benchmark datasets well demonstrate the efficacy of our proposed approach over state-of-the-art methods. The project page can be found at https://mengyuest.github.io/AR-Net