# Dynamic Sampling Networks for Efficient Action Recognition in Videos

arXiv: https://arxiv.org/abs/2006.15560 · HTML: https://mlsanity.com/paper/2006.15560/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Jun 2020.

## Built on by (most cited first, 30 of 34)

- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer](https://mlsanity.com/paper/2211.09552/) (2022)
- [An Image is Worth 16x16 Words, What is a Video Worth?](https://mlsanity.com/paper/2103.13915/) (2021)
- [FERV39k: A Large-Scale Multi-Scene Dataset for Facial Expression Recognition in Videos](https://mlsanity.com/paper/2203.09463/) (2022)
- [FrameExit: Conditional Early Exiting for Efficient Video Recognition](https://mlsanity.com/paper/2104.13400/) (2021)
- [Efficient Video Transformers with Spatial-Temporal Token Selection](https://mlsanity.com/paper/2111.11591/) (2021)
- [MGSampler: An Explainable Sampling Strategy for Video Action Recognition](https://mlsanity.com/paper/2104.09952/) (2021)
- [MAR: Masked Autoencoders for Efficient Action Recognition](https://mlsanity.com/paper/2207.11660/) (2022)
- [OCSampler: Compressing Videos to One Clip with Single-step Sampling](https://mlsanity.com/paper/2201.04388/) (2022)
- [Diff-IP2D: Diffusion-Based Hand-Object Interaction Prediction on Egocentric Videos](https://mlsanity.com/paper/2405.04370/) (2024)
- [Efficient Video Action Detection with Token Dropout and Context Refinement](https://mlsanity.com/paper/2304.08451/) (2023)
- [MADiff: Motion-Aware Mamba Diffusion Models for Hand Trajectory Prediction on Egocentric Videos](https://mlsanity.com/paper/2409.02638/) (2024)
- [NSNet: Non-saliency Suppression Sampler for Efficient Video Recognition](https://mlsanity.com/paper/2207.10388/) (2022)
- [Spatiotemporal Self-attention Modeling with Temporal Patch Shift for Action Recognition](https://mlsanity.com/paper/2207.13259/) (2022)
- [Computation-efficient Deep Learning for Computer Vision: A Survey](https://mlsanity.com/paper/2308.13998/) (2023)
- [The Wisdom of Crowds: Temporal Progressive Attention for Early Action Prediction](https://mlsanity.com/paper/2204.13340/) (2022)
- [Active Acquisition for Multimodal Temporal Data: A Challenging Decision-Making Task](https://mlsanity.com/paper/2211.05039/) (2022)
- [MAMBA4D: Efficient Long-Sequence Point Cloud Video Understanding with Disentangled Spatial-Temporal State Space Models](https://mlsanity.com/paper/2405.14338/) (2024)
- [Motion-driven Visual Tempo Learning for Video-based Action Recognition](https://mlsanity.com/paper/2202.12116/) (2022)
- [AsConvSR: Fast and Lightweight Super-Resolution Network with Assembled Convolutions](https://mlsanity.com/paper/2305.03387/) (2023)
- [PMI Sampler: Patch Similarity Guided Frame Selection for Aerial Action Recognition](https://mlsanity.com/paper/2304.06866/) (2023)
- [Revisiting Kernel Temporal Segmentation as an Adaptive Tokenizer for Long-form Video Understanding](https://mlsanity.com/paper/2309.11569/) (2023)
- [MRSN: Multi-Relation Support Network for Video Action Detection](https://mlsanity.com/paper/2304.11975/) (2023)
- [Uni-Hand: Universal Hand Motion Forecasting in Egocentric Views](https://mlsanity.com/paper/2511.12878/) (2025)
- [Cross-Modal Graph with Meta Concepts for Video Captioning](https://mlsanity.com/paper/2108.06458/) (2021)
- [Audio-Visual Glance Network for Efficient Video Recognition](https://mlsanity.com/paper/2308.09322/) (2023)
- [Champion Solution for the WSDM2023 Toloka VQA Challenge](https://mlsanity.com/paper/2301.09045/) (2023)
- [Action Keypoint Network for Efficient Video Recognition](https://mlsanity.com/paper/2201.06304/) (2022)
- [Zero-Shot Temporal Interaction Localization for Egocentric Videos](https://mlsanity.com/paper/2506.03662/) (2025)
- [Efficient Human Vision Inspired Action Recognition using Adaptive Spatiotemporal Sampling](https://mlsanity.com/paper/2207.05249/) (2022)

## Abstract (arXiv)

The existing action recognition methods are mainly based on clip-level classifiers such as two-stream CNNs or 3D CNNs, which are trained from the randomly selected clips and applied to densely sampled clips during testing. However, this standard setting might be suboptimal for training classifiers and also requires huge computational overhead when deployed in practice. To address these issues, we propose a new framework for action recognition in videos, called em Dynamic Sampling Networks (DSN), by designing a dynamic sampling module to improve the discriminative power of learned clip-level classifiers and as well increase the inference efficiency during testing. Specifically, DSN is composed of a sampling module and a classification module, whose objective is to learn a sampling policy to on-the-fly select which clips to keep and train a clip-level classifier to perform action recognition based on these selected clips, respectively. In particular, given an input video, we train an observation network in an associative reinforcement learning setting to maximize the rewards of the selected clips with a correct prediction. We perform extensive experiments to study different aspects of the DSN framework on four action recognition datasets: UCF101, HMDB51, THUMOS14, and ActivityNet v1.3. The experimental results demonstrate that DSN is able to greatly improve the inference efficiency by only using less than half of the clips, which can still obtain a slightly better or comparable recognition accuracy to the state-of-the-art approaches.