# 3D CNNs with Adaptive Temporal Feature Resolutions

arXiv: https://arxiv.org/abs/2011.08652 · HTML: https://mlsanity.com/paper/2011.08652/

## Key facts

- Cited by 15 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 17 Nov 2020.

## Built on by (most cited first, 15 of 15)

- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [Adaptive Token Sampling For Efficient Vision Transformers](https://mlsanity.com/paper/2111.15667/) (2021)
- [Bodily Behaviors in Social Interaction: Novel Annotations and State-of-the-Art Evaluation](https://mlsanity.com/paper/2207.12817/) (2022)
- [Efficient Video Action Detection with Token Dropout and Context Refinement](https://mlsanity.com/paper/2304.08451/) (2023)
- [ViGAT: Bottom-up event recognition and explanation in video using factorized graph attention network](https://mlsanity.com/paper/2207.09927/) (2022)
- [Spatial-temporal Transformer-guided Diffusion based Data Augmentation for Efficient Skeleton-based Action Recognition](https://mlsanity.com/paper/2302.13434/) (2023)
- [Enhancing Action Recognition by Leveraging the Hierarchical Structure of Actions and Textual Context](https://mlsanity.com/paper/2410.21275/) (2024)
- [Identity-aware Graph Memory Network for Action Detection](https://mlsanity.com/paper/2108.11559/) (2021)
- [Uncovering the Unseen: Discover Hidden Intentions by Micro-Behavior Graph Reasoning](https://mlsanity.com/paper/2308.15169/) (2023)
- [STSM: Spatio-Temporal Shift Module for Efficient Action Recognition](https://mlsanity.com/paper/2112.02523/) (2021)
- [Gated-ViGAT: Efficient Bottom-Up Event Recognition and Explanation Using a New Frame Selection Policy and Gating Mechanism](https://mlsanity.com/paper/2301.07565/) (2023)
- [Beyond the Horizon: Decoupling Multi-View UAV Action Recognition via Partial Order Transfer](https://mlsanity.com/paper/2504.20530/) (2025)
- [IndGIC: Supervised Action Recognition under Low Illumination](https://mlsanity.com/paper/2308.15345/) (2023)
- [Smooth regularization for efficient video recognition](https://mlsanity.com/paper/2511.20928/) (2025)
- [Effects of Different Attention Mechanisms Applied on 3D Models in Video Classification](https://mlsanity.com/paper/2601.10854/) (2026)

## Abstract (arXiv)

While state-of-the-art 3D Convolutional Neural Networks (CNN) achieve very good results on action recognition datasets, they are computationally very expensive and require many GFLOPs. While the GFLOPs of a 3D CNN can be decreased by reducing the temporal feature resolution within the network, there is no setting that is optimal for all input clips. In this work, we therefore introduce a differentiable Similarity Guided Sampling (SGS) module, which can be plugged into any existing 3D CNN architecture. SGS empowers 3D CNNs by learning the similarity of temporal features and grouping similar features together. As a result, the temporal feature resolution is not anymore static but it varies for each input video clip. By integrating SGS as an additional layer within current 3D CNNs, we can convert them into much more efficient 3D CNNs with adaptive temporal feature resolutions (ATFR). Our evaluations show that the proposed module improves the state-of-the-art by reducing the computational cost (GFLOPs) by half while preserving or even improving the accuracy. We evaluate our module by adding it to multiple state-of-the-art 3D CNNs on various datasets such as Kinetics-600, Kinetics-400, mini-Kinetics, Something-Something V2, UCF101, and HMDB51.