# Fine-grained Video Categorization with Redundancy Reduction Attention

arXiv: https://arxiv.org/abs/1810.11189 · HTML: https://mlsanity.com/paper/1810.11189/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Oct 2018.

## Built on by (most cited first, 12 of 12)

- [Fine-Grained Image Analysis with Deep Learning: A Survey](https://mlsanity.com/paper/2111.06119/) (2021)
- [FineParser: A Fine-grained Spatio-temporal Action Parser for Human-centric Action Quality Assessment](https://mlsanity.com/paper/2405.06887/) (2024)
- [NSNet: Non-saliency Suppression Sampler for Efficient Video Recognition](https://mlsanity.com/paper/2207.10388/) (2022)
- [SSAN: Separable Self-Attention Network for Video Representation Learning](https://mlsanity.com/paper/2105.13033/) (2021)
- [Exploring Fine-Grained Audiovisual Categorization with the SSW60 Dataset](https://mlsanity.com/paper/2207.10664/) (2022)
- [Temporal Saliency Query Network for Efficient Video Recognition](https://mlsanity.com/paper/2207.10379/) (2022)
- [Few-Shot Fine-Grained Action Recognition via Bidirectional Attention and Contrastive Meta-Learning](https://mlsanity.com/paper/2108.06647/) (2021)
- [Optimization Planning for 3D ConvNets](https://mlsanity.com/paper/2201.04021/) (2022)
- [Class Prototypes based Contrastive Learning for Classifying Multi-Label and Fine-Grained Educational Videos](https://mlsanity.com/paper/2510.11204/) (2025)
- [HCMS: Hierarchical and Conditional Modality Selection for Efficient Video Recognition](https://mlsanity.com/paper/2104.09760/) (2021)
- [How Do You Do It? Fine-Grained Action Understanding with Pseudo-Adverbs](https://mlsanity.com/paper/2203.12344/) (2022)
- [Distill Video Datasets into Images](https://mlsanity.com/paper/2512.14621/) (2025)

## Abstract (arXiv)

For fine-grained categorization tasks, videos could serve as a better source than static images as videos have a higher chance of containing discriminative patterns. Nevertheless, a video sequence could also contain a lot of redundant and irrelevant frames. How to locate critical information of interest is a challenging task. In this paper, we propose a new network structure, known as Redundancy Reduction Attention (RRA), which learns to focus on multiple discriminative patterns by sup- pressing redundant feature channels. Specifically, it firstly summarizes the video by weight-summing all feature vectors in the feature maps of selected frames with a spatio-temporal soft attention, and then predicts which channels to suppress or to enhance according to this summary with a learned non-linear transform. Suppression is achieved by modulating the feature maps and threshing out weak activations. The updated feature maps are then used in the next iteration. Finally, the video is classified based on multiple summaries. The proposed method achieves out- standing performances in multiple video classification datasets. Further- more, we have collected two large-scale video datasets, YouTube-Birds and YouTube-Cars, for future researches on fine-grained video categorization. The datasets are available at http://www.cs.umd.edu/~chenzhu/fgvc.