# Temporal-attentive Covariance Pooling Networks for Video Recognition

arXiv: https://arxiv.org/abs/2110.14381 · HTML: https://mlsanity.com/paper/2110.14381/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 57 of its 72 references that are in the map.
- First posted on arXiv 27 Oct 2021.

## Builds on (most cited first, 30 of 57)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [A Closer Look at Spatiotemporal Convolutions for Action Recognition](https://mlsanity.com/paper/1711.11248/) (2017)
- [The "something something" video database for learning and evaluating visual common sense](https://mlsanity.com/paper/1706.04261/) (2017)
- [Two-Stream Convolutional Networks for Action Recognition in Videos](https://mlsanity.com/paper/1406.2199/) (2014)
- [TSM: Temporal Shift Module for Efficient Video Understanding](https://mlsanity.com/paper/1811.08383/) (2018)
- [X3D: Expanding Architectures for Efficient Video Recognition](https://mlsanity.com/paper/2004.04730/) (2020)
- [Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding](https://mlsanity.com/paper/1604.01753/) (2016)
- [Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification](https://mlsanity.com/paper/1712.04851/) (2017)
- [Res2Net: A New Multi-scale Backbone Architecture](https://mlsanity.com/paper/1904.01169/) (2019)
- [Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks](https://mlsanity.com/paper/1711.10305/) (2017)
- [Convolutional Two-Stream Network Fusion for Video Action Recognition](https://mlsanity.com/paper/1604.06573/) (2016)
- [Temporal Segment Networks for Action Recognition in Videos](https://mlsanity.com/paper/1705.02953/) (2017)
- [Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding](https://mlsanity.com/paper/1606.01847/) (2016)
- [Long-Term Feature Banks for Detailed Video Understanding](https://mlsanity.com/paper/1812.05038/) (2018)
- [Bilinear CNNs for Fine-grained Visual Recognition](https://mlsanity.com/paper/1504.07889/) (2015)
- [Videos as Space-Time Region Graphs](https://mlsanity.com/paper/1806.01810/) (2018)
- [TEA: Temporal Excitation and Aggregation for Action Recognition](https://mlsanity.com/paper/2004.01398/) (2020)
- [Temporal Pyramid Network for Action Recognition](https://mlsanity.com/paper/2004.03548/) (2020)
- [STM: SpatioTemporal and Motion Encoding for Action Recognition](https://mlsanity.com/paper/1908.02486/) (2019)
- [TAM: Temporal Adaptive Module for Video Recognition](https://mlsanity.com/paper/2005.06803/) (2020)
- [Multi-modal Factorized Bilinear Pooling with Co-Attention Learning for Visual Question Answering](https://mlsanity.com/paper/1708.01471/) (2017)
- [ECO: Efficient Convolutional Network for Online Video Understanding](https://mlsanity.com/paper/1804.09066/) (2018)

## Built on by (most cited first, 11 of 11)

- [Fast Differentiable Matrix Square Root and Inverse Square Root](https://mlsanity.com/paper/2201.12543/) (2022)
- [Orthogonal SVD Covariance Conditioning and Latent Disentanglement](https://mlsanity.com/paper/2212.05599/) (2022)
- [Improving Covariance Conditioning of the SVD Meta-layer by Orthogonality](https://mlsanity.com/paper/2207.02119/) (2022)
- [ViGAT: Bottom-up event recognition and explanation in video using factorized graph attention network](https://mlsanity.com/paper/2207.09927/) (2022)
- [PM2: A New Prompting Multi-modal Model Paradigm for Few-shot Medical Image Classification](https://mlsanity.com/paper/2404.08915/) (2024)
- [Batch-efficient EigenDecomposition for Small and Medium Matrices](https://mlsanity.com/paper/2207.04228/) (2022)
- [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)
- [Cov2Pose: Leveraging Spatial Covariance for Direct Manifold-aware 6-DoF Object Pose Estimation](https://mlsanity.com/paper/2603.19961/) (2026)
- [Towards Diverse Perspective Learning with Selection over Multiple Temporal Poolings](https://mlsanity.com/paper/2403.09749/) (2024)
- [A2M2-Net: Adaptively Aligned Multi-Scale Moment for Few-Shot Action Recognition](https://mlsanity.com/paper/2509.17638/) (2025)
- [STAR: Semantic-Temporal Adaptive Representation Learning for Few-Shot Action Recognition](https://mlsanity.com/paper/2605.13202/) (2026)

## Abstract (arXiv)

For video recognition task, a global representation summarizing the whole contents of the video snippets plays an important role for the final performance. However, existing video architectures usually generate it by using a simple, global average pooling (GAP) method, which has limited ability to capture complex dynamics of videos. For image recognition task, there exist evidences showing that covariance pooling has stronger representation ability than GAP. Unfortunately, such plain covariance pooling used in image recognition is an orderless representative, which cannot model spatio-temporal structure inherent in videos. Therefore, this paper proposes a Temporal-attentive Covariance Pooling(TCP), inserted at the end of deep architectures, to produce powerful video representations. Specifically, our TCP first develops a temporal attention module to adaptively calibrate spatio-temporal features for the succeeding covariance pooling, approximatively producing attentive covariance representations. Then, a temporal covariance pooling performs temporal pooling of the attentive covariance representations to characterize both intra-frame correlations and inter-frame cross-correlations of the calibrated features. As such, the proposed TCP can capture complex temporal dynamics. Finally, a fast matrix power normalization is introduced to exploit geometry of covariance representations. Note that our TCP is model-agnostic and can be flexibly integrated into any video architectures, resulting in TCPNet for effective video recognition. The extensive experiments on six benchmarks (e.g., Kinetics, Something-Something V1 and Charades) using various video architectures show our TCPNet is clearly superior to its counterparts, while having strong generalization ability. The source code is publicly available.