# Temporal-Spatial Mapping for Action Recognition

arXiv: https://arxiv.org/abs/1809.03669 · HTML: https://mlsanity.com/paper/1809.03669/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Sep 2018.

## Built on by (most cited first, 8 of 8)

- [HARDVS: Revisiting Human Activity Recognition with Dynamic Vision Sensors](https://mlsanity.com/paper/2211.09648/) (2022)
- [Attention in Attention: Modeling Context Correlation for Efficient Video Classification](https://mlsanity.com/paper/2204.09303/) (2022)
- [ViGAT: Bottom-up event recognition and explanation in video using factorized graph attention network](https://mlsanity.com/paper/2207.09927/) (2022)
- [Efficient Spatialtemporal Context Modeling for Action Recognition](https://mlsanity.com/paper/2103.11190/) (2021)
- [Interpretable Prediction of Pulmonary Hypertension in Newborns using Echocardiograms](https://mlsanity.com/paper/2203.13038/) (2022)
- [Human Activity Recognition Using Cascaded Dual Attention CNN and Bi-Directional GRU Framework](https://mlsanity.com/paper/2208.05034/) (2022)
- [DroneAttention: Sparse Weighted Temporal Attention for Drone-Camera Based Activity Recognition](https://mlsanity.com/paper/2212.03384/) (2022)
- [SWTF: Sparse Weighted Temporal Fusion for Drone-Based Activity Recognition](https://mlsanity.com/paper/2211.05531/) (2022)

## Abstract (arXiv)

Deep learning models have enjoyed great success for image related computer vision tasks like image classification and object detection. For video related tasks like human action recognition, however, the advancements are not as significant yet. The main challenge is the lack of effective and efficient models in modeling the rich temporal spatial information in a video. We introduce a simple yet effective operation, termed Temporal-Spatial Mapping (TSM), for capturing the temporal evolution of the frames by jointly analyzing all the frames of a video. We propose a video level 2D feature representation by transforming the convolutional features of all frames to a 2D feature map, referred to as VideoMap. With each row being the vectorized feature representation of a frame, the temporal-spatial features are compactly represented, while the temporal dynamic evolution is also well embedded. Based on the VideoMap representation, we further propose a temporal attention model within a shallow convolutional neural network to efficiently exploit the temporal-spatial dynamics. The experiment results show that the proposed scheme achieves the state-of-the-art performance, with 4.2% accuracy gain over Temporal Segment Network (TSN), a competing baseline method, on the challenging human action benchmark dataset HMDB51.