# Attentive Spatio-Temporal Representation Learning for Diving Classification

arXiv: https://arxiv.org/abs/1905.00050 · HTML: https://mlsanity.com/paper/1905.00050/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Apr 2019.

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

- [Temporal-wise Attention Spiking Neural Networks for Event Streams Classification](https://mlsanity.com/paper/2107.11711/) (2021)
- [Temporal Query Networks for Fine-grained Video Understanding](https://mlsanity.com/paper/2104.09496/) (2021)
- [SkeletonMAE: Graph-based Masked Autoencoder for Skeleton Sequence Pre-training](https://mlsanity.com/paper/2307.08476/) (2023)
- [SportsCap: Monocular 3D Human Motion Capture and Fine-grained Understanding in Challenging Sports Videos](https://mlsanity.com/paper/2104.11452/) (2021)
- [Learning Self-Similarity in Space and Time as Generalized Motion for Video Action Recognition](https://mlsanity.com/paper/2102.07092/) (2021)
- [A Survey on Video Action Recognition in Sports: Datasets, Methods and Applications](https://mlsanity.com/paper/2206.01038/) (2022)
- [EAN: Event Adaptive Network for Enhanced Action Recognition](https://mlsanity.com/paper/2107.10771/) (2021)
- [Benchmarking Badminton Action Recognition with a New Fine-Grained Dataset](https://mlsanity.com/paper/2403.12385/) (2024)
- [Learning from Next-Frame Prediction: Autoregressive Video Modeling Encodes Effective Representations](https://mlsanity.com/paper/2512.21004/) (2025)
- [Adaptive Recursive Circle Framework for Fine-grained Action Recognition](https://mlsanity.com/paper/2107.11813/) (2021)
- [Video Understanding by Design: How Datasets Shape Video Models](https://mlsanity.com/paper/2509.09151/) (2025)

## Abstract (arXiv)

Competitive diving is a well recognized aquatic sport in which a person dives from a platform or a springboard into the water. Based on the acrobatics performed during the dive, diving is classified into a finite set of action classes which are standardized by FINA. In this work, we propose an attention guided LSTM-based neural network architecture for the task of diving classification. The network takes the frames of a diving video as input and determines its class. We evaluate the performance of the proposed model on a recently introduced competitive diving dataset, Diving48. It contains over 18000 video clips which covers 48 classes of diving. The proposed model outperforms the classification accuracy of the state-of-the-art models in both 2D and 3D frameworks by 11.54% and 4.24%, respectively. We show that the network is able to localize the diver in the video frames during the dive without being trained with such a supervision.