paper-with-me

Papers

Attentive Spatio-Temporal Representation Learning for Diving Classification

2019-04-30 · Gagan Kanojia, Sudhakar Kumawat, Shanmuganathan Raman

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.

📄 PDF Abstract BibTeX arXiv:1905.00050

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationGeneral ClassificationRepresentation Learning

Similar Papers 제목 키워드 기반

FineParser: A Fine-grained Spatio-temporal Action Parser for Human-centric Action Quality Assessment

2024-05-11 · CVPR 2024 1 · Jinglin Xu, Sibo Yin, Guohao Zhao, Zishuo Wang 외

Existing action quality assessment (AQA) methods mainly learn deep representations at the video level for scoring diverse actions. Due to the lack of a fine-grained understanding of actions in videos, they harshly suffer…

Action Quality AssessmentAction Understanding

Context-Aware Network Based on Multi-scale Spatio-temporal Attention for Action Recognition in Videos

2025-12-21 · Xiaoyang Li, Wenzhu Yang, Kanglin Wang, Tiebiao Wang 외 arxiv

Action recognition is a critical task in video understanding, requiring the comprehensive capture of spatio-temporal cues across various scales. However, existing methods often overlook the multi-granularity nature of ac…

Action Recognition In Videos

Temporal-attentive Covariance Pooling Networks for Video Recognition

2021-10-27 · NeurIPS 2021 12 · Zilin Gao, Qilong Wang, Bingbing Zhang, QinGhua Hu 외

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 usi…

Video Recognition

UTAL-GNN: Unsupervised Temporal Action Localization using Graph Neural Networks

2025-08-27 · Bikash Kumar Badatya, Vipul Baghel, Ravi Hegde arxiv

Fine-grained action localization in untrimmed sports videos presents a significant challenge due to rapid and subtle motion transitions over short durations. Existing supervised and weakly supervised solutions often rely…

Temporal Action LocalizationComputational Efficiency

Dual Contrastive Learning for Spatio-temporal Representation

2022-07-12 · Shuangrui Ding, Rui Qian, Hongkai Xiong

Contrastive learning has shown promising potential in self-supervised spatio-temporal representation learning. Most works naively sample different clips to construct positive and negative pairs. However, we observe that …

Contrastive LearningRepresentation Learning