computer-vision-2

Sports Analytics

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in sports-analytics-2

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find sports-analytics-2 models and implementations

wywywang/coachai-projects

2 papers 70

Datasets

No datasets available.

Subtasks

No subtasks available.

Most implemented papers

Sports Camera Calibration via Synthetic Data

J. Little, Jianhui Chen•Wed Oct 24 2018

This work develops a novel camera pose engine that generates camera poses by randomly sampling camera parameters and uses a novel GAN (generative adversarial network) model to detect field markings in real images.

85

Content

0

Paper Graph

ActNetFormer: Transformer-ResNet Hybrid Method for Semi-Supervised Action Recognition in Videos

Sharana Dharshikgan Suresh Dass, H. Barua, Ganesh Krishnasamy, Raveendran Paramesran, Raphael C.-W. Phan•Mon Apr 08 2024

This work proposes a novel approach using Cross-Architecture Pseudo-Labeling with contrastive learning for semi-supervised action recognition, combining pseudo-labeling with contrastive learning for effective learning from both types of samples.

6 0

Paper Graph

Cracking the Black Box: Distilling Deep Sports Analytics

O. Schulte, Xiangyu Sun, Jack Davis, Guiliang Liu•Wed Jun 03 2020

A simple and transparent model is built that mimics the output of the original deep learning model and represents the learned knowledge in an explicit interpretable way to address the computational challenge from datasets with millions of data points.

27 0

Paper Graph

Applying Deep Learning to Basketball Trajectories

R. Shah, Rob Romijnders•Thu Aug 11 2016

Using a dataset of over 20,000 three pointers from NBA SportVu data, recurrent neural networks based simply on sequential positional data outperform a static feature rich machine learning model in predicting whether a three-point shot is successful.

59 0

Paper Graph

From Motor Control to Team Play in Simulated Humanoid Football

H. F. Song, N. Heess, Tuomas Haarnoja, Yuval Tassa, Brendan D. Tracey, T. Graepel, Wojciech M. Czarnecki, S. Eslami, A. Abdolmaleki, J. Merel, Leonard Hasenclever, Siqi Liu, Guy Lever, Zhe Wang, Daniel Hennes, Shayegan Omidshafiei, Noah Siegel, Luke Marris, S. Tunyasuvunakool, Markus Wulfmeier, Paul Muller, K. Tuyls•Mon May 24 2021

This work optimized teams of agents to play simulated football via reinforcement learning, constraining the solution space to that of plausible movements learned using human motion capture data, resulting in a team of coordinated humanoid football players that exhibit complex behavior at different scales, quantified by a range of analysis and statistics.

153 0

Paper Graph

DeepSportLab: a Unified Framework for Ball Detection, Player Instance Segmentation and Pose Estimation in Team Sports Scenes

C. Vleeschouwer, Gabriel Van Zandycke, M. Istasse, Seyed Abolfazl Ghasemzadeh, Niels Sayez, A. Moshtaghpour•Tue Nov 30 2021

A single model is proposed that simultaneously predicts the ball and the player mask and pose by combining the part intensity fields and the spatial embeddings principles, achieving comparable performance to the SoA models addressing each individual task separately.

15 0

Paper Graph

LTC-GIF: Attracting More Clicks on Feature-length Sports Videos

G. Mujtaba, Jaehyuk Choi, Eun‐Seok Ryu•Fri Jan 21 2022

This paper proposes a lightweight method to attract users and increase views of the video by presenting personalized artistic media -- i.e, static thumbnails and animated GIFs, the first technique that uses LTC to generate artistic media while providing lightweight and high-performance services even on resource-constrained devices.

0 0

Paper Graph

SkeleVision: Towards Adversarial Resiliency of Person Tracking with Multi-Task Learning

Duen Horng Chau, Nilaksh Das, Shengyun Peng•Fri Apr 01 2022

This work studies the impact of multi-task learning (MTL) on the adversarial robustness of the widely used SiamRPN tracker, in the context of person tracking, and investigates the effect of jointly learning with semantically analogous tasks of persontracking and human keypoint detection.

2 0

Paper Graph

Unsupervised Learning of Neurosymbolic Encoders

Jennifer J. Sun, A. Kennedy, Eric Zhan, Yisong Yue, Swarat Chaudhuri•Tue Jul 27 2021

This work integrates modern program synthesis techniques with the variational autoencoding (VAE) framework, in order to learn a neurosymbolic encoder in conjunction with a standard decoder, and shows that this approach offers significantly better separation of meaningful categories than standard VAEs and leads to practical gains on downstream analysis tasks.

15 0

Paper Graph

A Survey on Video Action Recognition in Sports: Datasets, Methods and Applications

Haoyi Xiong, D. Dou, Jiang Bian, Feixiang Lu, Fei Wu, Qingzhong Wang, Junqing Cheng•Wed Jun 01 2022

To facilitate sports analytics, a toolbox using PaddlePaddle is developed, which supports football, basketball, table tennis and figure skating action recognition, and discusses the challenges and unsolved problems in this area.

89 0

Paper Graph

Adding a benchmark result helps the community track progress.