Search Results for author: Kanav Vats

Found 14 papers, 4 papers with code

Evaluating deep tracking models for player tracking in broadcast ice hockey video

no code implementations22 May 2022 Kanav Vats, Mehrnaz Fani, David A. Clausi, John S. Zelek

Tracking and identifying players is an important problem in computer vision based ice hockey analytics.

Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation

1 code implementation16 Nov 2021 William McNally, Kanav Vats, Alexander Wong, John McPhee

In keypoint estimation tasks such as human pose estimation, heatmap-based regression is the dominant approach despite possessing notable drawbacks: heatmaps intrinsically suffer from quantization error and require excessive computation to generate and post-process.

Keypoint Estimation Pose Estimation

Player Tracking and Identification in Ice Hockey

no code implementations6 Oct 2021 Kanav Vats, Pascale Walters, Mehrnaz Fani, David A. Clausi, John Zelek

The player identification model further takes advantage of the available NHL game roster data to obtain a player identification accuracy of 83%.

Event Detection Multi-Object Tracking

Multi-task learning for jersey number recognition in Ice Hockey

no code implementations17 Aug 2021 Kanav Vats, Mehrnaz Fani, David A. Clausi, John Zelek

Identifying players in sports videos by recognizing their jersey numbers is a challenging task in computer vision.

Multi-Task Learning

Puck localization and multi-task event recognition in broadcast hockey videos

no code implementations21 May 2021 Kanav Vats, Mehrnaz Fani, David A. Clausi, John Zelek

In this paper, we introduce and implement a network for puck localization in broadcast hockey video.

Multi-Task Learning

DeepDarts: Modeling Keypoints as Objects for Automatic Scorekeeping in Darts using a Single Camera

1 code implementation20 May 2021 William McNally, Pascale Walters, Kanav Vats, Alexander Wong, John McPhee

In the primary dataset containing 15k images captured from a face-on view of the dartboard using a smartphone, DeepDarts predicted the total score correctly in 94. 7% of the test images.

Data Augmentation Keypoint Detection +1

EvoPose2D: Pushing the Boundaries of 2D Human Pose Estimation using Accelerated Neuroevolution with Weight Transfer

1 code implementation17 Nov 2020 William McNally, Kanav Vats, Alexander Wong, John McPhee

Neural architecture search has proven to be highly effective in the design of efficient convolutional neural networks that are better suited for mobile deployment than hand-designed networks.

 Ranked #1 on Multi-Person Pose Estimation on MS COCO (Validation AP metric)

2D Human Pose Estimation Keypoint Detection +2

Event detection in coarsely annotated sports videos via parallel multi receptive field 1D convolutions

no code implementations13 Apr 2020 Kanav Vats, Mehrnaz Fani, Pascale Walters, David A. Clausi, John Zelek

Experimental results demonstrate the effectiveness of the network by obtaining a 55% average F1 score on the NHL dataset and by achieving competitive performance compared to the state of the art on the SoccerNet dataset.

Action Spotting Event Detection

PuckNet: Estimating hockey puck location from broadcast video

no code implementations11 Dec 2019 Kanav Vats, William McNally, Chris Dulhanty, Zhong Qiu Lin, David A. Clausi, John Zelek

The network is able to regress the puck location from broadcast hockey video clips with varying camera angles.

Beyond Explainability: Leveraging Interpretability for Improved Adversarial Learning

no code implementations21 Apr 2019 Devinder Kumar, Ibrahim Ben-Daya, Kanav Vats, Jeffery Feng, Graham Taylor and, Alexander Wong

In this study, we propose the leveraging of interpretability for tasks beyond purely the purpose of explainability.

KPTransfer: improved performance and faster convergence from keypoint subset-wise domain transfer in human pose estimation

no code implementations24 Mar 2019 Kanav Vats, Helmut Neher, Alexander Wong, David A. Clausi, John Zelek

This approach is motivated by the notion that rich contextual knowledge can be transferred between different keypoint subsets representing separate domains.

Keypoint Detection

GolfDB: A Video Database for Golf Swing Sequencing

1 code implementation15 Mar 2019 William McNally, Kanav Vats, Tyler Pinto, Chris Dulhanty, John McPhee, Alexander Wong

The golf swing is a complex movement requiring considerable full-body coordination to execute proficiently.

Temporal Hockey Action Recognition via Pose and Optical Flows

no code implementations22 Dec 2018 Zixi Cai, Helmut Neher, Kanav Vats, David Clausi, John Zelek

Third, pose and optical flow streams are fused and passed to fully-connected layers to estimate the hockey player's action.

Action Recognition Optical Flow Estimation +3

Cannot find the paper you are looking for? You can Submit a new open access paper.