Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Home
Viewadapt-det: View-adaptive Detection For Soccer Broadcasting Videos.

Home
Viewadapt-det: View-adaptive Detection For Soccer Broadcasting Videos.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

MRI-based deep learning combined with radiomics for the preoperative prediction of lymphovascular invasion in patients with bladder cancer.

Cancer imaging : the official publication of the International Cancer Imaging Society·2026

Same author

Isomucronulatol 7-O-glucoside attenuates post-AMI monocyte/macrophage cardiac recruitment via HIF-1α/THBS1-mediated immunometabolic adhesion.

Journal of ethnopharmacology·2026

Same author

Predictors of treatment response to subthreshold micropulse laser and oral spironolactone therapy for central serous chorioretinopathy.

BMC ophthalmology·2026

Same author

Hybrid spatial-field attention network for meteorological data downscaling.

Scientific reports·2026

Same author

Chinese medicine Sheng Jing Decoction alleviates oligoasthenospermia by modulating PI3K/Akt and MAPK signaling pathways.

Phytomedicine : international journal of phytotherapy and phytopharmacology·2026

Same author

Robust detection for selective harvesting of field flat jujube: overcoming occlusion and small-target challenges in unstructured environments.

Frontiers in plant science·2026

Same journal

Integrated remote sensing and aeromagnetic datasets for mapping iron mineralization potential in the El-Bahariya depression in the Western Desert of Egypt.

Scientific reports·2026

Same journal

Evaluation of locally available materials as thermal insulators for PV modules.

Scientific reports·2026

Same journal

Functional and structural olfactory changes in post-COVID-19 patients detected by 7 Tesla MRI.

Scientific reports·2026

Same journal

Comparative analysis of empirical evapotranspiration models across Northern Ethiopia's Climatic Zones.

Scientific reports·2026

Same journal

Adoption of particle-based biosensing as a cost-disruptive tool for screening highly dilute sample streams for bacterial contamination.

Scientific reports·2026

Same journal

Pathways to resilient agricultural water management through contrasting governance systems in California and South Korea.

Scientific reports·2026

See all related articles

Related Experiment Videos

ViewAdapt-Det: view-adaptive detection for soccer broadcasting videos.

Chunwang Zhu¹, Yongli Zhang², Sheng Gao¹

¹Mudanjiang Normal University, Mudanjiang, 157011, China.

Scientific Reports

|June 22, 2026

View abstract on PubMed

Summary

This summary is machine-generated.

This study introduces ViewAdapt-Det, a novel framework for soccer object detection that tackles challenges from frequent view switching. It significantly improves detection accuracy and robustness, outperforming existing methods in dynamic broadcast scenarios.

Keywords:

Computer vision Deep learning Object detection Sports video analysis

Related Experiment Videos

Area of Science:

Computer Vision
Machine Learning
Sports Analytics

Background:

Object detection in soccer videos is crucial for broadcasting and analysis.
Frequent view switching in broadcasts creates challenges like abrupt visual changes and varying object appearances.
Existing methods struggle with cross-view noise and diverse object scales.

Purpose of the Study:

To develop a robust object detection framework for soccer videos that addresses view switching challenges.
To improve detection accuracy and robustness in dynamic broadcast environments.
To handle variations in object appearance across different camera views.

Main Methods:

Proposed ViewAdapt-Det framework with two modules: View-Aware Temporal Gating (VATG) and View-Conditioned Detection Modulation (VCDM).
VATG dynamically controls temporal aggregation based on shot transitions, suppressing cross-view noise.
VCDM modulates detection features based on inferred view type for view-specific processing.

Main Results:

ViewAdapt-Det demonstrated superior performance compared to existing methods on SoccerNet-Tracking, SportsMOT, and BroadcastSwitch-Soccer datasets.
The framework showed enhanced robustness against abrupt shot transitions.
VATG effectively managed temporal aggregation during view changes, and VCDM adapted feature processing to different views.

Conclusions:

ViewAdapt-Det offers a robust solution for object detection in soccer videos with frequent view changes.
The proposed modules effectively mitigate challenges posed by temporal and feature dimension variations.
This framework advances intelligent broadcasting, tactical analysis, and player tracking in soccer.