SoccerNet: A Scalable Dataset for Action Spotting in Soccer Videos

@article{Giancola2018SoccerNetAS,
  title={SoccerNet: A Scalable Dataset for Action Spotting in Soccer Videos},
  author={Silvio Giancola and Mohieddine Amine and Tarek Dghaily and Bernard Ghanem},
  journal={2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
  year={2018},
  pages={1792-179210}
}
In this paper, we introduce SoccerNet, a benchmark for action spotting in soccer videos. The dataset is composed of 500 complete soccer games from six main European leagues, covering three seasons from 2014 to 2017 and a total duration of 764 hours. A total of 6,637 temporal annotations are automatically parsed from online match reports at a one minute resolution for three main classes of events (Goal, Yellow/Red Card, and Substitution). As such, the dataset is easily scalable. These… Expand
A Context-Aware Loss Function for Action Spotting in Soccer Videos
TLDR
This paper proposes a novel loss function that specifically considers the temporal context naturally present around each action, rather than focusing on the single annotated frame to spot, and demonstrates the generalization capability of this loss for generic activity proposals and detection on ActivityNet. Expand
Improved Soccer Action Spotting using both Audio and Video Streams
TLDR
This work used the SoccerNet benchmark dataset, which contains annotated events for 500 soccer game videos from the Big Five European leagues, and evaluated several ways to integrate audio stream into video-only-based architectures. Expand
Feature Combination Meets Attention: Baidu Soccer Embeddings and Transformer based Temporal Detection
TLDR
This tech report presents a two-stage paradigm to detect what and when events happen in soccer broadcast videos, fine-tune multiple action recognition models on soccer data to extract high-level semantic features, and design a transformer based temporal detection module to locate the target events. Expand
RMS-Net: Regression and Masking for Soccer Event Spotting
TLDR
A lightweight and modular network which can simultaneously predict the event label and its temporal offset using the same underlying features is devised, which reaches a gain of more than 10 Average-mAP points on the test set when fine-tuned in combination with a strong 2D backbone. Expand
SSET: a dataset for shot segmentation, event detection, player tracking in soccer videos
TLDR
A soccer dataset named SSET, which can meet the research needs of shot segmentation, soccer event detection and player tracking, and an annotation tool called Sports Video Dataset Markup (SVDM) for sports video data annotation is developed. Expand
Self-Supervised Small Soccer Player Detection and Tracking
TLDR
This work proposes a self-supervised pipeline which is able to detect and track low-resolution soccer players under different recording conditions without any need of ground-truth data and presents a comparison to several state-of-the-art methods showing that both the proposed detector and the proposed tracker achieve top-tier results. Expand
Multi-camera Temporal Grouping for Play/Break Event Detection in Soccer Games
TLDR
Raw video unit classifications by variants of the basic I3D network are post-processed by two novel and efficient grouping methods for localizing the boundaries of events. Expand
Camera Calibration and Player Localization in SoccerNet-v2 and Investigation of their Representations for Action Spotting
TLDR
This work distill a powerful commercial calibration tool in a recent neural network architecture on the largescale SoccerNet dataset, composed of untrimmed broadcast videos of 500 soccer games, and leverages it to provide 3 ways of representing the calibration results along with player localization. Expand
Temporally-Aware Feature Pooling for Action Spotting in Soccer Broadcasts
TLDR
A novel feature pooling method based on NetVLAD, dubbed netVLAD++, that embeds temporally-aware knowledge that split the context before and after an action occurs, and argues that considering the contextual information around the action spot as a single entity leads to a sub-optimal learning for the pooling module. Expand
Automatic Key Moment Extraction and Highlights Generation Based on Comprehensive Soccer Video Understanding
TLDR
The proposed system involves three crucial tasks which can be jointly used to produce highlights automatically, i.e. play-back detection, soccer event recognition and commentator emotion classification, and provides strong baselines on three tasks. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 88 REFERENCES
Goal!! Event detection in sports video
TLDR
This work develops a novel dataset for event detection in sports video and more specifically, for goal detection is football games, and investigates deep learning architectures, such as CNN and Autoencoders, for achieving efficient event detection. Expand
Fast Temporal Activity Proposals for Efficient Detection of Human Actions in Untrimmed Videos
TLDR
This paper introduces a proposal method that aims to recover temporal segments containing actions in untrimmed videos and introduces a learning framework to represent and retrieve activity proposals. Expand
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
TLDR
I3D models considerably improve upon the state-of-the-art in action classification, reaching 80.2% on HMDB-51 and 97.9% on UCF-101 after pre-training on Kinetics, and a new Two-Stream Inflated 3D Conv net that is based on 2D ConvNet inflation is introduced. Expand
Soccer Video Event Annotation by Synchronization of Attack–Defense Clips and Match Reports With Coarse-Grained Time Information
TLDR
A more generalized approach that synchronizes video events with text descriptions using high-level semantics with coarse time constraints, rather than assuming that the timestamp is given exactly in the text description. Expand
Automatic soccer video analysis and summarization
TLDR
The proposed framework includes some novel low-level processing algorithms, such as dominant color region detection, robust shot boundary detection, and shot classification, as well as some higher-level algorithms for goal detection, referee detection,and penalty-box detection. Expand
Automatic Soccer Video Event Detection Based on a Deep Neural Network Combined CNN and RNN
  • Haohao Jiang, Yao Lu, Jing Xue
  • Computer Science
  • 2016 IEEE 28th International Conference on Tools with Artificial Intelligence (ICTAI)
  • 2016
TLDR
A deep neural network is constructed to detect soccer video event and uses RNN to map the semantic features of key frames from PB to soccer event types, including goal, goal attempt, card and corner. Expand
Detecting Events and Key Actors in Multi-person Videos
TLDR
This paper proposes a model which learns to detect events in videos while automatically "attending" to the people responsible for the event, and outperforms state-of-the-art methods for both event classification and detection on this new dataset. Expand
Leveraging Contextual Cues for Generating Basketball Highlights
TLDR
The informativeness of five different cues derived from the video and from the environment are explored through user studies and show that for study participants, the highlights produced by the system are comparable to the ones produced by ESPN for the same games. Expand
Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs
TLDR
A novel loss function for the localization network is proposed to explicitly consider temporal overlap and achieve high temporal localization accuracy in untrimmed long videos. Expand
Action Classification in Soccer Videos with Long Short-Term Memory Recurrent Neural Networks
TLDR
Experimental results show that the proposed approach for action classification in soccer videos outperforms classification methods of related works, and that the combination of the two features (BoW and dominant motion) leads to a classification rate of 92%. Expand
...
1
2
3
4
5
...