X-VARS is a multi-modal large language model designed for understanding football videos from the point of view of a referee. X-VARS can perform a multitude of tasks, including video description, question answering, action recognition, and conducting meaningful conversations based on video content.
☆23Jun 18, 2024Updated last year
Alternatives and similar repositories for X-VARS
Users that are interested in X-VARS are comparing it to the libraries listed below
Sorting:
- ☆14Oct 3, 2023Updated 2 years ago
- SoccerNet@CVPR | 1st place solution for Camera Calibration Challenge 2023☆59Dec 30, 2024Updated last year
- ☆56Jan 9, 2025Updated last year
- ☆40Jul 16, 2025Updated 7 months ago
- VidPress Sports☆32Feb 4, 2023Updated 3 years ago
- [ECCV 2024] PyTorch implementation of CropMAE, introduced in "Efficient Image Pre-Training with Siamese Cropped Masked Autoencoders"☆60Feb 27, 2025Updated last year
- ☆15Mar 7, 2024Updated last year
- [CVPR 2024] Zero-shot method for Vision-Language Models based on a robust formulation of the MeanShift algorithm for Test-time Augmentati…☆66Dec 15, 2024Updated last year
- Repository containing all necessary codes to get started on the SoccerNet Re-Identification challenge. This repository also contains benc…☆81Jul 7, 2023Updated 2 years ago
- ☆23Apr 2, 2025Updated 11 months ago
- A General Framework for Jersey Number Recognition in Sports Video☆55Oct 7, 2024Updated last year
- Repository containing all necessary codes to get started on the SoccerNet Tracking challenge. This repository also contains benchmark met…☆93Jul 7, 2023Updated 2 years ago
- Transformer based Decision Networks for MOT☆25Feb 21, 2024Updated 2 years ago
- Repository containing all necessary codes to get started on the SoccerNet Jersey Number Recognition challenge.☆27Jul 2, 2024Updated last year
- Official Implementation of ECCV2024 paper: SLAck☆29Sep 18, 2024Updated last year
- TCF-LMO is a network made with dedicated modules to process videos and identify the presence of anomalies in frames. It is composed by: d…☆12Aug 28, 2024Updated last year
- [ECCV 2024] BUSCA: "Lost and Found: Overcoming Detector Failures in Online Multi-Object Tracking"☆43Dec 6, 2024Updated last year
- SnP: Large-Scale Training Data Search for Object Re-Identification (CVPR 2023)☆37Jul 17, 2023Updated 2 years ago
- [EMNLP 2024 Oral] MatchTime: Towards Automatic Soccer Game Commentary Generation☆94Jan 2, 2025Updated last year
- A Context-Aware Loss Function for Action Spotting in Soccer Videos☆34Mar 26, 2021Updated 4 years ago
- ☆15Sep 19, 2023Updated 2 years ago
- ☆13Dec 2, 2024Updated last year
- Repository containing all necessary codes to get started on the SoccerNet Action Spotting challenge. This repository also contains severa…☆94Feb 7, 2024Updated 2 years ago
- Code of "Learning Feature Recovery Transformer for Occluded Person Re-identification" (TIP)☆10Dec 28, 2022Updated 3 years ago
- Efficient Secure Aggregation for Privacy-Preserving Federated Machine Learning☆15Aug 21, 2025Updated 6 months ago
- This is the official implementation of our PrOmpt cLass lEarning (POLE).☆12Jan 21, 2024Updated 2 years ago
- The first range filter to simultaneously offer dynamicity, fast operations, and a robust false positive rate for any workload.☆12Jul 15, 2025Updated 7 months ago
- [CVPR 2025 - Highlight] Official implementation of the paper "Realistic Test-Time Adaptation of Vision-Language Models" (StatA).☆58Oct 31, 2025Updated 4 months ago
- Real-Time Deep-Learning-Based System for Facial Recognition☆13Oct 23, 2018Updated 7 years ago
- ☆14Dec 6, 2023Updated 2 years ago
- Code for the CVPR '23 paper, "Defending Against Patch-based Backdoor Attacks on Self-Supervised Learning"☆10Jun 9, 2023Updated 2 years ago
- SpotEdit [NeurIPS 2025 W]☆17Sep 24, 2025Updated 5 months ago
- ☆65Aug 22, 2024Updated last year
- [CVPRW'24] SoccerNet Game State Reconstruction: End-to-End Athlete Tracking and Identification on a Minimap (CVPR24 - CVSports workshop)☆378May 2, 2025Updated 10 months ago
- SoccerNet@CVPR | 1st place solution for Ball Action Spotting Challenge 2023☆128Jul 2, 2023Updated 2 years ago
- ☆32Feb 4, 2026Updated 3 weeks ago
- Yi-Min Chou, Chien-Hung Chen, Keng-Hao Liu, and Chu-Song Chen, "Changing Background to Foreground: An Augmentation Method Based on Condit…☆12Oct 23, 2018Updated 7 years ago
- PyTorch DataLoader for many VQA datasets☆14Jan 10, 2023Updated 3 years ago
- ☆22May 11, 2025Updated 9 months ago