heldJan / X-VARS
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.
☆13Updated 4 months ago
Related projects ⓘ
Alternatives and complementary repositories for X-VARS
- ☆32Updated 3 weeks ago
- Code for Spotting Temporally Precise, Fine-Grained Events in Video☆51Updated last year
- [CVPR2024] The official implementation of AdaTAD: End-to-End Temporal Action Detection with 1B Parameters Across 1000 Frames☆32Updated 4 months ago
- Official Implementation of SnAG (CVPR 2024)☆35Updated last week
- Repository containing all necessary codes to get started on the SoccerNet Action Spotting challenge. This repository also contains severa…☆63Updated 9 months ago
- Repository containing all necessary codes to get started on the SoccerNet Re-Identification challenge. This repository also contains benc…☆51Updated last year
- Official implementation of "Test-Time Zero-Shot Temporal Action Localization", CVPR 2024☆42Updated last month
- SoccerNet@CVPR | 1st place solution for Camera Calibration Challenge 2023☆31Updated 3 weeks ago
- Repository containing all necessary codes to get started on the SoccerNet Dense Video Captioning challenge.☆28Updated 6 months ago
- [CVPR2023] Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representation Learning (https://arxiv…☆107Updated last year
- ☆11Updated 8 months ago
- ☆22Updated last week
- ☆35Updated 2 months ago
- Code for Diffusion Action Segmentation (ICCV 2023)☆52Updated last year
- A General Framework for Jersey Number Recognition in Sports Video☆23Updated last month
- Code for referee classifier and unsupervised player classification using embedding network.☆15Updated 6 months ago
- Official implementation of paper - No Bells, Just Whistles: Sports Field Registration by Leveraging Geometric Properties☆29Updated 2 weeks ago
- ☆18Updated 5 months ago
- TemporalMaxer: Maximize Temporal Context with only Max Pooling for Temporal Action Localization☆53Updated last year
- TeamTrack: An Algorithm and Benchmark Dataset for Multi-Sport Multi-Object Tracking in Full-pitch Videos☆44Updated 6 months ago
- ☆30Updated last month
- BEAR: a new BEnchmark on video Action Recognition☆42Updated 6 months ago
- ☆13Updated 4 months ago
- A modular end-to-end tracking framework for research and development☆94Updated last month
- ☆35Updated 7 months ago
- The official code for Relational Context Learning for Human-Object Interaction Detection, CVPR2023.☆48Updated last year
- This is an official implementation of TubeR: Tubelet Transformer for Video Action Detection☆70Updated last year
- [CVPR 2022] An Empirical Study of End-to-end Temporal Action Detection☆81Updated last year
- Awesome Online Action Detection☆48Updated this week
- Official Implementation of "The Surprising Effectiveness of Multimodal Large Language Models for Video Moment Retrieval"☆45Updated last week