📹 Welcome to Sounding Video Generation Challenge 2024

The Sounding Video Generation (SVG) Challenge 2024 is a competition to create AI models that make videos where the visuals match perfectly with sounds, like a dog barking in sync with the video. Participants will work to improve how well sounds and scenes align, with prizes for the best results.

ADVANCING AUDIO-VISUAL SYNCHRONISATION

Join the Sounding Video Generation (SVG) Challenge 2024, a groundbreaking competition at the intersection of video generation and audio-visual synchronisation. This innovative challenge invites participants to build state-of-the-art AI models that generate perfectly aligned and contextually accurate videos guided by audio.

Use your machine learning expertise to advance the frontier of audio-visual synchronisation, transforming datasets into dynamic, synchronised videos. With the right code and creativity, you’ll contribute to a rapidly evolving field that’s set to redefine how we generate and experience multi-modal content.

dataset-preview

:bookmark_tabs: The Task
Develop models that generate videos with synchronised and contextually relevant audio in two specialised tracks:

  • Temporal Alignment Track: Create videos where the audio is perfectly synchronised with the video content in time (e.g., a dog barking exactly when seen in the video). Find the starter kit here.
  • Spatial Alignment Track: Develop models that produce videos with spatially aligned audio, creating a real sense of direction and space. Find the starter kit here.

Both tracks aim to push the boundaries of multi-modal AI, offering a unique platform to benchmark cutting-edge solutions in this underexplored domain.

:computer:Check out the starter-kits for Temporal Alignment Track and Spatial Alignment Track.
:file_cabinet: Download the resources for the challenge Temporal Alignment Track and Spatial Alignment Track.

:date: Timeline

  • Warmup Round: 29th Oct 2024
  • Phase I: 2nd Dec 2024
  • Phase II: 3rd Jan 2025
  • Challenge End: 25th Mar 2025

:moneybag: Prizes
The challenge boasts a prize pool of USD 35,000 split across both tracks. The top three teams or participants in each track will be rewarded as follows:

  • Track 1: Temporal Alignment ($17,500)
    • :1st_place_medal: First place: USD 10,000
    • :2nd_place_medal: Second place: USD 5,000
    • :3rd_place_medal: Third place: USD 2,500
  • Track 2: Spatial Alignment ($17,500)
    • :1st_place_medal: First place: USD 10,000
    • :2nd_place_medal: Second place: USD 5,000
    • :3rd_place_medal: Third place: USD 2,500

Join a Thriving Community
Collaborate with like-minded researchers, practitioners, and AI enthusiasts eager to share ideas, team up, and drive innovation in this captivating challenge.

Sign up now for the SVG Challenge 2024 and start building your models in the warm-up round!