Tracking Anything with Decoupled Video Segmentation paper page: huggingface.co/papers/2309.03… Training data for video segmentation are expensive to annotate. This impedes extensions of end-to-end algorithms to new video segmentation tasks, especially in large-vocabulary settings. To

In the 59th session of #MultimodalWeekly, we have three exciting presentations on video segmentation and video processing.

MMAudio just made Sora videos highly engaging and more watchable by adding relevant audio to them😎 Gradio app is up on Hugging Face Spaces: huggingface.co/spaces/hkcheng… Huge kudos to Rex Cheng and MMAudio team 🙌

babe wake up! video 2 audio just dropped on Replicate

I love old trains & Google's Veo2 is incredible! Adding audio to the clips with this open-source generative Video-to-Audio model is complete magic! 🪄 🧵👇🔊

【MMAudioがMacで利用可能に！】 ✎. FYIG: なんと、今年最高のAIモデルの一つ、MMAudioがMacで動くようになったそうです！ ビデオクリップを渡すと、そのビデオにマッチした音楽やサウンドを自動生成できるんですって…まさに魔法のようですね！

🌳Just tested MMAudio with a summer forest video! The environmental sound reproduction exceeded my expectations ✨ The rustling leaves and birdsong create an amazing atmosphere. I'm truly impressed with how well it turned out! (1/4)

Here is my entry for the #ProjectOdyssey Turn the sound on please Tools used: Midjourney Hailuo AI (MiniMax) Kling AI @Viduforhuman udio and special thanks to Rex Cheng for MMAudio.

This example from their paper (pub.sakana.ai/static/paper.p…), which is claimed to have 150x speedup, is actually 3x slower if you bench it...

Really cool to see Corridor using MMAudio to make such an entertaining and informative video! They did a great job breaking down how MMAudio works and how it was trained. youtu.be/SLz3NWLyHxg Love to see our work existing outside of arXiv. Sony AI @IllinoisCDS

🎉Excited to announce the 1st Workshop on Generative AI for Audio-Visual Content Creation (Gen4AVC) at #ICCV2025! Topics: Vision-to-audio, audio-to-vision, joint audio-visual generation & more. Let’s shape the future of immersive content!🚀 gen4avc.github.io

Excited to announce our Gen4AVC workshop #ICCV2025 ! Join us at #ICCV2025 for talks from amazing speakers & to share your work on audio-visual generation! We call for 4-page extended abstracts. 🗓️Deadline: July 1st, 2025 (23:59, AoE) 🌐More info: gen4avc.github.io