| 1. | | Veo 2: Our video generation model (deepmind.google) |
|
353 points by mvoodarla 11 hours ago | past | 172 comments
|
|
| 2. | | Guide to pure-audio and audiovisual speaker recognition techniques (sievedata.com) |
|
1 point by mvoodarla 41 days ago | past
|
|
| 3. | | SieveSync: Realistic, zero-shot lipsync pipeline using MuseTalk and LivePortrait (github.com/sieve-community) |
|
1 point by mvoodarla 82 days ago | past
|
|
| 4. | | SieveSync: High-quality, zero-shot lipsync built with MuseTalk and LivePortrait (sievedata.com) |
|
4 points by mvoodarla 3 months ago | past
|
|
| 5. | | Running Meta's SAM2 2x faster (sievedata.com) |
|
3 points by mvoodarla 3 months ago | past
|
|
| 6. | | API to automate social video editing with AI (twitter.com/sievedata) |
|
1 point by mvoodarla 7 months ago | past
|
|
| 7. | | Finding highlights in long-form video automatically with custom search terms (sievedata.com) |
|
1 point by mvoodarla 8 months ago | past
|
|
| 8. | | Describe Beta: The most descriptive audiovisual summaries for videos (github.com/sieve-community) |
|
2 points by mvoodarla 9 months ago | past | 1 comment
|
|
| 9. | | AI-generated sound effects for stock videos using CogVLM and AudioLDM (sievedata.com) |
|
1 point by mvoodarla 9 months ago | past
|
|
| 10. | | AI active speaker detection on video with a 90% speedup (sievedata.com) |
|
3 points by mvoodarla 9 months ago | past
|
|
| 11. | | Masked Audio Generation Using a Single Non-Autoregressive Transformer (huji.ac.il) |
|
1 point by mvoodarla 10 months ago | past
|
|
| 12. | | Masked Audio Generation Using a Single Non-Autoregressive Transformer (arxiv.org) |
|
1 point by mvoodarla 11 months ago | past
|
|
| 13. | | The most cost-effective audio transcription API (sievedata.com) |
|
3 points by mvoodarla on Dec 12, 2023 | past
|
|
| 14. | | Audiobox Demo: Where anyone can make a sound with an idea (metademolab.com) |
|
3 points by mvoodarla on Dec 11, 2023 | past
|
|
| 15. | | Audiobox: Generating audio from voice and natural language prompts (meta.com) |
|
3 points by mvoodarla on Dec 7, 2023 | past | 1 comment
|
|
| 16. | | Improving on open-source for fast, high-quality AI lipsyncing (sievedata.com) |
|
2 points by mvoodarla on Nov 22, 2023 | past
|
|
| 17. | | Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning (twitter.com/aiatmeta) |
|
3 points by mvoodarla on Nov 16, 2023 | past
|
|
| 18. | | Show HN: State of the art audio enhance (open source AudioSR and DeepFilterNet) (sievedata.com) |
|
8 points by mvoodarla on Oct 19, 2023 | past | 1 comment
|
|
| 19. | | DA-Clip: Controlling Vision-Language Models for Universal Image Restoration (twitter.com/fffiloni) |
|
1 point by mvoodarla on Oct 16, 2023 | past
|
|
| 20. | | Voicebox: The first generative AI model for speech to generalize across tasks (facebook.com) |
|
7 points by mvoodarla on June 16, 2023 | past | 2 comments
|
|
| 21. | | DINOv2: State-of-the-art computer vision models with self-supervised learning (metademolab.com) |
|
176 points by mvoodarla on April 17, 2023 | past | 16 comments
|
|
| 22. | | Show HN: TrackObject – Drag-and-drop computer vision object tracking (trackobject.xyz) |
|
23 points by mvoodarla on July 19, 2022 | past | 3 comments
|
|
| 23. | | Pix2Seq: A New Language Interface for Object Detection (googleblog.com) |
|
1 point by mvoodarla on April 25, 2022 | past
|
|
| 24. | | Ask HN: Building vision systems without knowing ML? |
|
1 point by mvoodarla on Feb 22, 2022 | past
|
|
| 25. | | Launch HN: Sieve (YC W22) – Pluggable APIs for Video Search (sievedata.com) |
|
71 points by mvoodarla on Feb 2, 2022 | past | 14 comments
|
|
| 26. | | Show HN: Processing 24 hours of video in ten minutes (sievedata.com) |
|
77 points by mvoodarla on Jan 11, 2022 | past | 37 comments
|
|
| 27. | | Turning petabytes of raw video data into a high-quality ML dataset (medium.com/mvoodarla) |
|
3 points by mvoodarla on Dec 30, 2021 | past | 2 comments
|
|
