Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
[ICCV 2023] Tracking Anything with Decoupled Video Segmentation
| Date | Stars |
|---|---|
| 2026-07-24 | 1506 |
| 2026-07-25 | 1506 |
| 2026-07-28 | 1506 |
| 2026-07-30 | 1506 |
| 2026-08-06 | 1506 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# DEVA: Tracking Anything with Decoupled Video Segmentation  [Ho Kei Cheng](https://hkchengrex.github.io/), [Seoung Wug Oh](https://sites.google.com/view/seoungwugoh/), [Brian Price](https://www.brianpricephd.com/), [Alexander Schwing](https://www.alexander-schwing.de/), [Joon-Young Lee](https://joonyoung-cv.github.io/) University of Illinois Urbana-Champaign and Adobe ICCV 2023 [[arXiV]](https://arxiv.org/abs/2309.03903) [[PDF]](https://arxiv.org/pdf/2309.03903.pdf) [[Project Page]](https://hkchengrex.github.io/Tracking-Anything-with-DEVA/) [](https://colab.research.google.com/drive/1OsyNVoV_7ETD1zIE8UWxL3NXxu12m_YZ?usp=sharing) ## Highlights 1. Provide long-term, open-vocabulary video segmentation with text-prompts out-of-the-box. 2. Fairly easy to **integrate your own image model**! Wouldn't you or your reviewers be interested in seeing examples where your image model also works well on videos :smirk:? No finetuning is needed! ***Note (Mar 6 2024):*** We have fixed a major bug (introduced in the last update) that prevented the deletion of unmatched segments in text/eval_with_detections modes. This should greatly reduce the amount of accumulated noisy detection/false positives, especially for long videos. See [#64](https://github.com/hkchengrex/Tracking-Anything-with-DEVA/issues/64). ***Note (Sep 12 2023):*** We have improved automatic video segmentation by not querying the points in segmented regions. We correspondingly increased the number of query points per side to 64 and deprecated the "engulf" mode. The old code can be found in the "legacy_engulf" branch. The new code should run a lot faster and capture smaller objects. The text-prompted mode is still recommended for better results. ***Note (Sep 11 2023):*** We have removed the "pluralize" option as it works weirdly sometimes with GroundingDINO. If needed, please pluralize the prompt yourself. ## Abstract We develop a decoupled video segmentation approach (**DEVA**), composed of task-specific image-level segmentation and class/task-agnostic bi-directional temporal propagation. Due to this design, we only need an image-level model for the target task and a universal temporal propagation model which is trained once and generalizes across tasks. To effectively combine these two modules, we propose a (semi-)online fusion of segmentation hypotheses from different frames to generate a coherent segmentation. We show that this decoupled formulation compares favorably to end-to-end approaches in several tasks, most notably in large-vocabulary video panoptic segmentation and open-world video segmentation. ## Demo Videos ### Demo with Grounded Segment Anything (text prompt: "guinea pigs" and "chicken"): https://github.com/hkchengrex/Tracking-Anything-with-DEVA/assets/7107196/457a9a6a-86c3-4c5a-a3cc-25199427cd11 Source: https://www.youtube.com/watch?v=FM9SemMfknA ### Demo with Grounded Segment Anything (text prompt: "pigs"): https://github.com/hkchengrex/Tracking-Anything-with-DEVA/assets/7107196/9a6dbcd1-2c84-45c8-ac0a-4ad31169881f Source: https://youtu.be/FbK3SL97zf8 ### Demo with Grounded Segment Anything (text prompt: "capybara"): https://github.com/hkchengrex/Tracking-Anything-with-DEVA/assets/7107196/2ac5acc2-d160-49be-a013-68ad1d4074c5 Source: https://youtu.be/couz1CrlTdQ ### Demo with Segment Anything (automatic points-in-grid prompting); original video follows DEVA result overlaying the video: https://github.com/hkchengrex/Tracking-Anything-with-DEVA/assets/7107196/ac6ab425-2f49-4438-bcd4-16e4ccfb0d98 Source: DAVIS 2017 validation set "soapbox" ### Demo with Segment Anything on a out-of-domain example; original video follows DEVA result overlaying the video: https://github.com/hkchengrex/Tracking-Anything-with-DEVA/assets/7107196/48542bcd-113c-4454-b512-030df26def08 Source: https://youtu.be/FQQaSyH9hZI ## Installation Tested on
Excerpt of 8,662 characters
Read on GitHub
Rex Cheng · Israel
86
Guspan Tanadi
4
Lei Ke · CMU · United States
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:44c60e89644c32f3, topic:deep-learning
matched fp:44c60e89644c32f3, topic:object-tracking
matched fp:44c60e89644c32f3, topic:video-editing