UNINEXT
ailia-models
UNINEXT | ailia-models | |
---|---|---|
2 | 4 | |
1,443 | 1,825 | |
- | 2.4% | |
5.5 | 9.8 | |
10 months ago | 4 days ago | |
Python | Python | |
MIT License | - |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
UNINEXT
-
[R] Universal Instance Perception as Object Discovery and Retrieval (Video Demo)
Hi, we have uploaded the complete paper (https://github.com/MasterBin-IIAU/UNINEXT/blob/master/assets/UNINEXT_Paper.pdf) to our repo. You can find more details in the paper :) About the first question, the input videos are NOT segmented aforehand and all target masks are predicted by our UNINEXT model. For SOT and VOS, we use target annotations (box or mask) from the first frame as the prompts. This helps UNINEXT to segment corresponding targets in the following frames.
ailia-models
-
10$ Full Body Tracking! I'm proud to release ToucanTrack (in Beta!). Get decent FBT with the power of 2 PS3 Eye Cameras and AI!
If you're looking for the differences in terms of how inference is done, I recommend you take a look at MediaPipe's source code. MediaPipe doesn't use raw code, but uses a "graph" instead (eg. pose_landmark_cpu.pbtxt), which can be visualised using MediaPipe Viz. I also used axinc-ai/ailia-models as the base (preprocessing, inference, postprocessing, etc...) which I further built upon (keypoint refinement, roi from keypoints, filtering / smoothing, etc...)
- [P] A collection of pre-trained, state-of-the-art AI models
- Ailia-models: A collection of pre-trained, state-of-the-art AI models
What are some alternatives?
VolleyVision - Applying Deep Learning Approaches to Volleyball Data
DeepCamera - Open-Source AI Camera. Empower any camera/CCTV with state-of-the-art AI, including facial recognition, person recognition(RE-ID) car detection, fall detection and more
py-motmetrics - :bar_chart: Benchmark multiple object trackers (MOT) in Python
tensorflow-onnx - Convert TensorFlow, Keras, Tensorflow.js and Tflite models to ONNX
norfair - Lightweight Python library for adding real-time multi-object tracking to any detector.
Put-In-Context - Putting Visual Object Recognition in Context
TagMaps - Spatio-Temporal Tag and Photo Location Clustering for generating Tag Maps
robotics-level-4 - This repo contains projects created using TensorFlow-Lite on Raspberry Pi and Teachable Machine. AI and ML capabilities have been integrated with Robot's software.
unimatch - [TPAMI'23] Unifying Flow, Stereo and Depth Estimation
mlapi - An easy to use/extend object recognition API you can locally install. Python+Flask. Also works with ZMES!
VNext - Next-generation Video instance recognition framework on top of Detectron2 which supports InstMove (CVPR 2023), SeqFormer(ECCV Oral), and IDOL(ECCV Oral))
PeekingDuck - A modular framework built to simplify Computer Vision inference workloads.