doc: update README and products

- Update paper link
- Update support hardware
- Update product lists

Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>

diff --git a/Documentation/products.md b/Documentation/products.md
index 8e5daab..e718393 100644 (file)
--- a/Documentation/products.md
+++ b/Documentation/products.md
@@ -1,17 +1,38 @@
----
-title: Products
-...
+# Products with NNStreamer
 
-This is WIP page
+## Mass-produced Devices
 
-# Devices with NNStreamer.
+- Samsung Galaxy Watch 3
+- Samsung TV 2022 models
 
-## Released
+## Devices to be mass-produced Soon
 
-## To be released soon
+- Robotic vacuum cleaners
+- Refrigerators, ovens, ...
 
-## Prototypes
+## Products manufactured in small numbers
 
-# Services with NNStreamer.
+- Activity Recognition Sensors
+- Augmented workers (factories)
+- Robots (to be released soon)
 
-# Application software with NNStreamer
+# Companies known to use NNStreamer
+
+Reports and tips welcomed!
+
+- Fainders.ai: unmanned retail system.
+- KLleon: video processing.
+- NXP Semiconductors: edge-AI developing tool.
+- OpenNCC: edge-AI developing tool.
+- (TBU): AR games.
+
+
+
+# Research
+
+## Research based on NNStreamer
+
+- J. Karjee, et. al., Dynamic Split Computing of PoseNet Inference for Fitness Applications in Home IoT-Edge Platform, COMSNET 2022 [IEEE Explore](https://ieeexplore.ieee.org/abstract/document/9668605)
+- S. Lee, et. al., Implementation of Object Detection System for Real-time Video with NNStreamer, KIISE 2020 [DBPIA](https://www.dbpia.co.kr/pdf/pdfView.do?nodeId=NODE10530073&mark=0&useDate=&ipRange=N&accessgl=Y&language=en_US&hasTopBanner=true) (Korean)
+- J. Moon, et. al., Performance Analysis of Neural Network Pipelining for Multimodal On-Device AI Applications, KIISE 2019 [DBPIA](https://www.dbpia.co.kr/pdf/pdfView.do?nodeId=NODE09301525&mark=0&useDate=&ipRange=N&accessgl=Y&language=en_US&hasTopBanner=true) (Korean)
+- J. Karjee, et. al., Energy Profiling based Load-Balancing Approach in IoT-Edge for Split Computing, INDICON 2021 [IEEE Explorer](https://ieeexplore.ieee.org/abstract/document/9691607)

diff --git a/README.md b/README.md
index d1aad7f..18a233b 100644 (file)
--- a/README.md
+++ b/README.md
@@ -18,7 +18,7 @@ neural network developers to manage neural network pipelines and their filters e
 
 [Architectural Description](https://github.com/nnstreamer/nnstreamer/wiki/Architectural-Description) (WIP)<br /> <br />
 
-[Toward Among-Device AI from On-Device AI with Stream Pipelines](https://conf.researchr.org/home/icse-2022), Submitted. Under Review<br />
+[Toward Among-Device AI from On-Device AI with Stream Pipelines](https://conf.researchr.org/home/icse-2022), IEEE/ACM ICSE 2022 SEIP <br />
 [NNStreamer: Efficient and Agile Development of On-Device AI Systems](https://ieeexplore.ieee.org/document/9402062), IEEE/ACM ICSE 2021 SEIP [[media](https://youtu.be/HtNXFReF2GY)]<br />
 [NNStreamer: Stream Processing Paradigm for Neural Networks ...](https://arxiv.org/abs/1901.04985) [[pdf/tech report](https://arxiv.org/pdf/1901.04985)]<br />
 [GStreamer Conference 2018, NNStreamer](https://gstreamer.freedesktop.org/conference/2018/talks-and-speakers.html#nnstreamer-neural-networks-as-filters) [[media](https://github.com/nnstreamer/nnstreamer/wiki/Gstreamer-Conference-2018-Presentation-Video)] [[pdf/slides](https://github.com/nnstreamer/nnstreamer/wiki/slides/2018_GSTCON_Ham_181026.pdf)]<br />
@@ -123,7 +123,10 @@ Although a framework may accelerate transparently as Tensorflow-GPU does, nnstre
 - ARMNN via armnn subplugin: Released
 - Verisilicon-Vivante via vivante subplugin: Released
 - Qualcomm SNPE via snpe subplugin: Released
-- Exynos NPU: WIP
+- NVidia via TensorRT subplugin: Released
+- TRI-x NPUs: Released
+- NXP i.MX series: [via the vendor](https://www.nxp.com/docs/en/user-guide/IMX-MACHINE-LEARNING-UG.pdf)
+- Others: TVM, TensorFlow, TensorFlow-lite, PyTorch, Caffe2, SNAP, ...
 
 
 [gitter-url]: https://gitter.im/nnstreamer/Lobby