Scalable Image Coding for Humans and Machines Using Feature Fusion Network

no code implementations • 15 May 2024 • Takahiro Shindo, Taiju Watanabe, Yui Tatsumi, Hiroshi Watanabe

Our method's additional information compression model is adjusted to reduce the number of parameters by enabling combinations of features of different sizes in the feature fusion network.

Image Compression

Image Coding for Machines with Edge Information Learning Using Segment Anything

no code implementations • 7 Mar 2024 • Takahiro Shindo, Kein Yamada, Taiju Watanabe, Hiroshi Watanabe

We also show that SA-NeRV is superior to ordinary NeRV in video compression for machines.

Image Compression Video Compression

Image Coding for Machines with Object Region Learning

no code implementations • 27 Aug 2023 • Takahiro Shindo, Taiju Watanabe, Kein Yamada, Hiroshi Watanabe

The former approach has the problem of requiring an ROI-map as input in addition to the input image.

Image Compression Object

VVC Extension Scheme for Object Detection Using Contrast Reduction

no code implementations • 30 May 2023 • Takahiro Shindo, Taiju Watanabe, Kein Yamada, Hiroshi Watanabe

In 2019, the Moving Picture Experts Group (MPEG) has started standardization of Video Coding for Machines (VCM) as a video coding technology for image recognition.

Decoder Object +3

Accuracy Improvement of Object Detection in VVC Coded Video Using YOLO-v7 Features

no code implementations • 3 Apr 2023 • Takahiro Shindo, Taiju Watanabe, Kein Yamada, Hiroshi Watanabe

Versatile Video Coding (VVC) will be used for the video compression method, since it is the latest video coding method with the best encoding performance.

Object object-detection +2