Related papers: Image Coding for Machines with Omnipotent Feature …
Video compression is a fundamental topic in the visual intelligence, bridging visual signal sensing/capturing and high-level visual analytics. The broad success of artificial intelligence (AI) technology has enriched the horizon of video…
Learning-based lossy image compression usually involves the joint optimization of rate-distortion performance. Most existing methods adopt spatially invariant bit length allocation and incorporate discrete entropy approximation to constrain…
Learning-based image compression was shown to achieve a competitive performance with state-of-the-art transform-based codecs. This motivated the development of new learning-based visual compression standards such as JPEG-AI. Of particular…
Deep learning based image compressed sensing (CS) has achieved great success. However, existing CS systems mainly adopt a fixed measurement matrix to images, ignoring the fact the optimal measurement numbers and bases are different for…
At the core of self-supervised learning for vision is the idea of learning invariant or equivariant representations with respect to a set of data transformations. This approach, however, introduces strong inductive biases, which can render…
Recent work has shown that learned image compression strategies can outperform standard hand-crafted compression algorithms that have been developed over decades of intensive research on the rate-distortion trade-off. With growing…
Compressing integer keys is a fundamental operation among multiple communities, such as database management (DB), information retrieval (IR), and high-performance computing (HPC). Recent advances in \emph{learned indexes} have inspired the…
As a fundamental visual attribute, image complexity significantly influences both human perception and the performance of computer vision models. However, accurately assessing and quantifying image complexity remains a challenging task. (1)…
Masking strategies commonly employed in natural language processing are still underexplored in vision tasks such as concept learning, where conventional methods typically rely on full images. However, using masked images diversifies…
Traditional image/video compression aims to reduce the transmission/storage cost with signal fidelity as high as possible. However, with the increasing demand for machine analysis and semantic monitoring in recent years, semantic fidelity…
Feature coding has been recently considered to facilitate intelligent video analysis for urban computing. Instead of raw videos, extracted features in the front-end are encoded and transmitted to the back-end for further processing. In this…
We introduce a cutting-edge video compression framework tailored for the age of ubiquitous video data, uniquely designed to serve machine learning applications. Unlike traditional compression methods that prioritize human visual perception,…
Masked image modeling (MIM) has become a leading self-supervised learning strategy. MIMs such as Masked Autoencoder (MAE) learn strong representations by randomly masking input tokens for the encoder to process, with the decoder…
An increasing share of image and video content is analyzed by machines rather than viewed by humans, and therefore it becomes relevant to optimize codecs for such applications where the analysis is performed remotely. Unfortunately,…
Compressive learning (CL) is an emerging framework that integrates signal acquisition via compressed sensing (CS) and machine learning for inference tasks directly on a small number of measurements. It can be a promising alternative to…
We present a compact encoder for image categorization that emphasizes computation economy through content-conditioned multi-pass processing. The model employs a single lightweight core block that can be re-applied a small number of times,…
Massive human-related data is collected to train neural networks for computer vision tasks. A major conflict is exposed relating to software engineers between better developing AI systems and distancing from the sensitive training data. To…
This paper describes a novel approach to unsupervised learning that has been developed within a framework of "information compression by multiple alignment, unification and search" (ICMAUS), designed to integrate learning with other AI…
Neural audio codecs, leveraging quantization algorithms, have significantly impacted various speech/audio tasks. While high-fidelity reconstruction is paramount for human perception, audio coding for machines (ACoM) prioritizes efficient…
Image classification is a core task of intelligent sensing, conventionally follows a sequential imaging then processing pipeline. However, redundant high-dimensional image reconstruction is inherently inefficient, especially in photon…