Existing deep learning-enabled semantic communication systems often rely on shared
background knowledge between the transmitter and receiver that includes empirical data …

At present, and increasingly so in the future, much of the captured visual content will not be
seen by humans. Instead, it will be used for automated machine vision analytics and may …

Abstract We present Reversible Vision Transformers, a memory efficient architecture design
for visual recognition. By decoupling the GPU memory footprint from the depth of the model …

With the proliferation of sensor devices, the extensive utilization of three-dimensional data in
multimedia continues to grow. Point clouds are widely adopted within this domain because …

Temporal action localization (TAL) requires long-form reasoning to predict actions of various
durations and complex content. Given limited GPU memory, training TAL end to end (ie, from …

Point cloud data is pivotal in applications like autonomous driving, virtual reality, and
robotics. However, its substantial volume poses significant challenges in storage and …

Most video compression methods aim to improve the decoded video visual quality, instead
of particularly guaranteeing the semantic-completeness, which deteriorates downstream …

A new source model, which consists of an intrinsic state part and an extrinsic observation
part, is proposed and its information-theoretic characterization, namely its rate-distortion …

Semantic communications have emerged as a new paradigm for improving communication
efficiency by transmitting the semantic information of a source message that is most relevant …

We address the requirement of image coding for joint human-machine vision, ie, the
decoded image serves both human observation and machine analysis/understanding …