相关论文: Multi-Objective Design Space Exploration for the O…
High-resolution segmentation is critical for precise disease diagnosis by extracting fine-grained morphological details. Existing hierarchical encoder-decoder frameworks have demonstrated remarkable adaptability across diverse medical…
This paper presents a novel adaptive-sparse polynomial dimensional decomposition (PDD) method for stochastic design optimization of complex systems. The method entails an adaptive-sparse PDD approximation of a high-dimensional stochastic…
In recent years, the proliferation of multimedia applications and formats, such as IPTV, Virtual Reality (VR, 360-degree), and point cloud videos, has presented new challenges to the video compression research community. Simultaneously,…
Ensemble learning has gain attention in resent deep learning research as a way to further boost the accuracy and generalizability of deep neural network (DNN) models. Recent ensemble training method explores different training algorithms or…
This paper presents a general-purpose video super-resolution (VSR) method, dubbed VSR-HE, specifically designed to enhance the perceptual quality of compressed content. Targeting scenarios characterized by heavy compression, the method…
The rapid development of intelligent tasks, e.g., segmentation, detection, classification, etc, has brought an urgent need for semantic compression, which aims to reduce the compression cost while maintaining the original semantic…
Current Transformer-based methods for small object detection continue emerging, yet they have still exhibited significant shortcomings. This paper introduces HeatMap Position Embedding (HMPE), a novel Transformer Optimization technique that…
In this paper we show that a small amount of bit stream features can be used to accurately estimate the energy consumption of state-of-the-art software and hardware accelerated decoder implementations for four different video codecs. By…
We introduce a practical real-time neural video codec (NVC) designed to deliver high compression ratio, low latency and broad versatility. In practice, the coding speed of NVCs depends on 1) computational costs, and 2) non-computational…
To avoid delays arising from a need to decrypt a video prior to transcoding and then re-encrypt it afterwards, this paper assesses a selective encryption (SE) content protection scheme. The scheme is suited to both recent standardized…
The cache and transcoding of the multi-access edge computing (MEC) server and wireless resource allocation in eNodeB interact and determine the quality of experience (QoE) of dynamic adaptive streaming over HTTP (DASH) clients in MEC…
We propose an optimal MMSE precoding technique using quantized signals with constant envelope. Unlike the existing MMSE design that relies on 1-bit resolution, the proposed approach employs uniform phase quantization and the bounding step…
In this paper, we propose a data-model-hardware tri-design framework for high-throughput, low-cost, and high-accuracy multi-object tracking (MOT) on High-Definition (HD) video stream. First, to enable ultra-light video intelligence, we…
Context-aware compression techniques have gained increasing attention as model sizes continue to grow, introducing computational bottlenecks that hinder efficient deployment. A structured encoding approach was proposed to selectively…
Prevalent predictive coding-based video compression methods rely on a heavy encoder to reduce temporal redundancy, which makes it challenging to deploy them on resource-constrained devices. Since the 1970s, distributed source coding theory…
High efficiency video coding (HEVC) has brought outperforming efficiency for video compression. To reduce the compression artifacts of HEVC, we propose a DenseNet based approach as the in-loop filter of HEVC, which leverages multiple…
It has recently been demonstrated that spatial resolution adaptation can be integrated within video compression to improve overall coding performance by spatially down-sampling before encoding and super-resolving at the decoder. Significant…
Accurately estimating the pose of an object is a crucial task in computer vision and robotics. There are two main deep learning approaches for this: geometric representation regression and iterative refinement. However, these methods have…
The Bj{\o}ntegaard Delta rate (BD-rate) objectively assesses the coding efficiency of video codecs using the rate-distortion (R-D) performance but overlooks encoding energy, which is crucial in practical applications, especially for those…
The objective of this paper is self-supervised learning of spatio-temporal embeddings from video, suitable for human action recognition. We make three contributions: First, we introduce the Dense Predictive Coding (DPC) framework for…