相关论文: Low Bandwidth Video-Chat Compression using Deep Ge…

Adversarial attacks involve adding, small, often imperceptible, perturbations to inputs with the goal of getting a machine learning model to misclassifying them. While many different adversarial attack strategies have been proposed on image…

This paper addresses 2 challenging tasks: improving the quality of low resolution facial images and accurately locating the facial landmarks on such poor resolution images. To this end, we make the following 5 contributions: (a) we propose…

Recent advances in deep generative models led to the development of neural face video compression codecs that use an order of magnitude less bandwidth than engineered codecs. These neural codecs reconstruct the current frame by warping a…

Traditional low bit-rate speech coding approach only handles narrowband speech at 8kHz, which limits further improvements in speech quality. Motivated by recent successful exploration of deep learning methods for image and speech…

A lot of work has been done towards reconstructing the 3D facial structure from single images by capitalizing on the power of Deep Convolutional Neural Networks (DCNNs). In the recent works, the texture features either correspond to…

This paper presents a novel approach for generating 3D talking heads from raw audio inputs. Our method grounds on the idea that speech related movements can be comprehensively and efficiently described by the motion of a few control points…

People with visual impairments have difficulty accessing touchscreen-enabled personal computing devices like mobile phones and laptops. The image-to-speech (ITS) systems can assist them in mitigating this problem, but their huge model size…

The computation and memory costs of large language models kept increasing over last decade, which reached over the scale of 1T parameters. To address the challenges from the large scale models, model compression techniques such as low-rank…

Recent progress of deep image classification models has provided great potential to improve state-of-the-art performance in related computer vision tasks. However, the transition to semantic segmentation is hampered by strict memory…

The introduction of multiple viewpoints in video scenes inevitably increases the bitrates required for storage and transmission. To reduce bitrates, researchers have developed methods to skip intermediate viewpoints during compression and…

The proliferation of edge devices has unlocked unprecedented opportunities for deep learning model deployment in computer vision applications. However, these complex models require considerable power, memory and compute resources that are…

While promising performance for speaker verification has been achieved by deep speaker embeddings, the advantage would reduce in the case of speaking-style variability. Speaking rate mismatch is often observed in practical speaker…

In Collaborative Intelligence, a deep neural network (DNN) is partitioned and deployed at the edge and the cloud for bandwidth saving and system optimization. When a model input is an image, it has been confirmed that the intermediate…

Video represents the majority of internet traffic today, driving a continual race between the generation of higher quality content, transmission of larger file sizes, and the development of network infrastructure. In addition, the recent…

The rise of deep generative models has greatly advanced video compression, reshaping the paradigm of face video coding through their powerful capability for semantic-aware representation and lifelike synthesis. Generative Face Video Coding…

Audio-driven talking face generation aims to synthesize video with lip movements synchronized to input audio. However, current generative techniques face challenges in preserving intricate regional textures (skin, teeth). To address the…

Despite significant advancements in traditional syntactic communications based on Shannon's theory, these methods struggle to meet the requirements of 6G immersive communications, especially under challenging transmission conditions. With…

Generative adversarial networks (GANs) have an enormous potential impact on digital content creation, e.g., photo-realistic digital avatars, semantic content editing, and quality enhancement of speech and images. However, the performance of…

Deep convolutional neural networks contain tens of millions of parameters, making them impossible to work efficiently on embedded devices. We propose iterative approach of applying low-rank approximation to compress deep convolutional…

Accurate face landmark localization is an essential part of face recognition, reconstruction and morphing. To accurately localize face landmarks, we present our heatmap regression approach. Each model consists of a MobileNetV2 backbone…