相关论文: Lumi\`ereNet: Lecture Video Synthesis from Audio

LLM unlearning is a technique to remove the impacts of undesirable knowledge from the model without retraining from scratch, which is indispensable towards trustworthy AI. Existing unlearning methods face significant limitations:…

Latent diffusion models (LDMs) enable high-fidelity synthesis by operating in learned latent spaces. However, training state-of-the-art LDMs requires complex staging: a tokenizer must be trained first, before the diffusion model can be…

This work presents a large-scale audio-visual speech recognition system based on a recurrent neural network transducer (RNN-T) architecture. To support the development of such a system, we built a large audio-visual (A/V) dataset of…

Long-context modelling for large language models (LLMs) has been a key area of recent research because many real world use cases require reasoning over longer inputs such as documents. The focus of research into modelling long context has…

Recently developed deep learning models are able to learn to segment scenes into component objects without supervision. This opens many new and exciting avenues of research, allowing agents to take objects (or entities) as inputs, rather…

In this paper, we develop a personalized video relighting algorithm that produces high-quality and temporally consistent relit videos under any pose, expression, and lighting condition in real-time. Existing relighting algorithms typically…

Large Language Models (LLMs) have achieved remarkable results. However, existing models are expensive to train and deploy, and it is also difficult to expand their knowledge beyond pre-training data without forgetting previous knowledge.…

Recent years have witnessed great progress in creating vivid audio-driven portraits from monocular videos. However, how to seamlessly adapt the created video avatars to other scenarios with different backgrounds and lighting conditions…

We present Unified Latents (UL), a framework for learning latent representations that are jointly regularized by a diffusion prior and decoded by a diffusion model. By linking the encoder's output noise to the prior's minimum noise level,…

Image denoising aims to restore a clean image from an observed noisy image. The model-based image denoising approaches can achieve good generalization ability over different noise levels and are with high interpretability. Learning-based…

Ensembling is a universally useful approach to boost the performance of machine learning models. However, individual models in an ensemble were traditionally trained independently in separate stages without information access about the…

Scene-text image synthesis techniques that aim to naturally compose text instances on background scene images are very appealing for training deep neural networks due to their ability to provide accurate and comprehensive annotation…

Lecture slide presentations, a sequence of pages that contain text and figures accompanied by speech, are constructed and presented carefully in order to optimally transfer knowledge to students. Previous studies in multimedia and…

In recent years, deep learning (DL) approaches have demonstrated promising results in decoding hemodynamic responses captured by functional near-infrared spectroscopy (fNIRS), particularly in the context of brain-computer interface (BCI)…

Vision-Language Models (VLMs) can process visual and textual information in multiple formats: texts, images, interleaved texts and images, or even hour-long videos. In this work, we conduct fine-grained quantitative and qualitative analyses…

Unlike prevalent facial expressions, micro expressions have subtle, involuntary muscle movements which are short-lived in nature. These minute muscle movements reflect true emotions of a person. Due to the short duration and low intensity,…

This paper presents an innovative deep learning pipeline which estimates the relative pose of a spacecraft by incorporating the temporal information from a rendezvous sequence. It leverages the performance of long short-term memory (LSTM)…

Speechreading is a notoriously difficult task for humans to perform. In this paper we present an end-to-end model based on a convolutional neural network (CNN) for generating an intelligible acoustic speech signal from silent video frames…

Transformer-based video diffusion models rely on 3D attention over spatial and temporal tokens, which incurs quadratic time and memory complexity and makes end-to-end training for ultra-high-resolution videos prohibitively expensive. To…

Multimodal foundation models can process several modalities. However, since the space of possible modalities is large and evolving over time, training a model from scratch to encompass all modalities is unfeasible. Moreover, integrating a…