Related papers: Towards Continual Expansion of Data Coverage: Auto…
We present a lighting-aware image editing pipeline that, given a portrait image and a text prompt, performs single image relighting. Our model modifies the lighting and color of both the foreground and background to align with the provided…
High-quality Text-to-Speech (TTS) model training requires extensive and diverse text and speech data. It is challenging to procure such data from real sources due to issues of domain specificity, licensing, and scalability. Large language…
Personalized text-to-image generation has attracted unprecedented attention in the recent few years due to its unique capability of generating highly-personalized images via using the input concept dataset and novel textual prompt. However,…
Natural language instructions are a powerful interface for editing the outputs of text-to-image diffusion models. However, several challenges need to be addressed: 1) underspecification (the need to model the implicit meaning of…
Class-agnostic 3D instance segmentation tackles the challenging task of segmenting all object instances, including previously unseen ones, without semantic class reliance. Current methods struggle with generalization due to the scarce…
This paper presents a new synthesis-based approach for batch image processing. Unlike existing tools that can only apply global edits to the entire image, our method can apply fine-grained edits to individual objects within the image. For…
High-quality data is essential for conversational recommendation systems and serves as the cornerstone of the network architecture development and training strategy design. Existing works contribute heavy human efforts to manually labeling…
How to leverage dynamic contextual information in end-to-end speech recognition has remained an active research area. Previous solutions to this problem were either designed for specialized use cases that did not generalize well to…
Attribute guided face image synthesis aims to manipulate attributes on a face image. Most existing methods for image-to-image translation can either perform a fixed translation between any two image domains using a single attribute or…
Personalizing text-to-image diffusion models is crucial for adapting the pre-trained models to specific target concepts, enabling diverse image generation. However, fine-tuning with few images introduces an inherent trade-off between…
Text-to-image synthesis is the task of generating images from text descriptions. Image generation, by itself, is a challenging task. When we combine image generation and text, we bring complexity to a new level: we need to combine data from…
Text-to-image diffusion models have emerged as powerful tools for high-quality image generation and editing. Many existing approaches rely on text prompts as editing guidance. However, these methods are constrained by the need for manual…
At present, multi-oriented text detection methods based on deep neural network have achieved promising performances on various benchmarks. Nevertheless, there are still some difficulties for arbitrary shape text detection, especially for a…
Contextualized end-to-end automatic speech recognition has been an active research area, with recent efforts focusing on the implicit learning of contextual phrases based on the final loss objective. However, these approaches ignore the…
Controllable image synthesis with user scribbles has gained huge public interest with the recent advent of text-conditioned latent diffusion models. The user scribbles control the color composition while the text prompt provides control…
With the surging inclination towards carrying out tasks on computational devices and digital mediums, any method that converts a task that was previously carried out manually, to a digitized version, is always welcome. Irrespective of the…
Recently, diffusion-based deep generative models (e.g., Stable Diffusion) have shown impressive results in text-to-image synthesis. However, current text-to-image models often require multiple passes of prompt engineering by humans in order…
Linguistic knowledge is of great benefit to scene text recognition. However, how to effectively model linguistic rules in end-to-end deep networks remains a research challenge. In this paper, we argue that the limited capacity of language…
End-to-end (E2E) systems synthesise high-quality speech, but this typically requires a large amount of data. As E2E synthesis progressed from Tacotron to FastSpeech2, it became evident that features representing prosody, particularly…
Current text-to-image generative models struggle to accurately represent object states (e.g., "a table without a bottle," "an empty tumbler"). In this work, we first design a fully-automatic pipeline to generate high-quality synthetic data…