相关论文: SPEECH-COCO: 600k Visually Grounded Spoken Caption…

In this paper we present the first model for directly synthesizing fluent, natural-sounding spoken audio captions for images that does not require natural language text as an intermediate representation or source of supervision. Instead, we…

Synthesizing realistic images from text descriptions on a dataset like Microsoft Common Objects in Context (MS COCO), where each image can contain several objects, is a challenging task. Prior work has used text captions to generate images.…

Massive web datasets play a key role in the success of large vision-language models like CLIP and Flamingo. However, the raw web data is noisy, and existing filtering methods to reduce noise often come at the expense of data diversity. Our…

This paper presents a novel approach for automatically generating image descriptions: visual detectors, language models, and multimodal similarity models learnt directly from a dataset of image captions. We use multiple instance learning to…

Audio captioning is the novel task of general audio content description using free text. It is an intermodal translation task (not speech-to-text), where a system accepts as an input an audio signal and outputs the textual description (i.e.…

Image captioning is a multimodal problem that has drawn extensive attention in both the natural language processing and computer vision community. In this paper, we present a novel image captioning architecture to better explore semantics…

Generative models have shown significant achievements in audio generation tasks. However, existing models struggle with complex and detailed prompts, leading to potential performance degradation. We hypothesize that this problem stems from…

We present Pix2Cap-COCO, the first panoptic pixel-level caption dataset designed to advance fine-grained visual understanding. To achieve this, we carefully design an automated annotation pipeline that prompts GPT-4V to generate…

This paper introduces RyanSpeech, a new speech corpus for research on automated text-to-speech (TTS) systems. Publicly available TTS corpora are often noisy, recorded with multiple speakers, or lack quality male speech data. In order to…

Image descriptions can help visually impaired people to quickly understand the image content. While we made significant progress in automatically describing images and optical character recognition, current approaches are unable to include…

Visual captioning aims to generate textual descriptions given images or videos. Traditionally, image captioning models are trained on human annotated datasets such as Flickr30k and MS-COCO, which are limited in size and diversity. This…

Instruction-based speech processing is becoming popular. Studies show that training with multiple tasks boosts performance, but collecting diverse, large-scale tasks and datasets is expensive. Thus, it is highly desirable to design a…

Image captioning requires numerous annotated image-text pairs, resulting in substantial annotation costs. Recently, large models (e.g. diffusion models and large language models) have excelled in producing high-quality images and text. This…

Recent progress in audio-language modeling, such as automated audio captioning, has benefited from training on synthetic data generated with the aid of large-language models. However, such approaches for environmental sound captioning have…

We argue that generative text-to-image models often struggle with prompt adherence due to the noisy and unstructured nature of large-scale datasets like LAION-5B. This forces users to rely heavily on prompt engineering to elicit desirable…

Dubbed series are gaining a lot of popularity in recent years with strong support from major media service providers. Such popularity is fueled by studies that showed that dubbed versions of TV shows are more popular than their subtitled…

Understanding another person's creative output requires a shared language of association. However, when training vision-language models such as CLIP, we rely on web-scraped datasets containing short, predominantly literal, alt-text. In this…

Text-to-Speech (TTS) synthesis faces the inherent challenge of producing multiple speech outputs with varying prosody given a single text input. While previous research has addressed this by predicting prosodic information from both text…

With the emergence of audio-language models, constructing large-scale paired audio-language datasets has become essential yet challenging for model development, primarily due to the time-intensive and labour-heavy demands involved. While…

State-of-The-Art (SoTA) image captioning models are often trained on the MicroSoft Common Objects in Context (MS-COCO) dataset, which contains human-annotated captions with an average length of approximately ten tokens. Although effective…