Document AI aims to automatically analyze documents by leveraging natural language processing and computer vision techniques. One of the major tasks of Document AI is document layout analysis, which structures document pages by interpreting the content and spatial relationships of layout, image, and text. This task can be image-centric, wherein the aim is to identify and label various regions such as authors and paragraphs, or text-centric, where the focus is on classifying individual words in a document. Although there are increasingly sophisticated methods for improving layout analysis, doubts remain about the extent to which their findings can be generalized to a broader context. Specifically, prior work developed systems based on very different architectures, such as transformer-based, graph-based, and CNNs. However, no work has mentioned the effectiveness of these models in a comparative analysis. Moreover, while language-independent Document AI models capable of knowledge transfer have been developed, it remains to be investigated to what degree they can effectively transfer knowledge. In this study, we aim to fill these gaps by conducting a comparative evaluation of state-of-the-art models in document layout analysis and investigating the potential of cross-lingual layout analysis by utilizing machine translation techniques.
Text-to-motion generation is a formidable task, aiming to produce human motions that align with the input text while also adhering to human capabilities and physical laws. While there have been advancements in diffusion models, their application in discrete spaces remains underexplored. Current methods often overlook the varying significance of different motions, treating them uniformly. It is essential to recognize that not all motions hold the same relevance to a particular textual description. Some motions, being more salient and informative, should be given precedence during generation. In response, we introduce a Priority-Centric Motion Discrete Diffusion Model (M2DM), which utilizes a Transformer-based VQ-VAE to derive a concise, discrete motion representation, incorporating a global self-attention mechanism and a regularization term to counteract code collapse. We also present a motion discrete diffusion model that employs an innovative noise schedule, determined by the significance of each motion token within the entire motion sequence. This approach retains the most salient motions during the reverse diffusion process, leading to more semantically rich and varied motions. Additionally, we formulate two strategies to gauge the importance of motion tokens, drawing from both textual and visual indicators. Comprehensive experiments on the HumanML3D and KIT-ML datasets confirm that our model surpasses existing techniques in fidelity and diversity, particularly for intricate textual descriptions.
This paper describes the DeepZen text to speech (TTS) system for Blizzard Challenge 2023. The goal of this challenge is to synthesise natural and high-quality speech in French, from a large monospeaker dataset (hub task) and from a smaller dataset by speaker adaptation (spoke task). We participated to both tasks with the same model architecture. Our approach has been to use an auto-regressive model, which retains an advantage for generating natural sounding speech but to improve prosodic control in several ways. Similarly to non-attentive Tacotron, the model uses a duration predictor and gaussian upsampling at inference, but with a simpler unsupervised training. We also model the speaking style at both sentence and word levels by extracting global and local style tokens from the reference speech. At inference, the global and local style tokens are predicted from a BERT model run on text. This BERT model is also used to predict specific pronunciation features like schwa elision and optional liaisons. Finally, a modified version of HifiGAN trained on a large public dataset and fine-tuned on the target voices is used to generate speech waveform. Our team is identified as O in the the Blizzard evaluation and MUSHRA test results show that our system performs second ex aequo in both hub task (median score of 0.75) and spoke task (median score of 0.68), over 18 and 14 participants, respectively.
Representing wild sounds as images is an important but challenging task due to the lack of paired datasets between sound and images and the significant differences in the characteristics of these two modalities. Previous studies have focused on generating images from sound in limited categories or music. In this paper, we propose a novel approach to generate images from in-the-wild sounds. First, we convert sound into text using audio captioning. Second, we propose audio attention and sentence attention to represent the rich characteristics of sound and visualize the sound. Lastly, we propose a direct sound optimization with CLIPscore and AudioCLIP and generate images with a diffusion-based model. In experiments, it shows that our model is able to generate high quality images from wild sounds and outperforms baselines in both quantitative and qualitative evaluations on wild audio datasets.
Extracting relational triples (subject, predicate, object) from text enables the transformation of unstructured text data into structured knowledge. The named entity recognition (NER) and the relation extraction (RE) are two foundational subtasks in this knowledge generation pipeline. The integration of subtasks poses a considerable challenge due to their disparate nature. This paper presents a novel approach that converts the triple extraction task into a graph labeling problem, capitalizing on the structural information of dependency parsing and graph recursive neural networks (GRNNs). To integrate subtasks, this paper proposes a dynamic feedback forest algorithm that connects the representations of subtasks by inference operations during model training. Experimental results demonstrate the effectiveness of the proposed method.
Recently, large-scale pre-trained vision-language models have presented benefits for alleviating class imbalance in long-tailed recognition. However, the long-tailed data distribution can corrupt the representation space, where the distance between head and tail categories is much larger than the distance between two tail categories. This uneven feature space distribution causes the model to exhibit unclear and inseparable decision boundaries on the uniformly distributed test set, which lowers its performance. To address these challenges, we propose the uniformly category prototype-guided vision-language framework to effectively mitigate feature space bias caused by data imbalance. Especially, we generate a set of category prototypes uniformly distributed on a hypersphere. Category prototype-guided mechanism for image-text matching makes the features of different classes converge to these distinct and uniformly distributed category prototypes, which maintain a uniform distribution in the feature space, and improve class boundaries. Additionally, our proposed irrelevant text filtering and attribute enhancement module allows the model to ignore irrelevant noisy text and focus more on key attribute information, thereby enhancing the robustness of our framework. In the image recognition fine-tuning stage, to address the positive bias problem of the learnable classifier, we design the class feature prototype-guided classifier, which compensates for the performance of tail classes while maintaining the performance of head classes. Our method outperforms previous vision-language methods for long-tailed learning work by a large margin and achieves state-of-the-art performance.
Our objective is open-world object counting in images, where the target object class is specified by a text description. To this end, we propose CounTX, a class-agnostic, single-stage model using a transformer decoder counting head on top of pre-trained joint text-image representations. CounTX is able to count the number of instances of any class given only an image and a text description of the target object class, and can be trained end-to-end. To the best of our knowledge, we are the first to tackle the open-world counting problem in this way. In addition to this model, we make the following contributions: (i) we compare the performance of CounTX to prior work on open-world object counting, and show that our approach exceeds the state of the art on all measures on the FSC-147 benchmark for methods that use text to specify the task; (ii) we present and release FSC-147-D, an enhanced version of FSC-147 with text descriptions, so that object classes can be described with more detailed language than their simple class names. FSC-147-D is available at https://github.com/niki-amini-naieni/CounTX/.
Generative text-to-image models such as Stable Diffusion allow users to generate images based on a textual description, the prompt. Changing the prompt is still the primary means for the user to change a generated image as desired. However, changing the image by reformulating the prompt remains a difficult process of trial and error, which has led to the emergence of prompt engineering as a new field of research. We propose and analyze methods to change the embedding of a prompt directly instead of the prompt text. It allows for more fine-grained and targeted control that takes into account user intentions. Our approach treats the generative text-to-image model as a continuous function and passes gradients between the image space and the prompt embedding space. By addressing different user interaction problems, we can apply this idea in three scenarios: (1) Optimization of a metric defined in image space that could measure, for example, image style. (2) Assistance of users in creative tasks by enabling them to navigate the image space along a selection of directions of "near" prompt embeddings. (3) Changing the embedding of the prompt to include information that the user has seen in a particular seed but finds difficult to describe in the prompt. Our experiments demonstrate the feasibility of the described methods.
Despite the remarkable performance of text-to-image diffusion models in image generation tasks, recent studies have raised the issue that generated images sometimes cannot capture the intended semantic contents of the text prompts, which phenomenon is often called semantic misalignment. To address this, here we present a novel energy-based model (EBM) framework. Specifically, we first formulate EBMs of latent image representations and text embeddings in each cross-attention layer of the denoising autoencoder. Then, we obtain the gradient of the log posterior of context vectors, which can be updated and transferred to the subsequent cross-attention layer, thereby implicitly minimizing a nested hierarchy of energy functions. Our latent EBMs further allow zero-shot compositional generation as a linear combination of cross-attention outputs from different contexts. Using extensive experiments, we demonstrate that the proposed method is highly effective in handling various image generation tasks, including multi-concept generation, text-guided image inpainting, and real and synthetic image editing.
On-line handwritten character segmentation is often associated with handwriting recognition and even though recognition models include mechanisms to locate relevant positions during the recognition process, it is typically insufficient to produce a precise segmentation. Decoupling the segmentation from the recognition unlocks the potential to further utilize the result of the recognition. We specifically focus on the scenario where the transcription is known beforehand, in which case the character segmentation becomes an assignment problem between sampling points of the stylus trajectory and characters in the text. Inspired by the $k$-means clustering algorithm, we view it from the perspective of cluster assignment and present a Transformer-based architecture where each cluster is formed based on a learned character query in the Transformer decoder block. In order to assess the quality of our approach, we create character segmentation ground truths for two popular on-line handwriting datasets, IAM-OnDB and HANDS-VNOnDB, and evaluate multiple methods on them, demonstrating that our approach achieves the overall best results.