Structure information is critical for understanding the semantics of text-rich images, such as documents, tables, and charts. Existing Multimodal Large Language Models (MLLMs) for Visual Document Understanding are equipped with text recognition ability but lack general structure understanding abilities for text-rich document images. In this work, we emphasize the importance of structure information in Visual Document Understanding and propose the Unified Structure Learning to boost the performance of MLLMs. Our Unified Structure Learning comprises structure-aware parsing tasks and multi-grained text localization tasks across 5 domains: document, webpage, table, chart, and natural image. To better encode structure information, we design a simple and effective vision-to-text module H-Reducer, which can not only maintain the layout information but also reduce the length of visual features by merging horizontal adjacent patches through convolution, enabling the LLM to understand high-resolution images more efficiently. Furthermore, by constructing structure-aware text sequences and multi-grained pairs of texts and bounding boxes for publicly available text-rich images, we build a comprehensive training set DocStruct4M to support structure learning. Finally, we construct a small but high-quality reasoning tuning dataset DocReason25K to trigger the detailed explanation ability in the document domain. Our model DocOwl 1.5 achieves state-of-the-art performance on 10 visual document understanding benchmarks, improving the SOTA performance of MLLMs with a 7B LLM by more than 10 points in 5/10 benchmarks. Our codes, models, and datasets are publicly available at https://github.com/X-PLUG/mPLUG-DocOwl/tree/main/DocOwl1.5.
We introduce SPAFormer, an innovative model designed to overcome the combinatorial explosion challenge in the 3D Part Assembly (3D-PA) task. This task requires accurate prediction of each part's pose and shape in sequential steps, and as the number of parts increases, the possible assembly combinations increase exponentially, leading to a combinatorial explosion that severely hinders the efficacy of 3D-PA. SPAFormer addresses this problem by leveraging weak constraints from assembly sequences, effectively reducing the solution space's complexity. Since assembly part sequences convey construction rules similar to sentences being structured through words, our model explores both parallel and autoregressive generation. It further enhances assembly through knowledge enhancement strategies that utilize the attributes of parts and their sequence information, enabling it to capture the inherent assembly pattern and relationships among sequentially ordered parts. We also construct a more challenging benchmark named PartNet-Assembly covering 21 varied categories to more comprehensively validate the effectiveness of SPAFormer. Extensive experiments demonstrate the superior generalization capabilities of SPAFormer, particularly with multi-tasking and in scenarios requiring long-horizon assembly. Codes and model weights will be released at \url{https://github.com/xuboshen/SPAFormer}.
We humans are good at translating third-person observations of hand-object interactions (HOI) into an egocentric view. However, current methods struggle to replicate this ability of view adaptation from third-person to first-person. Although some approaches attempt to learn view-agnostic representation from large-scale video datasets, they ignore the relationships among multiple third-person views. To this end, we propose a Prompt-Oriented View-agnostic learning (POV) framework in this paper, which enables this view adaptation with few egocentric videos. Specifically, We introduce interactive masking prompts at the frame level to capture fine-grained action information, and view-aware prompts at the token level to learn view-agnostic representation. To verify our method, we establish two benchmarks for transferring from multiple third-person views to the egocentric view. Our extensive experiments on these benchmarks demonstrate the efficiency and effectiveness of our POV framework and prompt tuning techniques in terms of view adaptation and view generalization. Our code is available at \url{https://github.com/xuboshen/pov_acmmm2023}.
Large Multimodal Models (LMMs) often suffer from multimodal hallucinations, wherein they may create content that is not present in the visual inputs. In this paper, we explore a new angle of this issue: overly detailed training data hinders the model's ability to timely terminate generation, leading to continued outputs beyond visual perception limits. By investigating how the model decides to terminate generation with EOS, the special end-of-sentence token, we find that the model assesses the completeness of the entire sequence by comparing the generated text with the image. This observation suggests that the model possesses an inherent potential of making proper EOS decisions based on its visual perception to avoid overly lengthy outputs. To take advantage of such potential, we explore two methods to mitigate multimodal hallucinations: a training objective that enables the model to reduce hallucinations by learning from regular instruction data, and a data filtering strategy to prevent harmful training data from exacerbating model hallucinations. Both methods significantly improve the hallucination performance of LMMs, without requiring any additional data or knowledge.
In singing voice synthesis (SVS), generating singing voices from musical scores faces challenges due to limited data availability, a constraint less common in text-to-speech (TTS). This study proposes a new approach to address this data scarcity. We utilize an existing singing voice synthesizer for data augmentation and apply precise manual tuning to reduce unnatural voice synthesis. Our development of two extensive singing voice corpora, ACE-Opencpop and KiSing-v2, facilitates large-scale, multi-singer voice synthesis. Utilizing pre-trained models derived from these corpora, we achieve notable improvements in voice quality, evident in both in-domain and out-of-domain scenarios. The corpora, pre-trained models, and their related training recipes are publicly available at Muskits-ESPnet (https://github.com/espnet/espnet).
Text is ubiquitous in our visual world, conveying crucial information, such as in documents, websites, and everyday photographs. In this work, we propose UReader, a first exploration of universal OCR-free visually-situated language understanding based on the Multimodal Large Language Model (MLLM). By leveraging the shallow text recognition ability of the MLLM, we only finetuned 1.2% parameters and the training cost is much lower than previous work following domain-specific pretraining and finetuning paradigms. Concretely, UReader is jointly finetuned on a wide range of Visually-situated Language Understanding tasks via a unified instruction format. To enhance the visual text and semantic understanding, we further apply two auxiliary tasks with the same format, namely text reading and key points generation tasks. We design a shape-adaptive cropping module before the encoder-decoder architecture of MLLM to leverage the frozen low-resolution vision encoder for processing high-resolution images. Without downstream finetuning, our single model achieves state-of-the-art ocr-free performance in 8 out of 10 visually-situated language understanding tasks, across 5 domains: documents, tables, charts, natural images, and webpage screenshots. Codes and instruction-tuning datasets will be released.
While current visual captioning models have achieved impressive performance, they often assume that the image is well-captured and provides a complete view of the scene. In real-world scenarios, however, a single image may not offer a good viewpoint, hindering fine-grained scene understanding. To overcome this limitation, we propose a novel task called Embodied Captioning, which equips visual captioning models with navigation capabilities, enabling them to actively explore the scene and reduce visual ambiguity from suboptimal viewpoints. Specifically, starting at a random viewpoint, an agent must navigate the environment to gather information from different viewpoints and generate a comprehensive paragraph describing all objects in the scene. To support this task, we build the ET-Cap dataset with Kubric simulator, consisting of 10K 3D scenes with cluttered objects and three annotated paragraphs per scene. We propose a Cascade Embodied Captioning model (CaBOT), which comprises of a navigator and a captioner, to tackle this task. The navigator predicts which actions to take in the environment, while the captioner generates a paragraph description based on the whole navigation trajectory. Extensive experiments demonstrate that our model outperforms other carefully designed baselines. Our dataset, codes and models are available at https://aim3-ruc.github.io/ExploreAndTell.
There has been a growing interest in using end-to-end acoustic models for singing voice synthesis (SVS). Typically, these models require an additional vocoder to transform the generated acoustic features into the final waveform. However, since the acoustic model and the vocoder are not jointly optimized, a gap can exist between the two models, leading to suboptimal performance. Although a similar problem has been addressed in the TTS systems by joint-training or by replacing acoustic features with a latent representation, adopting corresponding approaches to SVS is not an easy task. How to improve the joint-training of SVS systems has not been well explored. In this paper, we conduct a systematic investigation of how to better perform a joint-training of an acoustic model and a vocoder for SVS. We carry out extensive experiments and demonstrate that our joint-training strategy outperforms baselines, achieving more stable performance across different datasets while also increasing the interpretability of the entire framework.
Stylized visual captioning aims to generate image or video descriptions with specific styles, making them more attractive and emotionally appropriate. One major challenge with this task is the lack of paired stylized captions for visual content, so most existing works focus on unsupervised methods that do not rely on parallel datasets. However, these approaches still require training with sufficient examples that have style labels, and the generated captions are limited to predefined styles. To address these limitations, we explore the problem of Few-Shot Stylized Visual Captioning, which aims to generate captions in any desired style, using only a few examples as guidance during inference, without requiring further training. We propose a framework called FS-StyleCap for this task, which utilizes a conditional encoder-decoder language model and a visual projection module. Our two-step training scheme proceeds as follows: first, we train a style extractor to generate style representations on an unlabeled text-only corpus. Then, we freeze the extractor and enable our decoder to generate stylized descriptions based on the extracted style vector and projected visual content vectors. During inference, our model can generate desired stylized captions by deriving the style representation from user-supplied examples. Our automatic evaluation results for few-shot sentimental visual captioning outperform state-of-the-art approaches and are comparable to models that are fully trained on labeled style corpora. Human evaluations further confirm our model s ability to handle multiple styles.
Temporal video grounding (TVG) aims to retrieve the time interval of a language query from an untrimmed video. A significant challenge in TVG is the low "Semantic Noise Ratio (SNR)", which results in worse performance with lower SNR. Prior works have addressed this challenge using sophisticated techniques. In this paper, we propose a no-frills TVG model that consists of two core modules, namely multi-scale neighboring attention and zoom-in boundary detection. The multi-scale neighboring attention restricts each video token to only aggregate visual contexts from its neighbor, enabling the extraction of the most distinguishing information with multi-scale feature hierarchies from high-ratio noises. The zoom-in boundary detection then focuses on local-wise discrimination of the selected top candidates for fine-grained grounding adjustment. With an end-to-end training strategy, our model achieves competitive performance on different TVG benchmarks, while also having the advantage of faster inference speed and lighter model parameters, thanks to its lightweight architecture.