The convergence of text, visual, and audio data is a key step towards human-like artificial intelligence, however the current Vision-Language-Speech landscape is dominated by encoder-only models which lack generative abilities. We propose closing this gap with i-Code V2, the first model capable of generating natural language from any combination of Vision, Language, and Speech data. i-Code V2 is an integrative system that leverages state-of-the-art single-modality encoders, combining their outputs with a new modality-fusing encoder in order to flexibly project combinations of modalities into a shared representational space. Next, language tokens are generated from these representations via an autoregressive decoder. The whole framework is pretrained end-to-end on a large collection of dual- and single-modality datasets using a novel text completion objective that can be generalized across arbitrary combinations of modalities. i-Code V2 matches or outperforms state-of-the-art single- and dual-modality baselines on 7 multimodal tasks, demonstrating the power of generative multimodal pretraining across a diversity of tasks and signals.
ChatGPT and its improved variant GPT4 have revolutionized the NLP field with a single model solving almost all text related tasks. However, such a model for computer vision does not exist, especially for 3D vision. This article first provides a brief view on the progress of deep learning in text, image and 3D fields from the model perspective. Moreover, this work further discusses how AIGC evolves from the data perspective. On top of that, this work presents an outlook on the development of AIGC in 3D from the data perspective.
Geoparsing is a fundamental technique for analyzing geo-entity information in text. We focus on document-level geoparsing, which considers geographic relatedness among geo-entity mentions, and presents a Japanese travelogue dataset designed for evaluating document-level geoparsing systems. Our dataset comprises 200 travelogue documents with rich geo-entity information: 12,171 mentions, 6,339 coreference clusters, and 2,551 geo-entities linked to geo-database entries.
Creating synthetic voices with found data is challenging, as real-world recordings often contain various types of audio degradation. One way to address this problem is to pre-enhance the speech with an enhancement model and then use the enhanced data for text-to-speech (TTS) model training. Ideally, the enhancement model should be able to tackle multiple types of audio degradation simultaneously. This paper investigates the use of conditional diffusion models for generalized speech enhancement. The enhancement is performed on the log Mel-spectrogram domain to align with the TTS training objective. Text information is introduced as an additional condition to improve the model robustness. Experiments on real-world recordings demonstrate that the synthetic voice built on data enhanced by the proposed model produces higher-quality synthetic speech, compared to those trained on data enhanced by strong baselines. Audio samples are available at \url{https://dmse4tts.github.io/}.
Existing research on multimodal relation extraction (MRE) faces two co-existing challenges, internal-information over-utilization and external-information under-exploitation. To combat that, we propose a novel framework that simultaneously implements the idea of internal-information screening and external-information exploiting. First, we represent the fine-grained semantic structures of the input image and text with the visual and textual scene graphs, which are further fused into a unified cross-modal graph (CMG). Based on CMG, we perform structure refinement with the guidance of the graph information bottleneck principle, actively denoising the less-informative features. Next, we perform topic modeling over the input image and text, incorporating latent multimodal topic features to enrich the contexts. On the benchmark MRE dataset, our system outperforms the current best model significantly. With further in-depth analyses, we reveal the great potential of our method for the MRE task. Our codes are open at https://github.com/ChocoWu/MRE-ISE.
How can speech-to-text translation (ST) perform as well as machine translation (MT)? The key point is to bridge the modality gap between speech and text so that useful MT techniques can be applied to ST. Recently, the approach of representing speech with unsupervised discrete units yields a new way to ease the modality problem. This motivates us to propose Discrete Unit Back-translation (DUB) to answer two questions: (1) Is it better to represent speech with discrete units than with continuous features in direct ST? (2) How much benefit can useful MT techniques bring to ST? With DUB, the back-translation technique can successfully be applied on direct ST and obtains an average boost of 5.5 BLEU on MuST-C En-De/Fr/Es. In the low-resource language scenario, our method achieves comparable performance to existing methods that rely on large-scale external data. Code and models are available at https://github.com/0nutation/DUB.
Recent advancements in vision-language pre-training (e.g. CLIP) have shown that vision models can benefit from language supervision. While many models using language modality have achieved great success on 2D vision tasks, the joint representation learning of 3D point cloud with text remains under-explored due to the difficulty of 3D-Text data pair acquisition and the irregularity of 3D data structure. In this paper, we propose a novel Text4Point framework to construct language-guided 3D point cloud models. The key idea is utilizing 2D images as a bridge to connect the point cloud and the language modalities. The proposed Text4Point follows the pre-training and fine-tuning paradigm. During the pre-training stage, we establish the correspondence of images and point clouds based on the readily available RGB-D data and use contrastive learning to align the image and point cloud representations. Together with the well-aligned image and text features achieved by CLIP, the point cloud features are implicitly aligned with the text embeddings. Further, we propose a Text Querying Module to integrate language information into 3D representation learning by querying text embeddings with point cloud features. For fine-tuning, the model learns task-specific 3D representations under informative language guidance from the label set without 2D images. Extensive experiments demonstrate that our model shows consistent improvement on various downstream tasks, such as point cloud semantic segmentation, instance segmentation, and object detection. The code will be available here: https://github.com/LeapLabTHU/Text4Point
Recent works have explored text-guided image editing using diffusion models and generated edited images based on text prompts. However, the models struggle to accurately locate the regions to be edited and faithfully perform precise edits. In this work, we propose a framework termed InstructEdit that can do fine-grained editing based on user instructions. Our proposed framework has three components: language processor, segmenter, and image editor. The first component, the language processor, processes the user instruction using a large language model. The goal of this processing is to parse the user instruction and output prompts for the segmenter and captions for the image editor. We adopt ChatGPT and optionally BLIP2 for this step. The second component, the segmenter, uses the segmentation prompt provided by the language processor. We employ a state-of-the-art segmentation framework Grounded Segment Anything to automatically generate a high-quality mask based on the segmentation prompt. The third component, the image editor, uses the captions from the language processor and the masks from the segmenter to compute the edited image. We adopt Stable Diffusion and the mask-guided generation from DiffEdit for this purpose. Experiments show that our method outperforms previous editing methods in fine-grained editing applications where the input image contains a complex object or multiple objects. We improve the mask quality over DiffEdit and thus improve the quality of edited images. We also show that our framework can accept multiple forms of user instructions as input. We provide the code at https://github.com/QianWangX/InstructEdit.
Large Language Models (LLMs) have achieved great success in various natural language tasks. It has aroused much interest in evaluating the specific reasoning capability of LLMs, such as multilingual reasoning and mathematical reasoning. However, as one of the key reasoning perspectives, logical reasoning capability has not yet been thoroughly evaluated. In this work, we aim to bridge those gaps and provide comprehensive evaluations. Firstly, to offer systematic evaluations, this paper selects fifteen typical logical reasoning datasets and organizes them into deductive, inductive, abductive and mixed-form reasoning settings. Considering the comprehensiveness of evaluations, we include three representative LLMs (i.e., text-davinci-003, ChatGPT and BARD) and evaluate them on all selected datasets under zero-shot, one-shot and three-shot settings. Secondly, different from previous evaluations relying only on simple metrics (e.g., accuracy), we propose fine-level evaluations from objective and subjective manners, covering both answers and explanations. Also, to uncover the logical flaws of LLMs, bad cases will be attributed to five error types from two dimensions. Thirdly, to avoid the influences of knowledge bias and purely focus on benchmarking the logical reasoning capability of LLMs, we propose a new dataset with neutral content. It contains 3K samples and covers deductive, inductive and abductive reasoning settings. Based on the in-depth evaluations, this paper finally concludes the ability maps of logical reasoning capability from six dimensions (i.e., correct, rigorous, self-aware, active, oriented and no hallucination). It reflects the pros and cons of LLMs and gives guiding directions for future works.
Conversational emotion recognition (CER) is an important research topic in human-computer interactions. Although deep learning (DL) based CER approaches have achieved excellent performance, existing cross-modal feature fusion methods used in these DL-based approaches either ignore the intra-modal and inter-modal emotional interaction or have high computational complexity. To address these issues, this paper develops a novel cross-modal feature fusion method for the CER task, i.e., the low-rank matching attention method (LMAM). By setting a matching weight and calculating attention scores between modal features row by row, LMAM contains fewer parameters than the self-attention method. We further utilize the low-rank decomposition method on the weight to make the parameter number of LMAM less than one-third of the self-attention. Therefore, LMAM can potentially alleviate the over-fitting issue caused by a large number of parameters. Additionally, by computing and fusing the similarity of intra-modal and inter-modal features, LMAM can also fully exploit the intra-modal contextual information within each modality and the complementary semantic information across modalities (i.e., text, video and audio) simultaneously. Experimental results on some benchmark datasets show that LMAM can be embedded into any existing state-of-the-art DL-based CER methods and help boost their performance in a plug-and-play manner. Also, experimental results verify the superiority of LMAM compared with other popular cross-modal fusion methods. Moreover, LMAM is a general cross-modal fusion method and can thus be applied to other multi-modal recognition tasks, e.g., session recommendation and humour detection.