Large-scale vision-language pre-training has shown promising advances on various downstream tasks and achieved significant performance in multi-modal understanding and generation tasks. However, existing methods often perform poorly on image-text matching tasks that require a detailed semantics understanding of the text. Although there have been some works on this problem, they do not sufficiently exploit the structural knowledge present in sentences to enhance multi-modal language representations, which leads to poor performance. In this paper, we present an end-to-end framework Structure-CLIP, which integrates latent detailed semantics from the text to enhance fine-grained semantic representations. Specifically, (1) we use scene graphs in order to pay more attention to the detailed semantic learning in the text and fully explore structured knowledge between fine-grained semantics, and (2) we utilize the knowledge-enhanced framework with the help of the scene graph to make full use of representations of structured knowledge. To verify the effectiveness of our proposed method, we pre-trained our models with the aforementioned approach and conduct experiments on different downstream tasks. Numerical results show that Structure-CLIP can often achieve state-of-the-art performance on both VG-Attribution and VG-Relation datasets. Extensive experiments show its components are effective and its predictions are interpretable, which proves that our proposed method can enhance detailed semantic representation well.
Portrait stylization is a long-standing task enabling extensive applications. Although 2D-based methods have made great progress in recent years, real-world applications such as metaverse and games often demand 3D content. On the other hand, the requirement of 3D data, which is costly to acquire, significantly impedes the development of 3D portrait stylization methods. In this paper, inspired by the success of 3D-aware GANs that bridge 2D and 3D domains with 3D fields as the intermediate representation for rendering 2D images, we propose a novel method, dubbed HyperStyle3D, based on 3D-aware GANs for 3D portrait stylization. At the core of our method is a hyper-network learned to manipulate the parameters of the generator in a single forward pass. It not only offers a strong capacity to handle multiple styles with a single model, but also enables flexible fine-grained stylization that affects only texture, shape, or local part of the portrait. While the use of 3D-aware GANs bypasses the requirement of 3D data, we further alleviate the necessity of style images with the CLIP model being the stylization guidance. We conduct an extensive set of experiments across the style, attribute, and shape, and meanwhile, measure the 3D consistency. These experiments demonstrate the superior capability of our HyperStyle3D model in rendering 3D-consistent images in diverse styles, deforming the face shape, and editing various attributes.
Quantum many-body physics simulation has important impacts on understanding fundamental science and has applications to quantum materials design and quantum technology. However, due to the exponentially growing size of the Hilbert space with respect to the particle number, a direct simulation is intractable. While representing quantum states with tensor networks and neural networks are the two state-of-the-art methods for approximate simulations, each has its own limitations in terms of expressivity and optimization. To address these challenges, we develop a novel architecture, Autoregressive Neural TensorNet (ANTN), which bridges tensor networks and autoregressive neural networks. We show that Autoregressive Neural TensorNet parameterizes normalized wavefunctions with exact sampling, generalizes the expressivity of tensor networks and autoregressive neural networks, and inherits a variety of symmetries from autoregressive neural networks. We demonstrate our approach on the 2D $J_1$-$J_2$ Heisenberg model with different systems sizes and coupling parameters, outperforming both tensor networks and autoregressive neural networks. Our work opens up new opportunities for both scientific simulations and machine learning applications.
Automatic target sound extraction (TSE) is a machine learning approach to mimic the human auditory perception capability of attending to a sound source of interest from a mixture of sources. It often uses a model conditioned on a fixed form of target sound clues, such as a sound class label, which limits the ways in which users can interact with the model to specify the target sounds. To leverage variable number of clues cross modalities available in the inference phase, including a video, a sound event class, and a text caption, we propose a unified transformer-based TSE model architecture, where a multi-clue attention module integrates all the clues across the modalities. Since there is no off-the-shelf benchmark to evaluate our proposed approach, we build a dataset based on public corpora, Audioset and AudioCaps. Experimental results for seen and unseen target-sound evaluation sets show that our proposed TSE model can effectively deal with a varying number of clues which improves the TSE performance and robustness against partially compromised clues.
We propose a cross-lingual neural codec language model, VALL-E X, for cross-lingual speech synthesis. Specifically, we extend VALL-E and train a multi-lingual conditional codec language model to predict the acoustic token sequences of the target language speech by using both the source language speech and the target language text as prompts. VALL-E X inherits strong in-context learning capabilities and can be applied for zero-shot cross-lingual text-to-speech synthesis and zero-shot speech-to-speech translation tasks. Experimental results show that it can generate high-quality speech in the target language via just one speech utterance in the source language as a prompt while preserving the unseen speaker's voice, emotion, and acoustic environment. Moreover, VALL-E X effectively alleviates the foreign accent problems, which can be controlled by a language ID. Audio samples are available at \url{https://aka.ms/vallex}.
The rapid development of multi-view 3D human pose estimation (HPE) is attributed to the maturation of monocular 2D HPE and the geometry of 3D reconstruction. However, 2D detection outliers in occluded views due to neglect of view consistency, and 3D implausible poses due to lack of pose coherence, remain challenges. To solve this, we introduce a Multi-View Fusion module to refine 2D results by establishing view correlations. Then, Holistic Triangulation is proposed to infer the whole pose as an entirety, and anatomy prior is injected to maintain the pose coherence and improve the plausibility. Anatomy prior is extracted by PCA whose input is skeletal structure features, which can factor out global context and joint-by-joint relationship from abstract to concrete. Benefiting from the closed-form solution, the whole framework is trained end-to-end. Our method outperforms the state of the art in both precision and plausibility which is assessed by a new metric.
Speaker change detection (SCD) is an important feature that improves the readability of the recognized words from an automatic speech recognition (ASR) system by breaking the word sequence into paragraphs at speaker change points. Existing SCD solutions either require additional ensemble for the time based decisions and recognized word sequences, or implement a tight integration between ASR and SCD, limiting the potential optimum performance for both tasks. To address these issues, we propose a novel framework for the SCD task, where an additional SCD module is built on top of an existing Transformer Transducer ASR (TT-ASR) network. Two variants of the SCD network are explored in this framework that naturally estimate speaker change probability for each word, while allowing the ASR and SCD to have independent optimization scheme for the best performance. Experiments show that our methods can significantly improve the F1 score on LibriCSS and Microsoft call center data sets without ASR degradation, compared with a joint SCD and ASR baseline.
Molecule generation with desired properties has grown immensely in popularity by disruptively changing the way scientists design molecular structures and providing support for chemical and materials design. However, despite the promising outcome, previous machine learning-based deep generative models suffer from a reliance on complex, task-specific fine-tuning, limited dimensional latent spaces, or the quality of expert rules. In this work, we propose MolGen, a pre-trained molecular language model that effectively learns and shares knowledge across multiple generation tasks and domains. Specifically, we pre-train MolGen with the chemical language SELFIES on more than 100 million unlabelled molecules. We further propose multi-task molecular prefix tuning across several molecular generation tasks and different molecular domains (synthetic & natural products) with a self-feedback mechanism. Extensive experiments show that MolGen can obtain superior performances on well-known molecular generation benchmark datasets. The further analysis illustrates that MolGen can accurately capture the distribution of molecules, implicitly learn their structural characteristics, and efficiently explore the chemical space with the guidance of multi-task molecular prefix tuning. Codes, datasets, and the pre-trained model will be available in https://github.com/zjunlp/MolGen.
We introduce a language modeling approach for text to speech synthesis (TTS). Specifically, we train a neural codec language model (called Vall-E) using discrete codes derived from an off-the-shelf neural audio codec model, and regard TTS as a conditional language modeling task rather than continuous signal regression as in previous work. During the pre-training stage, we scale up the TTS training data to 60K hours of English speech which is hundreds of times larger than existing systems. Vall-E emerges in-context learning capabilities and can be used to synthesize high-quality personalized speech with only a 3-second enrolled recording of an unseen speaker as an acoustic prompt. Experiment results show that Vall-E significantly outperforms the state-of-the-art zero-shot TTS system in terms of speech naturalness and speaker similarity. In addition, we find Vall-E could preserve the speaker's emotion and acoustic environment of the acoustic prompt in synthesis. See https://aka.ms/valle for demos of our work.