No Arabic abstract
Cross-modality generation is an emerging topic that aims to synthesize data in one modality based on information in a different modality. In this paper, we consider a task of such: given an arbitrary audio speech and one lip image of arbitrary target identity, generate synthesized lip movements of the target identity saying the speech. To perform well in this task, it inevitably requires a model to not only consider the retention of target identity, photo-realistic of synthesized images, consistency and smoothness of lip images in a sequence, but more importantly, learn the correlations between audio speech and lip movements. To solve the collective problems, we explore the best modeling of the audio-visual correlations in building and training a lip-movement generator network. Specifically, we devise a method to fuse audio and image embeddings to generate multiple lip images at once and propose a novel correlation loss to synchronize lip changes and speech changes. Our final model utilizes a combination of four losses for a comprehensive consideration in generating lip movements; it is trained in an end-to-end fashion and is robust to lip shapes, view angles and different facial characteristics. Thoughtful experiments on three datasets ranging from lab-recorded to lips in-the-wild show that our model significantly outperforms other state-of-the-art methods extended to this task.
In this study, we propose a deep neural network for reconstructing intelligible speech from silent lip movement videos. We use auditory spectrogram as spectral representation of speech and its corresponding sound generation method resulting in a more natural sounding reconstructed speech. Our proposed network consists of an autoencoder to extract bottleneck features from the auditory spectrogram which is then used as target to our main lip reading network comprising of CNN, LSTM and fully connected layers. Our experiments show that the autoencoder is able to reconstruct the original auditory spectrogram with a 98% correlation and also improves the quality of reconstructed speech from the main lip reading network. Our model, trained jointly on different speakers is able to extract individual speaker characteristics and gives promising results of reconstructing intelligible speech with superior word recognition accuracy.
Object recognition is often viewed as a feedforward, bottom-up process in machine learning, but in real neural systems, object recognition is a complicated process which involves the interplay between two signal pathways. One is the parvocellular pathway (P-pathway), which is slow and extracts fine features of objects; the other is the magnocellular pathway (M-pathway), which is fast and extracts coarse features of objects. It has been suggested that the interplay between the two pathways endows the neural system with the capacity of processing visual information rapidly, adaptively, and robustly. However, the underlying computational mechanisms remain largely unknown. In this study, we build a computational model to elucidate the computational advantages associated with the interactions between two pathways. Our model consists of two convolution neural networks: one mimics the P-pathway, referred to as FineNet, which is deep, has small-size kernels, and receives detailed visual inputs; the other mimics the M-pathway, referred to as CoarseNet, which is shallow, has large-size kernels, and receives low-pass filtered or binarized visual inputs. The two pathways interact with each other via a Restricted Boltzmann Machine. We find that: 1) FineNet can teach CoarseNet through imitation and improve its performance considerably; 2) CoarseNet can improve the noise robustness of FineNet through association; 3) the output of CoarseNet can serve as a cognitive bias to improve the performance of FineNet. We hope that this study will provide insight into understanding visual information processing and inspire the development of new object recognition architectures.
Lip reading aims to recognize text from talking lip, while lip generation aims to synthesize talking lip according to text, which is a key component in talking face generation and is a dual task of lip reading. In this paper, we develop DualLip, a system that jointly improves lip reading and generation by leveraging the task duality and using unlabeled text and lip video data. The key ideas of the DualLip include: 1) Generate lip video from unlabeled text with a lip generation model, and use the pseudo pairs to improve lip reading; 2) Generate text from unlabeled lip video with a lip reading model, and use the pseudo pairs to improve lip generation. We further extend DualLip to talking face generation with two additionally introduced components: lip to face generation and text to speech generation. Experiments on GRID and TCD-TIMIT demonstrate the effectiveness of DualLip on improving lip reading, lip generation, and talking face generation by utilizing unlabeled data. Specifically, the lip generation model in our DualLip system trained with only10% paired data surpasses the performance of that trained with the whole paired data. And on the GRID benchmark of lip reading, we achieve 1.16% character error rate and 2.71% word error rate, outperforming the state-of-the-art models using the same amount of paired data.
Recently, there emerges a series of vision Transformers, which show superior performance with a more compact model size than conventional convolutional neural networks, thanks to the strong ability of Transformers to model long-range dependencies. However, the advantages of vision Transformers also come with a price: Self-attention, the core part of Transformer, has a quadratic complexity to the input sequence length. This leads to a dramatic increase of computation and memory cost with the increase of sequence length, thus introducing difficulties when applying Transformers to the vision tasks that require dense predictions based on high-resolution feature maps. In this paper, we propose a new vision Transformer, named Glance-and-Gaze Transformer (GG-Transformer), to address the aforementioned issues. It is motivated by the Glance and Gaze behavior of human beings when recognizing objects in natural scenes, with the ability to efficiently model both long-range dependencies and local context. In GG-Transformer, the Glance and Gaze behavior is realized by two parallel branches: The Glance branch is achieved by performing self-attention on the adaptively-dilated partitions of the input, which leads to a linear complexity while still enjoying a global receptive field; The Gaze branch is implemented by a simple depth-wise convolutional layer, which compensates local image context to the features obtained by the Glance mechanism. We empirically demonstrate our method achieves consistently superior performance over previous state-of-the-art Transformers on various vision tasks and benchmarks. The codes and models will be made available at https://github.com/yucornetto/GG-Transformer.
Spatial downsampling layers are favored in convolutional neural networks (CNNs) to downscale feature maps for larger receptive fields and less memory consumption. However, for discriminative tasks, there is a possibility that these layers lose the discriminative details due to improper pooling strategies, which could hinder the learning process and eventually result in suboptimal models. In this paper, we present a unified framework over the existing downsampling layers (e.g., average pooling, max pooling, and strided convolution) from a local importance view. In this framework, we analyze the issues of these widely-used pooling layers and figure out the criteria for designing an effective downsampling layer. According to this analysis, we propose a conceptually simple, general, and effective pooling layer based on local importance modeling, termed as {em Local Importance-based Pooling} (LIP). LIP can automatically enhance discriminative features during the downsampling procedure by learning adaptive importance weights based on inputs. Experiment results show that LIP consistently yields notable gains with different depths and different architectures on ImageNet classification. In the challenging MS COCO dataset, detectors with our LIP-ResNets as backbones obtain a consistent improvement ($ge 1.4%$) over the vanilla ResNets, and especially achieve the current state-of-the-art performance in detecting small objects under the single-scale testing scheme.