arXiv subjects

Maja Pantic

Publications and source records attributed to Maja Pantic.

At least 73 records · Page 4Linked to original sources

arXiv2021

Dynamic Face Video Segmentation via Reinforcement Learning

For real-time semantic video segmentation, most recent works utilised a dynamic framework with a key scheduler to make online key/non-key decisions. Some works used a fixed key scheduling policy, while others proposed adaptive key scheduling methods based on heuristic strategies, both of which may lead to suboptimal global performance. To overcome this limitation, we model the online key decision process in dynamic video segmentation as a deep reinforcement learning problem and learn an efficient and effective scheduling policy from expert information about decision history and from the process of maximising global return. Moreover, we study the application of dynamic video segmentation on face videos, a field that has not been investigated before. By evaluating on the 300VW dataset, we show that the performance of our reinforcement key scheduler outperforms that of various baselines in terms of both effective key selections and running speed. Further results on the Cityscapes dataset demonstrate that our proposed method can also generalise to other scenarios. To the best of our knowledge, this is the first work to use reinforcement learning for online key-frame decision in dynamic video segmentation, and also the first work on its application on face videos.

cs.CV↗

arXiv2021

DINO: A Conditional Energy-Based GAN for Domain Translation

Domain translation is the process of transforming data from one domain to another while preserving the common semantics. Some of the most popular domain translation systems are based on conditional generative adversarial networks, which use source domain data to drive the generator and as an input to the discriminator. However, this approach does not enforce the preservation of shared semantics since the conditional input can often be ignored by the discriminator. We propose an alternative method for conditioning and present a new framework, where two networks are simultaneously trained, in a supervised manner, to perform domain translation in opposite directions. Our method is not only better at capturing the shared information between two domains but is more generic and can be applied to a broader range of problems. The proposed framework performs well even in challenging cross-modal translations, such as video-driven speech reconstruction, for which other systems struggle to maintain correspondence.

cs.LG↗

arXiv2021

Detecting Adversarial Attacks On Audiovisual Speech Recognition

Adversarial attacks pose a threat to deep learning models. However, research on adversarial detection methods, especially in the multi-modal domain, is very limited. In this work, we propose an efficient and straightforward detection method based on the temporal correlation between audio and video streams. The main idea is that the correlation between audio and video in adversarial examples will be lower than benign examples due to added adversarial noise. We use the synchronisation confidence score as a proxy for audiovisual correlation and based on it we can detect adversarial attacks. To the best of our knowledge, this is the first work on detection of adversarial attacks on audiovisual speech recognition models. We apply recent adversarial attacks on two audiovisual speech recognition models trained on the GRID and LRW datasets. The experimental results demonstrate that the proposed approach is an effective way for detecting such attacks.

cs.CV↗

arXiv2021

Cauchy-Schwarz Regularized Autoencoder

Recent work in unsupervised learning has focused on efficient inference and learning in latent variables models. Training these models by maximizing the evidence (marginal likelihood) is typically intractable. Thus, a common approximation is to maximize the Evidence Lower BOund (ELBO) instead. Variational autoencoders (VAE) are a powerful and widely-used class of generative models that optimize the ELBO efficiently for large datasets. However, the VAE's default Gaussian choice for the prior imposes a strong constraint on its ability to represent the true posterior, thereby degrading overall performance. A Gaussian mixture model (GMM) would be a richer prior, but cannot be handled efficiently within the VAE framework because of the intractability of the Kullback-Leibler divergence for GMMs. We deviate from the common VAE framework in favor of one with an analytical solution for Gaussian mixture prior. To perform efficient inference for GMM priors, we introduce a new constrained objective based on the Cauchy-Schwarz divergence, which can be computed analytically for GMMs. This new objective allows us to incorporate richer, multi-modal priors into the autoencoding framework. We provide empirical studies on a range of datasets and show that our objective improves upon variational auto-encoding models in density estimation, unsupervised clustering, semi-supervised learning, and face analysis.

cs.LG↗

arXiv2021

End-to-end Audio-visual Speech Recognition with Conformers

In this work, we present a hybrid CTC/Attention model based on a ResNet-18 and Convolution-augmented transformer (Conformer), that can be trained in an end-to-end manner. In particular, the audio and visual encoders learn to extract features directly from raw pixels and audio waveforms, respectively, which are then fed to conformers and then fusion takes place via a Multi-Layer Perceptron (MLP). The model learns to recognise characters using a combination of CTC and an attention mechanism. We show that end-to-end training, instead of using pre-computed visual features which is common in the literature, the use of a conformer, instead of a recurrent network, and the use of a transformer-based language model, significantly improve the performance of our model. We present results on the largest publicly available datasets for sentence-level speech recognition, Lip Reading Sentences 2 (LRS2) and Lip Reading Sentences 3 (LRS3), respectively. The results show that our proposed models raise the state-of-the-art performance by a large margin in audio-only, visual-only, and audio-visual experiments.

cs.CV↗

arXiv2020

Investigating Bias in Deep Face Analysis: The KANFace Dataset and Empirical Study

Deep learning-based methods have pushed the limits of the state-of-the-art in face analysis. However, despite their success, these models have raised concerns regarding their bias towards certain demographics. This bias is inflicted both by limited diversity across demographics in the training set, as well as the design of the algorithms. In this work, we investigate the demographic bias of deep learning models in face recognition, age estimation, gender recognition and kinship verification. To this end, we introduce the most comprehensive, large-scale dataset of facial images and videos to date. It consists of 40K still images and 44K sequences (14.5M video frames in total) captured in unconstrained, real-world conditions from 1,045 subjects. The data are manually annotated in terms of identity, exact age, gender and kinship. The performance of state-of-the-art models is scrutinized and demographic bias is exposed by conducting a series of experiments. Lastly, a method to debias network embeddings is introduced and tested on the proposed benchmarks.

cs.CV↗

arXiv2020

Multilinear Latent Conditioning for Generating Unseen Attribute Combinations

Deep generative models rely on their inductive bias to facilitate generalization, especially for problems with high dimensional data, like images. However, empirical studies have shown that variational autoencoders (VAE) and generative adversarial networks (GAN) lack the generalization ability that occurs naturally in human perception. For example, humans can visualize a woman smiling after only seeing a smiling man. On the contrary, the standard conditional VAE (cVAE) is unable to generate unseen attribute combinations. To this end, we extend cVAE by introducing a multilinear latent conditioning framework that captures the multiplicative interactions between the attributes. We implement two variants of our model and demonstrate their efficacy on MNIST, Fashion-MNIST and CelebA. Altogether, we design a novel conditioning framework that can be used with any architecture to synthesize unseen attribute combinations.

cs.LG↗

arXiv2020

Learning Speech Representations from Raw Audio by Joint Audiovisual Self-Supervision

The intuitive interaction between the audio and visual modalities is valuable for cross-modal self-supervised learning. This concept has been demonstrated for generic audiovisual tasks like video action recognition and acoustic scene classification. However, self-supervision remains under-explored for audiovisual speech. We propose a method to learn self-supervised speech representations from the raw audio waveform. We train a raw audio encoder by combining audio-only self-supervision (by predicting informative audio attributes) with visual self-supervision (by generating talking faces from audio). The visual pretext task drives the audio representations to capture information related to lip movements. This enriches the audio encoder with visual information and the encoder can be used for evaluation without the visual modality. Our method attains competitive performance with respect to existing self-supervised audio features on established isolated word classification benchmarks, and significantly outperforms other methods at learning from fewer labels. Notably, our method also outperforms fully supervised training, thus providing a strong initialization for speech related tasks. Our results demonstrate the potential of multimodal self-supervision in audiovisual speech for learning good audio representations.

eess.AS↗

arXiv2020

Enhancing Facial Data Diversity with Style-based Face Aging

A significant limiting factor in training fair classifiers relates to the presence of dataset bias. In particular, face datasets are typically biased in terms of attributes such as gender, age, and race. If not mitigated, bias leads to algorithms that exhibit unfair behaviour towards such groups. In this work, we address the problem of increasing the diversity of face datasets with respect to age. Concretely, we propose a novel, generative style-based architecture for data augmentation that captures fine-grained aging patterns by conditioning on multi-resolution age-discriminative representations. By evaluating on several age-annotated datasets in both single- and cross-database experiments, we show that the proposed method outperforms state-of-the-art algorithms for age transfer, especially in the case of age groups that lie in the tails of the label distribution. We further show significantly increased diversity in the augmented datasets, outperforming all compared methods according to established metrics.

cs.CV↗

arXiv2020

Factorized Higher-Order CNNs with an Application to Spatio-Temporal Emotion Estimation

Training deep neural networks with spatio-temporal (i.e., 3D) or multidimensional convolutions of higher-order is computationally challenging due to millions of unknown parameters across dozens of layers. To alleviate this, one approach is to apply low-rank tensor decompositions to convolution kernels in order to compress the network and reduce its number of parameters. Alternatively, new convolutional blocks, such as MobileNet, can be directly designed for efficiency. In this paper, we unify these two approaches by proposing a tensor factorization framework for efficient multidimensional (separable) convolutions of higher-order. Interestingly, the proposed framework enables a novel higher-order transduction, allowing to train a network on a given domain (e.g., 2D images or N-dimensional data in general) and using transduction to generalize to higher-order data such as videos (or (N+K)-dimensional data in general), capturing for instance temporal dynamics while preserving the learnt spatial information. We apply the proposed methodology, coined CP-Higher-Order Convolution (HO-CPConv), to spatio-temporal facial emotion analysis. Most existing facial affect models focus on static imagery and discard all temporal information. This is due to the above-mentioned burden of training 3D convolutional nets and the lack of large bodies of video data annotated by experts. We address both issues with our proposed framework. Initial training is first done on static imagery before using transduction to generalize to the temporal domain. We demonstrate superior performance on three challenging large scale affect estimation datasets, AffectNet, SEWA, and AFEW-VA.

cs.LG↗

arXiv2020

Toward fast and accurate human pose estimation via soft-gated skip connections

This paper is on highly accurate and highly efficient human pose estimation. Recent works based on Fully Convolutional Networks (FCNs) have demonstrated excellent results for this difficult problem. While residual connections within FCNs have proved to be quintessential for achieving high accuracy, we re-analyze this design choice in the context of improving both the accuracy and the efficiency over the state-of-the-art. In particular, we make the following contributions: (a) We propose gated skip connections with per-channel learnable parameters to control the data flow for each channel within the module within the macro-module. (b) We introduce a hybrid network that combines the HourGlass and U-Net architectures which minimizes the number of identity connections within the network and increases the performance for the same parameter budget. Our model achieves state-of-the-art results on the MPII and LSP datasets. In addition, with a reduction of 3x in model size and complexity, we show no decrease in performance when compared to the original HourGlass network.

cs.CV↗

arXiv2020

Visually Guided Self Supervised Learning of Speech Representations

Self supervised representation learning has recently attracted a lot of research interest for both the audio and visual modalities. However, most works typically focus on a particular modality or feature alone and there has been very limited work that studies the interaction between the two modalities for learning self supervised representations. We propose a framework for learning audio representations guided by the visual modality in the context of audiovisual speech. We employ a generative audio-to-video training scheme in which we animate a still image corresponding to a given audio clip and optimize the generated video to be as close as possible to the real video of the speech segment. Through this process, the audio encoder network learns useful speech representations that we evaluate on emotion recognition and speech recognition. We achieve state of the art results for emotion recognition and competitive results for speech recognition. This demonstrates the potential of visual supervision for learning audio representations as a novel way for self-supervised learning which has not been explored in the past. The proposed unsupervised audio features can leverage a virtually unlimited amount of training data of unlabelled audiovisual speech and have a large number of potentially promising applications.

eess.AS↗

arXiv2020

Speech-driven facial animation using polynomial fusion of features

Speech-driven facial animation involves using a speech signal to generate realistic videos of talking faces. Recent deep learning approaches to facial synthesis rely on extracting low-dimensional representations and concatenating them, followed by a decoding step of the concatenated vector. This accounts for only first-order interactions of the features and ignores higher-order interactions. In this paper we propose a polynomial fusion layer that models the joint representation of the encodings by a higher-order polynomial, with the parameters modelled by a tensor decomposition. We demonstrate the suitability of this approach through experiments on generated videos evaluated on a range of metrics on video quality, audiovisual synchronisation and generation of blinks.

cs.LG↗

arXiv2020

Lipreading using Temporal Convolutional Networks

Lip-reading has attracted a lot of research attention lately thanks to advances in deep learning. The current state-of-the-art model for recognition of isolated words in-the-wild consists of a residual network and Bidirectional Gated Recurrent Unit (BGRU) layers. In this work, we address the limitations of this model and we propose changes which further improve its performance. Firstly, the BGRU layers are replaced with Temporal Convolutional Networks (TCN). Secondly, we greatly simplify the training procedure, which allows us to train the model in one single stage. Thirdly, we show that the current state-of-the-art methodology produces models that do not generalize well to variations on the sequence length, and we addresses this issue by proposing a variable-length augmentation. We present results on the largest publicly-available datasets for isolated word recognition in English and Mandarin, LRW and LRW1000, respectively. Our proposed model results in an absolute improvement of 1.2% and 3.2%, respectively, in these datasets which is the new state-of-the-art performance.

cs.CV↗

arXiv2019

Fast and Effective Adaptation of Facial Action Unit Detection Deep Model

Detecting facial action units (AU) is one of the fundamental steps in automatic recognition of facial expression of emotions and cognitive states. Though there have been a variety of approaches proposed for this task, most of these models are trained only for the specific target AUs, and as such they fail to easily adapt to the task of recognition of new AUs (i.e., those not initially used to train the target models). In this paper, we propose a deep learning approach for facial AU detection that can easily and in a fast manner adapt to a new AU or target subject by leveraging only a few labeled samples from the new task (either an AU or subject). To this end, we propose a modeling approach based on the notion of the model-agnostic meta-learning, originally proposed for the general image recognition/detection tasks (e.g., the character recognition from the Omniglot dataset). Specifically, each subject and/or AU is treated as a new learning task and the model learns to adapt based on the knowledge of the previous tasks (the AUs and subjects used to pre-train the target models). Thus, given a new subject or AU, this meta-knowledge (that is shared among training and test tasks) is used to adapt the model to the new task using the notion of deep learning and model-agnostic meta-learning. We show on two benchmark datasets (BP4D and DISFA) for facial AU detection that the proposed approach can be easily adapted to new tasks (AUs/subjects). Using only a few labeled examples from these tasks, the model achieves large improvements over the baselines (i.e., non-adapted models).

cs.CV↗

arXiv2019

Incremental multi-domain learning with network latent tensor factorization

The prominence of deep learning, large amount of annotated data and increasingly powerful hardware made it possible to reach remarkable performance for supervised classification tasks, in many cases saturating the training sets. However the resulting models are specialized to a single very specific task and domain. Adapting the learned classification to new domains is a hard problem due to at least three reasons: (1) the new domains and the tasks might be drastically different; (2) there might be very limited amount of annotated data on the new domain and (3) full training of a new model for each new task is prohibitive in terms of computation and memory, due to the sheer number of parameters of deep CNNs. In this paper, we present a method to learn new-domains and tasks incrementally, building on prior knowledge from already learned tasks and without catastrophic forgetting. We do so by jointly parametrizing weights across layers using low-rank Tucker structure. The core is task agnostic while a set of task specific factors are learnt on each new domain. We show that leveraging tensor structure enables better performance than simply using matrix operations. Joint tensor modelling also naturally leverages correlations across different layers. Compared with previous methods which have focused on adapting each layer separately, our approach results in more compact representations for each new task/domain. We apply the proposed method to the 10 datasets of the Visual Decathlon Challenge and show that our method offers on average about 7.5x reduction in number of parameters and competitive performance in terms of both classification accuracy and Decathlon score.

cs.CV↗

arXiv2019

SEWA DB: A Rich Database for Audio-Visual Emotion and Sentiment Research in the Wild

Natural human-computer interaction and audio-visual human behaviour sensing systems, which would achieve robust performance in-the-wild are more needed than ever as digital devices are increasingly becoming an indispensable part of our life. Accurately annotated real-world data are the crux in devising such systems. However, existing databases usually consider controlled settings, low demographic variability, and a single task. In this paper, we introduce the SEWA database of more than 2000 minutes of audio-visual data of 398 people coming from six cultures, 50% female, and uniformly spanning the age range of 18 to 65 years old. Subjects were recorded in two different contexts: while watching adverts and while discussing adverts in a video chat. The database includes rich annotations of the recordings in terms of facial landmarks, facial action units (FAU), various vocalisations, mirroring, and continuously valued valence, arousal, liking, agreement, and prototypic examples of (dis)liking. This database aims to be an extremely valuable resource for researchers in affective computing and automatic human sensing and is expected to push forward the research in human behaviour analysis, including cultural studies. Along with the database, we provide extensive baseline experiments for automatic FAU detection and automatic valence, arousal and (dis)liking intensity estimation.

cs.HC↗

arXiv2019

Towards Pose-invariant Lip-Reading

Lip-reading models have been significantly improved recently thanks to powerful deep learning architectures. However, most works focused on frontal or near frontal views of the mouth. As a consequence, lip-reading performance seriously deteriorates in non-frontal mouth views. In this work, we present a framework for training pose-invariant lip-reading models on synthetic data instead of collecting and annotating non-frontal data which is costly and tedious. The proposed model significantly outperforms previous approaches on non-frontal views while retaining the superior performance on frontal and near frontal mouth views. Specifically, we propose to use a 3D Morphable Model (3DMM) to augment LRW, an existing large-scale but mostly frontal dataset, by generating synthetic facial data in arbitrary poses. The newly derived dataset, is used to train a state-of-the-art neural network for lip-reading. We conducted a cross-database experiment for isolated word recognition on the LRS2 dataset, and reported an absolute improvement of 2.55%. The benefit of the proposed approach becomes clearer in extreme poses where an absolute improvement of up to 20.64% over the baseline is achieved.

cs.CV↗