Audiovisual representation learning typically relies on the correspondence between sight and sound. However, there are often multiple audio tracks that can correspond with a visual scene. Consider, for example, different con-versations on the same crowded street. The effect of such counterfactual pairs on audiovisual representation learning has not been previously explored. To investigate this, we use dubbed versions of movies and television shows to augment cross-modal contrastive learning. Our approach learns to represent alternate audio tracks, differing only in speech, similarly to the same video. Our results, from a comprehensive set of experiments investigating different training strategies, show this general approach improves performance on a range of downstream auditory and audio-visual tasks, without majorly affecting linguistic task per-formance overall. These findings highlight the importance of considering speech variation when learning scene-level audiovisual correspondences and suggest that dubbed au-dio can be a useful augmentation technique for training au-diovisual models toward more robust performance on di-verse downstream tasks.

Attributes are semantically meaningful characteristics whose applicability widely crosses category boundaries. They are particularly important in describing and recognizing concepts for which no explicit training example is given, e.g., zero-shot learning. Additionally, since attributes are human describable, they can be used for efficient human-computer interaction. In this article, we propose to employ semantic segmentation to improve person-related attribute prediction. The core idea lies in the fact that many attributes describe local properties. In other words, the probability of an attribute to appear in an image is far from being uniform in the spatial domain. We build our attribute prediction model jointly with a deep semantic segmentation network. This harnesses the localization cues learned by the semantic segmentation to guide the attention of the attribute prediction to the regions where different attributes naturally show up. As a result of this approach, in addition to prediction, we are able to localize the attributes despite merely having access to image-level labels (weak supervision) during training. We first propose semantic segmentation-based pooling and gating, respectively denoted as SSP and SSG. In the former, the estimated segmentation masks are used to pool the final activations of the attribute prediction network, from multiple semantically homogeneous regions. This is in contrast to global average pooling which is agnostic with respect to where in the spatial domain activations occur. In SSG, the same idea is applied to the intermediate layers of the network. Specifically, we create multiple copies of the internal activations. In each copy, only values that fall within a certain semantic region are preserved while outside of that, activations are suppressed. This mechanism allows us to prevent pooling operation from blending activations that are associated with semantically different regions. SSP and SSG, while effective, impose heavy memory utilization since each channel of the activations is pooled/gated with all the semantic segmentation masks. To circumvent this, we propose Symbiotic Augmentation (SA), where we learn only one mask per activation channel. SA allows the model to either pick one, or combine (weighted superposition) multiple semantic maps, in order to generate the proper mask for each channel. SA simultaneously applies the same mechanism to the reverse problem by leveraging output logits of attribute prediction to guide the semantic segmentation task. We evaluate our proposed methods for facial attributes on CelebA and LFWA datasets, while benchmarking WIDER Attribute and Berkeley Attributes of People for whole body attributes. Our proposed methods achieve superior results compared to the previous works. Furthermore, we show that in the reverse problem, semantic face parsing significantly improves when its associated task is jointly learned, through our proposed Symbiotic Augmentation (SA), with facial attribute prediction. We confirm that when few training instances are available, indeed image-level facial attribute labels can serve as an effective source of weak supervision to improve semantic face parsing. That reaffirms the need to jointly model these two interconnected tasks.

Batch Normalization (BN) is essential to effectively train state-of-the-art deep Convolutional Neural Networks (CNN). It normalizes the layer outputs during training using the statistics of each mini-batch. BN accelerates training procedure by allowing to safely utilize large learning rates and alleviates the need for careful initialization of the parameters. In this work, we study BN from the viewpoint of Fisher kernels that arise from generative probability models. We show that assuming samples within a mini-batch are from the same probability density function, then BN is identical to the Fisher vector of a Gaussian distribution. That means batch normalizing transform can be explained in terms of kernels that naturally emerge from the probability density function that models the generative process of the underlying data distribution. Consequently, it promises higher discrimination power for the batch-normalized mini-batch. However, given the rectifying non-linearities employed in CNN architectures, distribution of the layer outputs show an asymmetric characteristic. Therefore, in order for BN to fully benefit from the aforementioned properties, we propose approximating underlying data distribution not with one, but a mixture of Gaussian densities. Deriving Fisher vector for a Gaussian Mixture Model (GMM), reveals that batch normalization can be improved by independently normalizing with respect to the statistics of disentangled sub-populations. We refer to our proposed soft piecewise version of batch normalization as Mixture Normalization (MN). Through extensive set of experiments on CIFAR-10 and CIFAR-100, using both a 5-layers deep CNN and modern Inception-V3 architecture, we show that mixture normalization reduces required number of gradient updates to reach the maximum test accuracy of the batch-normalized model by ∼ 31%-47% across a variety of training scenarios. Replacing even a few BN modules with MN in the 48-layers deep Inception-V3 architecture is sufficient to not only obtain considerable training acceleration but also better final test accuracy. We show that similar observations are valid for 40 and 100-layers deep DenseNet architectures as well. We complement our study by evaluating the application of mixture normalization to the Generative Adversarial Networks (GANs), where "mode collapse" hinders the training process. We solely replace a few batch normalization layers in the generator with our proposed mixture normalization. Our experiments using Deep Convolutional GAN (DCGAN) on CIFAR-10 show that mixture-normalized DCGAN not only provides an acceleration of ∼ 58% but also reaches lower (better) "Fréchet Inception Distance" (FID) of 33.35 compared to 37.56 of its batch-normalized counterpart.

Person re-identification is a challenging task mainly due to factors such as background clutter, pose, illumination and camera point of view variations. These elements hinder the process of extracting robust and discriminative representations, hence preventing different identities from being successfully distinguished. To improve the representation learning, usually local features from human body parts are extracted. However, the common practice for such a process has been based on bounding box part detection. In this paper, we propose to adopt human semantic parsing which, due to its pixel-level accuracy and capability of modeling arbitrary contours, is naturally a better alternative. Our proposed SPReID integrates human semantic parsing in person re-identification and not only considerably outperforms its counter baseline, but achieves state-of-the-art performance. We also show that, by employing a simple yet effective training strategy, standard popular deep convolutional architectures such as Inception-V3 and ResNet-152, with no modification, while operating solely on full image, can dramatically outperform current state-of-the-art. Our proposed methods improve state-of-the-art person re-identification on: Market-1501 [48] by ~17% in mAP and ~6% in rank-1, CUHK03 [24] by ~4% in rank-1 and DukeMTMC-reID [50] by ~24% in mAP and ~10% in rank-1.

Selfies are now a global phenomenon. This massive number of self-portrait images taken and shared on social media is revolutionizing the way people introduce themselves and the circle of their friends to the world. While taking photos of oneself can be seen simply as recording personal memories, the urge to share them with other people adds an exclusive sensation to the selfies. Due to the Big Data nature of selfies, it is nearly impossible to analyze them manually. In this paper, we provide, to the best of our knowledge, the first selfie dataset for research purposes with more than 46,000 images. We address interesting questions about selfies, including how appearance of certain objects, concepts and attributes influences the popularity of selfies. We also study the correlation between popularity and sentiment in selfie images. In a nutshell, from a large scale dataset, we automatically infer what makes a selfie a good selfie. We believe that this research creates new opportunities for social, psychological and behavioral scientists to study selfies from a large scale point of view, a perspective that best fits the nature of the selfie phenomenon.

While approaches based on bags of features excel at low-level action classification, they are ill-suited for recognizing complex events in video, where concept-based temporal representations currently dominate. This paper proposes a novel representation that captures the temporal dynamics of windowed mid-level concept detectors in order to improve complex event recognition. We first express each video as an ordered vector time series, where each time step consists of the vector formed from the concatenated confidences of the pre-trained concept detectors. We hypothesize that the dynamics of time series for different instances from the same event class, as captured by simple linear dynamical system (LDS) models, are likely to be similar even if the instances differ in terms of low-level visual features. We propose a two-part representation composed of fusing: (1) a singular value decomposition of block Hankel matrices (SSID-S) and (2) a harmonic signature (HS) computed from the corresponding eigen-dynamics matrix. The proposed method offers several benefits over alternate approaches: our approach is straightforward to implement, directly employs existing concept detectors and can be plugged into linear classification frameworks. Results on standard datasets such as NIST's TRECVID Multimedia Event Detection task demonstrate the improved accuracy of the proposed method.

The real world image databases such as Flickr are characterized by continuous addition of new images. The recent approaches for image annotation, i.e. the problem of assigning tags to images, have two major drawbacks. First, either models are learned using the entire training data, or to handle the issue of dataset imbalance, tag-specific discriminative models are trained. Such models become obsolete and require relearning when new images and tags are added to database. Second, the task of feature-fusion is typically dealt using ad-hoc approaches. In this paper, we present a weighted extension of Multi-view Non-negative Matrix Factorization (NMF) to address the aforementioned drawbacks. The key idea is to learn query-specific generative model on the features of nearest-neighbors and tags using the proposed NMF-KNN approach which imposes consensus constraint on the coefficient matrices across different features. This results in coefficient vectors across features to be consistent and, thus, naturally solves the problem of feature fusion, while the weight matrices introduced in the proposed formulation alleviate the issue of dataset imbalance. Furthermore, our approach, being query-specific, is unaffected by addition of images and tags in a database. We tested our method on two datasets used for evaluation of image annotation and obtained competitive results.

In medical imaging, the gold standard for image-quality assessment is a task-based approach in which one evaluates human observer performance for a given diagnostic task (e.g., detection of a myocardial perfusion or motion defect). To facilitate practical task-based image-quality assessment, model observers are needed as approximate surrogates for human observers. In cardiac-gated SPECT imaging, diagnosis relies on evaluation of the myocardial motion as well as perfusion. Model observers for the perfusion-defect detection task have been studied previously, but little effort has been devoted toward development of a model observer for cardiac-motion defect detection. In this work, we describe two model observers for predicting human observer performance in detection of cardiac-motion defects. Both proposed methods rely on motion features extracted using previously reported deformable mesh model for myocardium motion estimation. The first method is based on a Hotelling linear discriminant that is similar in concept to that used commonly for perfusion-defect detection. In the second method, based on relevance vector machines (RVM) for regression, we compute average human observer performance by first directly predicting individual human observer scores, and then using multi reader receiver operating characteristic analysis. Our results suggest that the proposed RVM model observer can predict human observer performance accurately, while the new Hotelling motion-defect detector is somewhat less effective.

This paper introduces a novel sparse Bayesian machine-learning algorithm for embedded feature selection in classification tasks. Our proposed algorithm, called the relevance sample feature machine (RSFM), is able to simultaneously choose the relevance samples and also the relevance features for regression or classification problems. We propose a separable model in feature and sample domains. Adopting a Bayesian approach and using Gaussian priors, the learned model by RSFM is sparse in both sample and feature domains. The proposed algorithm is an extension of the standard RVM algorithm, which only opts for sparsity in the sample domain. Experimental comparisons on synthetic as well as benchmark data sets show that RSFM is successful in both feature selection (eliminating the irrelevant features) and accurate classification. The main advantages of our proposed algorithm are: less system complexity, better generalization and avoiding overfitting, and less computational cost during the testing stage.