Variational Laws of Visual Attention for Dynamic Scenes The authors investigate what locations in static and dynamic images tend to be attended to by humans. They derive a model by first defining three basic principles for visual attention (defined as an energy function to be minimized by the movements of the eye): (1) Eye movements are constrained by a harmonic oscillator at the borders of the image within a limited-sized retina. Using a cost function derived from these three functions, the authors derive differential equations for predicting the eye movements across static or dynamic images (depending on the starting location and initial velocity). The authors evaluate their technique quantitatively on data sets of static and dynamic scenes coupled with human eye movements. They demonstrate that their method performs comparable to the state-of-the-art.

We propose to apply a 2D CNN architecture to 3D MRI image Alzheimer's disease classification. Training a 3D convolutional neural network (CNN) is time-consuming and computationally expensive. We make use of approximate rank pooling to transform the 3D MRI image volume into a 2D image to use as input to a 2D CNN. We show our proposed CNN model achieves $9.5\%$ better Alzheimer's disease classification accuracy than the baseline 3D models. We also show that our method allows for efficient training, requiring only 20% of the training time compared to 3D CNN models. The code is available online: https://github.com/UkyVision/alzheimer-project.

Correctly perceiving micro-expression is difficult since micro-expression is an involuntary, repressed, and subtle facial expression, and efficiently revealing the subtle movement changes and capturing the significant segments in a micro-expression sequence is the key to micro-expression recognition (MER). To handle the crucial issue, in this paper, we firstly propose a dynamic segmented sparse imaging module (DSSI) to compute dynamic images as local-global spatiotemporal descriptors under a unique sampling protocol, which reveals the subtle movement changes visually in an efficient way. Secondly, a segmented movement-attending spatiotemporal network (SMA-STN) is proposed to further unveil imperceptible small movement changes, which utilizes a spatiotemporal movement-attending module (STMA) to capture long-distance spatial relation for facial expression and weigh temporal segments. Besides, a deviation enhancement loss (DE-Loss) is embedded in the SMA-STN to enhance the robustness of SMA-STN to subtle movement changes in feature level. Extensive experiments on three widely used benchmarks, i.e., CASME II, SAMM, and SHIC, show that the proposed SMA-STN achieves better MER performance than other state-of-the-art methods, which proves that the proposed method is effective to handle the challenging MER problem.

We are interested in learning models of intuitive physics similar to the ones that animals use for navigation, manipulation and planning. In addition to learning general physical principles, however, we are also interested in learning ``on the fly'', from a few experiences, physical properties specific to new environments. We do all this in an unsupervised manner, using a meta-learning formulation where the goal is to predict videos containing demonstrations of physical phenomena, such as objects moving and colliding with a complex background. We introduce the idea of summarizing past experiences in a very compact manner, in our case using dynamic images, and show that this can be used to solve the problem well and efficiently. Empirically, we show via extensive experiments and ablation studies, that our model learns to perform physical predictions that generalize well in time and space, as well as to a variable number of interacting physical objects.

In this paper we present an end-to-end deep learning framework to turn images that show dynamic content, such as vehicles or pedestrians, into realistic static frames. This objective encounters two main challenges: detecting the dynamic objects, and inpainting the static occluded background. The second challenge is approached with a conditional generative adversarial model that, taking as input the original dynamic image and the computed dynamic/static binary mask, is capable of generating the final static image. The former challenge is addressed by the use of a convolutional network that learns a multi-class semantic segmentation of the image. The objective of this network is producing an accurate segmentation and helping the previous generative model to output a realistic static image. These generated images can be used for applications such as virtual reality or vision-based robot localization purposes. To validate our approach, we show both qualitative and quantitative comparisons against other inpainting methods by removing the dynamic objects and hallucinating the static structure behind them. Furthermore, to demonstrate the potential of our results, we conduct pilot experiments showing the benefits of our proposal for visual place recognition. Code has been made available on https://github.com/bertabescos/EmptyCities.

A novel deep neural network training paradigm that exploits the conjoint information in multiple heterogeneous sources is proposed. Specifically, in a RGB-D based action recognition task, it cooperatively trains a single convolutional neural network (named c-ConvNet) on both RGB visual features and depth features, and deeply aggregates the two kinds of features for action recognition. Differently from the conventional ConvNet that learns the deep separable features for homogeneous modality-based classification with only one softmax loss function, the c-ConvNet enhances the discriminative power of the deeply learned features and weakens the undesired modality discrepancy by jointly optimizing a ranking loss and a softmax loss for both homogeneous and heterogeneous modalities. The ranking loss consists of intra-modality and cross-modality triplet losses, and it reduces both the intra-modality and cross-modality feature variations. Furthermore, the correlations between RGB and depth data are embedded in the c-ConvNet, and can be retrieved by either of the modalities and contribute to the recognition in the case even only one of the modalities is available. The proposed method was extensively evaluated on two large RGB-D action recognition datasets, ChaLearn LAP IsoGD and NTU RGB+D datasets, and one small dataset, SYSU 3D HOI, and achieved state-of-the-art results.