Abstract: The authors present a novel methodology for analyzing integrated audiovisual signals and language to assess a persons personality. An evaluation of their proposed multimodal method using a job candidate screening system that predicted five personality traits from a short video demonstrates the methods effectiveness.

Abstract: In this dissertation, we explore different ways to perform human action recognition in video clips. We focus on data efficiency, proposing new approaches that alleviate the need for laborious and time-consuming manual data annotation. In the first part of this dissertation, we start by analyzing previous state-of-the-art models, comparing their differences and similarities in order to pinpoint where their real strengths come from. Leveraging this information, we then proceed to boost the classification accuracy of shallow models to levels that rival deep neural networks. We introduce hybrid video classification architectures based on carefully designed unsupervised representations of handcrafted spatiotemporal features classified by supervised deep networks. We show in our experiments that our hybrid model combine the best of both worlds: it is data efficient (trained on 150 to 10,000 short clips) and yet improved significantly on the state of the art, including deep models trained on millions of manually labeled images and videos. In the second part of this research, we investigate the generation of synthetic training data for action recognition, as it has recently shown promising results for a variety of other computer vision tasks. We propose an interpretable parametric generative model of human action videos that relies on procedural generation and other computer graphics techniques of modern game engines. We generate a diverse, realistic, and physically plausible dataset of human action videos, called PHAV for “Procedural Human Action Videos”. It contains a total of 39,982 videos, with more than 1,000 examples for each action of 35 categories. Our approach is not limited to existing motion capture sequences, and we procedurally define 14 synthetic actions. We then introduce deep multi-task representation learning architectures to mix synthetic and real videos, even if the action categories differ. Our experiments on the UCF-101 and HMDB-51 benchmarks suggest that combining our large set of synthetic videos with small real-world datasets can boost recognition performance, outperforming fine-tuning state-of-the-art unsupervised generative models of videos.

Abstract: We address the problem of image translation between domains or modalities for which no direct paired data is available (i.e. zero-pair translation). We propose mix and match networks, based on multiple encoders and decoders aligned in such a way that other encoder-decoder pairs can be composed at test time to perform unseen image translation tasks between domains or modalities for which explicit paired samples were not seen during training. We study the impact of autoencoders, side information and losses in improving the alignment and transferability of trained pairwise translation models to unseen translations. We show our approach is scalable and can perform colorization and style transfer between unseen combinations of domains. We evaluate our system in a challenging cross-modal setting where semantic segmentation is estimated from depth images, without explicit access to any depth-semantic segmentation training pairs. Our model outperforms baselines based on pix2pix and CycleGAN models.

Abstract: Person re-identification has received special attention by the human analysis community in the last few years. To address the challenges in this field, many researchers have proposed different strategies, which basically exploit either cross-view invariant features or cross-view robust metrics. In this work, we propose to exploit a post-ranking approach and combine different feature representations through ranking aggregation. Spatial information, which potentially benefits the person matching, is represented using a 2D body model, from which color and texture information are extracted and combined. We also consider background/foreground information, automatically extracted via Deep Decompositional Network, and the usage of Convolutional Neural Network (CNN) features. To describe the matching between images we use the polynomial feature map, also taking into account local and global information. The Discriminant Context Information Analysis based post-ranking approach is used to improve initial ranking lists. Finally, the Stuart ranking aggregation method is employed to combine complementary ranking lists obtained from different feature representations. Experimental results demonstrated that we improve the state-of-the-art on VIPeR and PRID450s datasets, achieving 67.21% and 75.64% on top-1 rank recognition rate, respectively, as well as obtaining competitive results on CUHK01 dataset.

Abstract: Visual impairment affects the normal course of activities in everyday life including mobility, education, employment, and social interaction. Most of the existing technical solutions devoted to empowering the visually impaired people are in the areas of navigation (obstacle avoidance), access to printed information and object recognition. Less effort has been dedicated so far in developing solutions to support social interactions. In this paper, we introduce a Social-Aware Assistant (SAA) that provides visually impaired people with cues to enhance their face-to-face conversations. The system consists of a perceptive component (represented by smartglasses with an embedded video camera) and a feedback component (represented by a haptic belt). When the vision system detects a head nodding, the belt vibrates, thus suggesting the user to replicate (mirror) the gesture. In our experiments, sighted persons interacted with blind people wearing the SAA. We instructed the former to mirror the noddings according to the vibratory signal, while the latter interacted naturally. After the face-to-face conversation, the participants had an interview to express their experience regarding the use of this new technological assistant. With the data collected during the experiment, we have assessed quantitatively and qualitatively the device usefulness and user satisfaction.

Abstract: The color appearance of a surface depends on the color of its surroundings (inducers). When the perceived color shifts towards that of the surroundings, the effect is called “color assimilation” and when it shifts away from the surroundings it is called “color contrast.” There is also evidence that the phenomenon depends on the spatial configuration of the inducer, e.g., uniform surrounds tend to induce color contrast and striped surrounds tend to induce color assimilation. However, previous work found that striped surrounds under certain conditions do not induce color assimilation but induce color contrast (or do not induce anything at all), suggesting that luminance differences and high spatial frequencies could be key factors in color assimilation. Here we present a new psychophysical study of color assimilation where we assessed the contribution of luminance differences (between the target and its surround) present in striped stimuli. Our results show that luminance differences are key factors in color assimilation for stimuli varying along the s axis of MacLeod-Boynton color space, but not for stimuli varying along the l axis. This asymmetry suggests that koniocellular neural mechanisms responsible for color assimilation only contribute when there is a luminance difference, supporting the idea that mutual-inhibition has a major role in color induction.

Abstract: In this paper we propose an approach for multi-modal image retrieval in multi-labelled images. A multi-modal deep network architecture is formulated to jointly model sketches and text as input query modalities into a common embedding space, which is then further aligned with the image feature space. Our architecture also relies on a salient object detection through a supervised LSTM-based visual attention model learned from convolutional features. Both the alignment between the queries and the image and the supervision of the attention on the images are obtained by generalizing the Hungarian Algorithm using different loss functions. This permits encoding the object-based features and its alignment with the query irrespective of the availability of the co-occurrence of different objects in the training set. We validate the performance of our approach on standard single/multi-object datasets, showing state-of-the art performance in every dataset.