Abstract: One of the most widely used assumptions in supervised learning is that data is independent and identically distributed. This assumption does not hold true in many real cases. Sequential learning is the discipline of machine learning that deals with dependent data such that neighboring examples exhibit some kind of relationship. In the literature, there are different approaches that try to capture and exploit this correlation, by means of different methodologies. In this paper we focus on meta-learning strategies and, in particular, the stacked sequential learning approach. The main contribution of this work is two-fold: first, we generalize the stacked sequential learning. This generalization reflects the key role of neighboring interactions modeling. Second, we propose an effective and efficient way of capturing and exploiting sequential correlations that takes into account long-range interactions by means of a multi-scale pyramidal decomposition of the predicted labels. Additionally, this new method subsumes the standard stacked sequential learning approach. We tested the proposed method on two different classification tasks: text lines classification in a FAQ data set and image classification. Results on these tasks clearly show that our approach outperforms the standard stacked sequential learning. Moreover, we show that the proposed method allows to control the trade-off between the detail and the desired range of the interactions.

Abstract: This article presents a GPU-accelerated software design of the recently proposed model of Slanted Stixels, which represents the geometric and semantic information of a scene in a compact and accurate way. We reformulate the measurement depth model to reduce the computational complexity of the algorithm, relying on the confidence of the depth estimation and the identification of invalid values to handle outliers. The proposed massively parallel scheme and data layout for the irregular computation pattern that corresponds to a Dynamic Programming paradigm is described and carefully analyzed in performance terms. Performance is shown to scale gracefully on current generation embedded GPUs. We assess the proposed methods in terms of semantic and geometric accuracy as well as run-time performance on three publicly available benchmark datasets. Our approach achieves real-time performance with high accuracy for 2048 × 1024 image sizes and 4 × 4 Stixel resolution on the low-power embedded GPU of an NVIDIA Tegra Xavier.

Abstract: Computational color constancy is a fundamental prerequisite for many computer vision applications. This paper presents a survey of many recent developments and state-of-the- art methods. Several criteria are proposed that are used to assess the approaches. A taxonomy of existing algorithms is proposed and methods are separated in three groups: static methods, gamut-based methods and learning-based methods. Further, the experimental setup is discussed including an overview of publicly available data sets. Finally, various freely available methods, of which some are considered to be state-of-the-art, are evaluated on two data sets.

Abstract: In open-ended domains, robots must continuously learn new object categories. When the training sets are created offline, it is not possible to ensure their representativeness with respect to the object categories and features the system will find when operating online. In the Bag of Words model, visual codebooks are constructed from training sets created offline. This might lead to non-discriminative visual words and, as a consequence, to poor recognition performance. This paper proposes a visual object recognition system which concurrently learns in an incremental and online fashion both the visual object category representations as well as the codebook words used to encode them. The codebook is defined using Gaussian Mixture Models which are updated using new object views. The approach contains similarities with the human visual object recognition system: evidence suggests that the development of recognition capabilities occurs on multiple levels and is sustained over large periods of time. Results show that the proposed system with concurrent learning of object categories and codebooks is capable of learning more categories, requiring less examples, and with similar accuracies, when compared to the classical Bag of Words approach using offline constructed codebooks.

Abstract: In this paper we propose the first deep unsupervised approach in human body reconstruction to estimate body surface from a sparse set of landmarks, so called DeepMurf. We apply a denoising autoencoder to estimate missing landmarks. Then we apply an attention model to estimate body joints from landmarks. Finally, a cascading network is applied to regress parameters of a statistical generative model that reconstructs body. Our set of proposed loss functions allows us to train the network in an unsupervised way. Results on four public datasets show that our approach accurately reconstructs the human body from real world mocap data.

Abstract: This article addresses the problems of word spotting and word recognition on images. In word spotting, the goal is to find all instances of a query word in a dataset of images. In recognition, the goal is to recognize the content of the word image, usually aided by a dictionary or lexicon. We describe an approach in which both word images and text strings are embedded in a common vectorial subspace. This is achieved by a combination of label embedding and attributes learning, and a common subspace regression. In this subspace, images and strings that represent the same word are close together, allowing one to cast recognition and retrieval tasks as a nearest neighbor problem. Contrary to most other existing methods, our representation has a fixed length, is low dimensional, and is very fast to compute and, especially, to compare. We test our approach on four public datasets of both handwritten documents and natural images showing results comparable or better than the state-of-the-art on spotting and recognition tasks.

Abstract: Deep learning for human action recognition in videos is making significant progress, but is slowed down by its dependency on expensive manual labeling of large video collections. In this work, 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 introduce a deep multi-task representation learning architecture to mix synthetic and real videos, even if the action categories differ. Our experiments on the UCF101 and HMDB51 benchmarks suggest that combining our large set of synthetic videos with small real-world datasets can boost recognition performance, significantly
outperforming fine-tuning state-of-the-art unsupervised generative models of videos.