Read by QxMD icon Read

IEEE Transactions on Pattern Analysis and Machine Intelligence

Pau Panareda Busto, Ahsan Iqbal, Juergen Gall
Since annotating and curating large datasets is very expensive, there is a need to transfer the knowledge from existing annotated datasets to unlabelled data. Data that is relevant for a specific application, however, usually differs from publicly available datasets since it is sampled from a different domain. While domain adaptation methods compensate for such a domain shift, they assume that all categories in the target domain are known and match the categories in the source domain. Since this assumption is violated under real-world conditions, we propose an approach for open set domain adaptation where the target domain contains instances of categories that are not present in the source domain...
November 12, 2018: IEEE Transactions on Pattern Analysis and Machine Intelligence
Feng Liu, Tao Xiang, Timothy M Hospedales, Wankou Yang, Changyin Sun
In this paper we propose the inverse problem of VQA (iVQA). The iVQA task is to generate a question that corresponds to a given image and answer pair. We propose a variational iVQA model that can generate diverse, grammatically correct and content correlated questions that match the given answer. Based on this model, we show that iVQA is an interesting benchmark for visuo-linguistic understanding, and a more challenging alternative to VQA because an iVQA model needs to understand the image better to be successful...
November 9, 2018: IEEE Transactions on Pattern Analysis and Machine Intelligence
Julia Vinogradska, Bastian Bischoff, Jan Achterhold, Torsten Koller, Jan Peters
Learning control policies has become an appealing alternative to the derivation of control laws based on classic control theory. Model-based approaches have proven an outstanding data efficiency, especially when combined with probabilistic models to eliminate model bias. However, a major difficulty for these methods is that multi-step-ahead predictions typically become intractable for larger planning horizons and can only poorly be approximated. In this paper, we propose the use of numerical quadrature to overcome this drawback and provide significantly more accurate multi-step-ahead predictions...
November 2, 2018: IEEE Transactions on Pattern Analysis and Machine Intelligence
Miguel A A Ferrer, Moises Diaz, Cristina A Carmona, Rejean Plamondon
The Kinematic Theory of rapid movements and its associated Sigma-Lognormal model have been extensively used in a large variety of applications. While the physical and biological meaning of the model have been widely tested and validated for rapid movements, some shortcomings have been detected when it is used with continuous long and complex movements. To alleviate such drawbacks, and inspired by the motor equivalence theory and a conceivable visual feedback, this paper proposes a novel framework to extract the Sigma-Lognormal parameters, namely iDeLog...
November 2, 2018: IEEE Transactions on Pattern Analysis and Machine Intelligence
Xinwang Liu, Xinzhong Zhu, Miaomiao Li, Lei Wang, Chang Tang, Jianping Yin, Dinggang Shen, Huaimin Wang, Wen Gao
Incomplete multi-view clustering optimally integrates a group of pre-specified incomplete views to improve clustering performance. Among various excellent solutions, multiple kernel -means with incomplete kernels forms a benchmark, which redefines the incomplete multi-view clustering as a joint optimization problem where the imputation and clustering are alternately performed until convergence. However, the comparatively intensive computational and storage complexities preclude it from practical applications...
November 1, 2018: IEEE Transactions on Pattern Analysis and Machine Intelligence
Jianwen Xie, Yang Lu, Ruiqi Gao, Song-Chun Zhu, Ying Nian Wu
This paper studies the cooperative learning of two generative models. Both models are parametrized by ConvNets. The first model is a deep energy-based model, whose energy function is defined by a bottom-up ConvNet, which maps the observed image to the energy. We call it the descriptor network. The second model is a generator network, which is defined by a top-down ConvNet, which maps the latent factors to the observed image. The maximum likelihood learning algorithms of both models involve MCMC sampling such as Langevin dynamics...
November 1, 2018: IEEE Transactions on Pattern Analysis and Machine Intelligence
Seong Joon Oh, Rodrigo Benenson, Mario Fritz, Bernt Schiele
People nowadays share large parts of their personal lives through social media. Being able to automatically recognise people in personal photos may greatly enhance user convenience by easing photo album organisation. For human identification task, however, traditional focus of computer vision has been face recognition and pedestrian re-identification. Person recognition in social media photos sets new challenges for computer vision, including non-cooperative subjects (e.g. backward viewpoints, unusual poses) and great changes in appearance...
November 1, 2018: IEEE Transactions on Pattern Analysis and Machine Intelligence
Yun Liu, Ming-Ming Cheng, Xiaowei Hu, Jia-Wang Bian, Le Zhang, Xiang Bai, Jinhui Tang
Edge detection is a fundamental problem in computer vision. Recently, convolutional neural networks (CNNs) have pushed forward this field significantly. Existing methods which adopt specific layers of deep CNNs may fail to capture complex data structures caused by variations of scales and aspect ratios. In this paper, we propose an accurate edge detector using richer convolutional features (RCF). RCF encapsulates all convolutional features into more discriminative representation, which makes good usage of rich feature hierarchies, and is amenable to training via backpropagation...
October 31, 2018: IEEE Transactions on Pattern Analysis and Machine Intelligence
Mahmudul Hasan, Sujoy Paul, Anastasios I Mourikis, Amit K Roy-Chowdhury
Activity recognition is a challenging problem with many practical applications. In addition to the visual features, recent approaches got benefited from the use of context e.g., interrelationships among the activities and objects. However, these approaches require data to be labeled, entirely available beforehand, and not designed to be updated continuously, which make them unsuitable for surveillance applications. In contrast, we propose a continuous-learning framework for context-aware activity recognition from unlabeled video, which has two distinct advantages over existing methods...
October 30, 2018: IEEE Transactions on Pattern Analysis and Machine Intelligence
Yongming Rao, Jiwen Lu, Ji Lin, Jie Zhou
In this paper, we propose a generic Runtime Network Routing (RNR) framework for efficient image classification, which selects an optimal path inside the network. Unlike existing static neural network acceleration methods, our method preserves the full ability of the original large network and conducts dynamic routing at runtime according to the input image and current feature maps. The routing is performed in a bottom-up, layer-by-layer manner, where we model it as a Markov decision process and use reinforcement learning for training...
October 26, 2018: IEEE Transactions on Pattern Analysis and Machine Intelligence
Seungryong Kim, Dongbo Min, Stephen Lin, Kwanghoon Sohn
Techniques for dense semantic correspondence have provided limited ability to deal with the geometric variations that commonly exist between semantically similar images. While variations due to scale and rotation have been examined, there is a lack of practical solutions for more complex deformations such as affine transformations because of the tremendous size of the associated solution space. To address this problem, we present a discrete-continuous transformation matching (DCTM) framework where dense affine transformation fields are inferred through a discrete label optimization in which the labels are iteratively updated via continuous regularization...
October 26, 2018: IEEE Transactions on Pattern Analysis and Machine Intelligence
Ravi Kiran Sarvadevabhatla, Shiv Surya, Trisha Mittal, Venkatesh Babu Radhakrishnan
The ability of intelligent agents to play games in human-like fashion is popularly considered a benchmark of progress in Artificial Intelligence. Similarly, performance on multi-disciplinary tasks such as Visual Question Answering (VQA) is considered a marker for gauging progress in Computer Vision. In our work, we bring games and multi-disciplinary tasks together. Specifically, we introduce the first computational model aimed at Pictionary, the popular word-guessing social game. We first introduce Sketch-QA...
October 25, 2018: IEEE Transactions on Pattern Analysis and Machine Intelligence
Gil Shamai, Michael Zibulevsky, Ron Kimmel
Multidimensional scaling (MDS) is a dimensionality reduction tool used for information analysis, data visualization and manifold learning. Most MDS procedures embed data points in low-dimensional Euclidean (flat) domains, such that distances between the points are as close as possible to given inter-point dissimilarities. We present an efficient solver for classical scaling, a specific MDS model, by extrapolating the information provided by distances measured from a subset of the points to the remainder. The computational and space complexities of the new MDS methods are thereby reduced from quadratic to quasi-linear in the number of data points...
October 25, 2018: IEEE Transactions on Pattern Analysis and Machine Intelligence
Lu Sheng, Jianfei Cai, Tat-Jen Cham, Vladimir Pavlovic, KingNgi Ngan
In this paper, we propose a generative framework that unifies depth-based 3D facial pose tracking and face model adaptation on-the-fly, in the unconstrained scenarios with heavy occlusions and arbitrary facial expression variations. Specifically, we introduce a statistical 3D morphable model that flexibly describes the distribution of points on the surface of the face model, with an efficient switchable online adaptation that gradually captures the identity of the tracked subject and rapidly constructs a suitable face model when the subject changes...
October 23, 2018: IEEE Transactions on Pattern Analysis and Machine Intelligence
Changqing Zhang, Huazhu Fu, Qinghua Hu, Xiaochun Cao, Yuan Xie, Dacheng Tao, Dong Xu
Subspace clustering is an effective method that has been successfully applied to many applications. Here we propose a novel subspace clustering model for multi-view data using a latent representation termed Latent Multi-View Subspace Clustering (LMSC). Unlike most existing single-view subspace clustering methods, which directly reconstruct data points using original features, our method explores underlying complementary information from multiple views and simultaneously seeks the underlying latent representation...
October 23, 2018: IEEE Transactions on Pattern Analysis and Machine Intelligence
Ayush Tewari, Michael Zollhoefer, Florian Bernard, Pablo Garrido, Hyeongwoo Kim, Patrick Perez, Christian Theobalt
In this work we propose a novel model-based deep convolutional autoencoder that addresses the highly challenging problem of reconstructing a 3D human face from a single in-the-wild color image. To this end, we combine a convolutional encoder network with an expert-designed generative model that serves as decoder. The core innovation is the differentiable parametric decoder that encapsulates image formation analytically based on a generative model. Our decoder takes as input a code vector with exactly defined semantic meaning that encodes detailed face pose, shape, expression, skin reflectance and scene illumination...
October 18, 2018: IEEE Transactions on Pattern Analysis and Machine Intelligence
Zhibin Liao, Tom Drummond, Ian Reid, Gustavo Carneiro
In this paper, we introduce a novel methodology for characterising the performance of deep learning networks (ResNets and DenseNet) with respect to training convergence and generalisation as a function of mini-batch size and learning rate for image classification. This methodology is based on novel measurements derived from the eigenvalues of the approximate Fisher information matrix, which can be efficiently computed even for high capacity deep models. Our proposed measurements can help practitioners to monitor and control the training process (by actively tuning the mini-batch size and learning rate) to allow for good training convergence and generalisation...
October 16, 2018: IEEE Transactions on Pattern Analysis and Machine Intelligence
Biao Zhang, Deyi Xiong, Jinsong Su
Deepening neural models has been proven very successful in improving the model's capacity when solving complex learning tasks, such as the machine translation task. Previous efforts on deep neural machine translation mainly focus on the encoder and the decoder, while little on the attention mechanism. However, the attention mechanism is of vital importance to induce the translation correspondence between different languages where shallow neural networks are relatively insufficient, especially when the encoder and decoder are deep...
October 16, 2018: IEEE Transactions on Pattern Analysis and Machine Intelligence
Peng Tang, Xinggang Wang, Song Bai, Wei Shen, Xiang Bai, Wenyu Liu, Alan Loddon Yuille
Weakly Supervised Object Detection (WSOD), using only image-level annotations to train object detectors, is of growing importance in object recognition. In this paper, we propose a novel deep network for WSOD. Unlike previous networks that transfer the object detection problem to an image classification problem using Multiple Instance Learning (MIL), our strategy generates proposal clusters to learn refined instance classifiers by an iterative process. The proposals in the same cluster are spatially adjacent and associated with the same object...
October 16, 2018: IEEE Transactions on Pattern Analysis and Machine Intelligence
Margret Keuper, Siyu Tang, Bjorn Andres, Thomas Brox, Bernt Schiele
Models for computer vision are commonly defined either w.r.t. low-level concepts such as pixels that are to be grouped, or w.r.t. high-level concepts such as semantic objects that are to be detected and tracked. Combining bottom-up grouping with top-down detection and tracking, although highly desirable, is a challenging problem. We state this joint problem as a co-clustering problem that is principled and tractable by existing algorithms. We demonstrate the effectiveness of this approach by combining bottom-up motion segmentation by grouping of point trajectories with high-level multiple object tracking by clustering of bounding boxes...
October 16, 2018: IEEE Transactions on Pattern Analysis and Machine Intelligence
Fetch more papers »
Fetching more papers... Fetching...
Read by QxMD. Sign in or create an account to discover new knowledge that matter to you.
Remove bar
Read by QxMD icon Read

Search Tips

Use Boolean operators: AND/OR

diabetic AND foot
diabetes OR diabetic

Exclude a word using the 'minus' sign

Virchow -triad

Use Parentheses

water AND (cup OR glass)

Add an asterisk (*) at end of a word to include word stems

Neuro* will search for Neurology, Neuroscientist, Neurological, and so on

Use quotes to search for an exact phrase

"primary prevention of cancer"
(heart or cardiac or cardio*) AND arrest -"American Heart Association"