Published in IEEE transactions on pattern analysis and machine intelligence
The ability to predict, anticipate and reason about future outcomes is a key component of intelligent decision-making systems. In light of the success of deep learning in computer vision, deep-learning-based video prediction emerged as a promising research direction. Defined as a self-supervised learning task, video prediction represents a suitable...
Published in IEEE transactions on pattern analysis and machine intelligence
Capturing the 'mutual gaze' of people is essential for understanding and interpreting the social interactions between them. To this end, this paper addresses the problem of detecting people Looking At Each Other (LAEO) in video sequences. For this purpose, we propose LAEO-Net++, a new deep CNN for determining LAEO in videos. In contrast to previous...
Published in IEEE transactions on pattern analysis and machine intelligence
Full projector compensation aims to modify a projector input image to compensate for both geometric and photometric disturbance of the projection surface. Traditional methods usually solve the two parts separately and may suffer from suboptimal solutions. In this paper, we propose the first end-to-end differentiable solution, named CompenNeSt++, to...
Published in IEEE transactions on pattern analysis and machine intelligence
This paper aims to build a supervised classifier for dealing with imbalanced datasets, uncertain class proportions, dependencies between features, the presence of both numeric and categorical features, and arbitrary loss functions. The Bayes classifier suffers when prior probability shifts occur between the training and testing sets. A solution is ...
Published in IEEE transactions on pattern analysis and machine intelligence
Deep neural models, in recent years, have been successful in almost every field, even solving the most complex problem statements. However, these models are huge in size with millions (and even billions) of parameters, demanding heavy computation power and failing to be deployed on edge devices. Besides, the performance boost is highly dependent on...
Published in IEEE transactions on pattern analysis and machine intelligence
The principal rank-one (RO) components of an image represent the self-similarity of the image, which is an important property for image restoration. However, the RO components of a corrupted image could be decimated by the procedure of image denoising. We suggest that the RO property should be utilized and the decimation should be avoided in image ...
Published in IEEE transactions on pattern analysis and machine intelligence
We propose scene graph auto-encoder (SGAE) that incorporates the language inductive bias into the encoder-decoder image captioning framework for more human-like captions. Intuitively, we humans use the inductive bias to compose collocations and contextual inferences in discourse. For example, when we see the relation "a person on a bike", it is nat...
Published in IEEE transactions on pattern analysis and machine intelligence
Finding a small set of representatives from an unlabeled dataset is a core problem in a broad range of applications such as dataset summarization and information extraction. Classical exemplar selection methods such as k-medoids work under the assumption that the data points are close to a few cluster centroids, and cannot handle the case where dat...
Published in IEEE transactions on pattern analysis and machine intelligence
When demonstrating the effectiveness of a new algorithm, researchers are traditionally encouraged to compare their algorithm's performance against existing algorithms on well-studied benchmark test suites. In the absence of more nuanced methodologies, algorithm performance is typically summarized on average across the test suite examples. This pape...
Published in IEEE transactions on pattern analysis and machine intelligence
Multi-scale representations deeply learned via convolutional neural networks have shown tremendous importance for various pixel-level prediction problems. In this paper we present a novel approach that advances the state of the art on pixel-level prediction in a fundamental aspect, i.e. structured multi-scale features learning and fusion. In contra...
