Showing papers in "Image and Vision Computing in 2014"

TL;DR: Becauseposedandun-posed(aka "spontaneous") facialexpressionsdifferalong severaldimensions includingcomplexity andtiming, well-annotated video of un-posedfacialbehavior is needed.

TL;DR: The problem of person re-identification is explored and open issues and challenges of the problem are highlighted with a discussion on potential directions for further research.

TL;DR: Avoiding the use of complicated pre-processing steps such as accurate face and body part segmentation or image normalization, this paper proposes a novel face/person image representation which can properly handle background and illumination variations called gBiCov.

TL;DR: The co-occurrence between face and body helps to handle large variations, such as heavy occlusions, to further boost the face detection performance, and the hierarchical part based structural model is proposed to explicitly capture them.

TL;DR: The finding that automatic facial expression analysis was both consistent with manual coding and revealed the same pattern of findings suggests that automatic Facial expression analysis may be ready to relieve the burden of manual coding in behavioral and clinical science.

TL;DR: A detailed review of recent advances in visual speech decoding, focusing on the important questions asked by researchers and summarize the recent studies that attempt to answer them, and providing details of audio-visual speech databases.

TL;DR: FRIME (Face and Iris Recognition for Mobile Engagement) is described as a biometric application based on a multimodal recognition of face and iris, which is designed to be embedded in mobile devices and optimized to be low-demanding and computation-light.

TL;DR: The analysis shows that for matching frontal faces in still images, algorithms are consistently superior to humans, and for video and difficult still face pairs, humans are superior.

TL;DR: This paper evaluates the spatiotemporal interest point (STIP) based features for depth-based action recognition, and investigates a fusion of the best STIP features with the prevalent skeleton features, to present a complementary use of the STip features for action recognition on 3D data.

TL;DR: A number of nonverbal behavior descriptors that can be automatically estimated from audiovisual signals are proposed that could be used to support healthcare providers with quantified and objective observations that could ultimately improve clinical assessment.

TL;DR: The proposed discriminative dictionary learning with low-rank regularization (D2L2R2) approach is evaluated on four face and digit image datasets in comparison with existing representative dictionary learning and classification algorithms and demonstrates the superiority of the approach.

TL;DR: It is found that the canonical correlation analysis (CCA) based methods can derive an extremely low dimensionality in estimating age, gender and ethnicity.

TL;DR: A novel method is proposed that performs accurate gaze estimation without restricting the user's head motion by decomposing the original free-head motion problem into subproblems, including an initial fixed head pose problem and subsequent compensations to correct the initial estimation biases.

TL;DR: A novel stereo matching algorithm is presented that ranks the 10th among about 152 algorithms on the Middlebury stereo evaluation benchmark, and takes the 1st place in all local methods.

TL;DR: This work extends the idea of detecting facial expressions through 'concept frames' to 'concept segments' and argues through extensive experiments that algorithms such as MIL are needed to reap the benefits of such representation and demonstrates that MS-MIL yields a significant improvement on another spontaneous facial expression dataset, the FEEDTUM dataset.

TL;DR: An iterative optimization algorithm is proposed that obtains model parameters that best reproduce ToF measurements, recovering the depth of the scene without distortion and accurately corrects the multipath distortion, obtaining depth maps that are very close to ground truth data.

TL;DR: This paper proposes a direct approach that takes into account the image as a whole, and considers a similarity measure, the mutual information, which allows the method to deal with different image modalities (real and synthetic).

TL;DR: Transformed Grassmannian robust adaptive subspace tracking algorithm (t-GRASTA) as mentioned in this paper iteratively performs incremental gradient descent constrained to the Grassmann manifold of subspaces to estimate three components of a decomposition of a collection of images: a low-rank subspace, a sparse part of occlusions and foreground objects, and a transformation such as rotation or translation of the image.

TL;DR: Comparison of the two smile detection algorithms showed that improved smile detection helps correctly classify responses recorded in challenging lighting conditions and those in which the expressions were subtle, showed that temporal discriminative approaches to classification performed most strongly showing that temporal information about an individual's response is important.

TL;DR: A new constraint is introduced into AAM fitting that uses depth data from a commodity RGBD camera (Kinect) that significantly reduces 3D tracking errors and describes how to initialize the 3D morphable face model used in the tracking algorithm by computing its face shape parameters of the user from a batch of tracked frames.

TL;DR: This paper proposes a new method to extract a gait feature from a raw gait video directly using the Space-Time Interest Points (STIPs) to enhance the SVM-based gait classification.

TL;DR: A mathematical framework for obtaining the rotation, scaling and translation invariants of these two types of radial shifted Legendre moments is provided and the superiority of the proposed methods in terms of image reconstruction capability and invariant recognition accuracy under both noisy and noise-free conditions is shown.

TL;DR: An unsupervised distance learning approach for improving the effectiveness of image retrieval tasks by proposing a Reciprocal kNN Graph algorithm that considers the relationships among ranked lists in the context of a k-reciprocal neighborhood.

TL;DR: A novel solution for the problem of segmenting macro- and micro-expression frames (or retrieving the expression intervals) in video sequences, which is a prior step for many expression recognition algorithms is proposed.

TL;DR: A new computational phonetic modeling framework for sign language (SL) recognition based on dynamic-static statistical subunits and provides sequentiality in an unsupervised manner, without prior linguistic information is introduced.

TL;DR: A novel tracking method tailored to dense crowds is proposed which provides an alternative and complementary approach to methods that require modeling of crowd flow and is less likely to fail in the case of dynamic crowd flows and anomalies by minimally relying on previous frames.

TL;DR: A novel sparse feature selection framework for web image annotation, namely sparse Feature Selection based on Graph Laplacian (FSLG) is proposed, which applies the l"2","1"/"2-matrix norm into the sparse features selection algorithm to select the most sparse and discriminative features.

TL;DR: Novel work on autonomously identifying Safe Landing Zones (SLZs) which can be utilised upon occurrence of a safety critical event is presented and results are presented based on colour aerial imagery captured during manned flight demonstrating practical potential in the methods discussed.

TL;DR: It is shown that inter-session variability modelling using Gaussian mixture models provides a consistently robust system for face, speaker and bi-modal authentication and that multi-algorithm fusion provides a consistent performance improvement for face and speaker authentication.

TL;DR: An effective and efficient approach is presented by combining both boosted local texture and shape features extracted from 3D face models, in contrast to the existing ones that only depend on either 2D texture or 3D shape of faces, to improve results in gender and ethnicity classification.