The following shape segmentation problem is addressed: find the part decomposition of a 3D object that accounts for an observed pattern of similarities among several of the object's views. This represents the inve...
详细信息
The following shape segmentation problem is addressed: find the part decomposition of a 3D object that accounts for an observed pattern of similarities among several of the object's views. This represents the inverse, ill-posed version of the direct problem of computing perceptual similarities among object views when the object parts are known. The problem is solved by inverting a proposed model for the direct similarity-from-parts problem by resorting to regularization techniques. The algorithm takes as input the geometry of the object (given as a triangular mesh), the camera positions corresponding to the test views, and the perceptual similarities among the rest views. The output of the algorithm is a segmentation of the surface of the object hto connected regions, i.e., parts.
In this paper, we propose a compact frame-based facial expression recognition framework for facial expression recognition which achieves very competitive performance with respect to state-of-the-art methods while usin...
详细信息
ISBN:
(数字)9781538661000
ISBN:
(纸本)9781538661000
In this paper, we propose a compact frame-based facial expression recognition framework for facial expression recognition which achieves very competitive performance with respect to state-of-the-art methods while using much less parameters. The proposed framework is extended to a frame-to-sequence approach by exploiting temporal information with gated recurrent units. In addition, we develop an illumination augmentation scheme to alleviate the over-fitting problem when training the deep networks with hybrid data sources. Finally, we demonstrate the performance improvement by using the proposed technique on some public datasets.
Face recognition (FR) is the most preferred mode for biometric-based surveillance, due to its passive nature of detecting subjects, amongst all different types of biometric traits. FR under surveillance scenario does ...
详细信息
ISBN:
(纸本)9781509014378
Face recognition (FR) is the most preferred mode for biometric-based surveillance, due to its passive nature of detecting subjects, amongst all different types of biometric traits. FR under surveillance scenario does not give satisfactory performance due to low contrast, noise and poor illumination conditions on probes, as compared to the training samples. A state-of-the-art technology, Deep Learning, even fails to perform well in these scenarios. We propose a novel soft-margin based learning method for multiple feature-kernel combinations, followed by feature transformed using Domain Adaptation, which outperforms many recent state-of-the-art techniques, when tested using three real-world surveillance face datasets.
Image deblurring and super-resolution (SR) are computervision tasks aiming to restore image detail and spatial scale, respectively. Besides, only a few recent works of literature contribute to this task, as conventio...
详细信息
ISBN:
(纸本)9781665448994
Image deblurring and super-resolution (SR) are computervision tasks aiming to restore image detail and spatial scale, respectively. Besides, only a few recent works of literature contribute to this task, as conventional methods deal with SR or deblurring separately. We focus on designing a novel Pixel-Guided dual-branch attention network (PDAN) that handles both tasks jointly to address this issue. Then, we propose a novel loss function better focus on large and medium range errors. Extensive experiments demonstrated that the proposed PDAN with the novel loss function not only generates remarkably clear HR images and achieves compelling results for joint image deblurring and SR tasks. In addition, our method achieves second place in NTIRE 2021 Challenge on track 1 of the Image Deblurring Challenge.
A family of structure from motion algorithms called the factorization method has been recently developed from the orthographic projection model to the affine camera model [23, 16, 18]. All these algorithms are limited...
详细信息
ISBN:
(纸本)0818672587
A family of structure from motion algorithms called the factorization method has been recently developed from the orthographic projection model to the affine camera model [23, 16, 18]. All these algorithms are limited to handling only point features of the image stream. We propose in this paper an algorithm for the recovery of shape and motion from line correspondences by the factorization method with the affine camera. Instead of one step factorization for points, a multi-step factorization method is developed for lines based on the decomposition of the whole shape and motion into three separate substructures. Each of these substructures can then be linearly solved by factorizating the appropriate measurement matrices. It is also established that affine shape and motion with uncalibrated affine cameras can be achieved with at least seven lines over three views, which extends the previous results of Koenderink and Van Doorn [9] for points to lines.
In this paper, we study deep transfer learning as a way of overcoming object recognition challenges encountered in the field of digital pathology. Through several experiments, we investigate various uses of pre-traine...
详细信息
ISBN:
(数字)9781538661000
ISBN:
(纸本)9781538661000
In this paper, we study deep transfer learning as a way of overcoming object recognition challenges encountered in the field of digital pathology. Through several experiments, we investigate various uses of pre-trained neural network architectures and different combination schemes with random forests for feature selection. Our experiments on eight classification datasets show that densely connected and residual networks consistently yield best performances across strategies. It also appears that network fine-tuning and using inner layers features are the best performing strategies, with the former yielding slightly superior results.
We described a system for detection and description of buildings in aerial scenes. This is a difficult task as the aerial images contain a variety of objects. Low-level segmentation processes give highly fragmented se...
详细信息
ISBN:
(纸本)0818658258
We described a system for detection and description of buildings in aerial scenes. This is a difficult task as the aerial images contain a variety of objects. Low-level segmentation processes give highly fragmented segments due to a number of reasons. We use a perceptual grouping approach to collect these fragments and discard those that come from other sources. We use shape properties of the buildings for this. We use shadows to help form and verify the hypotheses generated by the grouping process. This latter step also provides 3-D descriptions of the buildings. Our system has been tested on a number of examples and is able to work with overhead or oblique views.
This paper introduces our approach to the EmotioNet Challenge 2020. We pose the AU recognition problem as a multi-task learning problem, where the non-rigid facial muscle motion (mainly the first 17 AUs) and the rigid...
详细信息
ISBN:
(数字)9781728193601
ISBN:
(纸本)9781728193601
This paper introduces our approach to the EmotioNet Challenge 2020. We pose the AU recognition problem as a multi-task learning problem, where the non-rigid facial muscle motion (mainly the first 17 AUs) and the rigid head motion (the last 6 AUs) are modeled separately. The co-occurrence of the expression features and the head pose features are explored. We observe that different AUs converge at various speed. By choosing the optimal checkpoint for each AU, the recognition results are improved. We are able to obtain a final score of 0.746 in validation set and 0.7306 in the test set of the challenge.
We offer a novel strategy to adapt the perceptual organization process to an object and its context in a scene. Given a set of training images of an object in context, a learning process decides on the relative import...
详细信息
ISBN:
(纸本)0818684976
We offer a novel strategy to adapt the perceptual organization process to an object and its context in a scene. Given a set of training images of an object in context, a learning process decides on the relative importance of the basic Gestalt relationships such as proximity, parallelness, similarity. symmetry, closure, and common region towards segregating the object from the background. This learning is accomplished using a team of stochastic automata in a N-player cooperative game framework. The grouping process which is based on graph partitioning is able to form large groups from relationships defined over a small set of primitives and is fast. We demonstrate the robust performance of the grouping system on a variety of real images. Among the interesting conclusions is the significant role of photometric attributes in grouping and the ability to perform figure-ground segmentation from a set of local relations, each defined over a small number of primitives.
Shadow removal is an important computervision task aiming at the detection and successful removal of the shadow produced by an occluded light source and a photorealistic restoration of the image contents. Decades of ...
详细信息
ISBN:
(纸本)9781665448994
Shadow removal is an important computervision task aiming at the detection and successful removal of the shadow produced by an occluded light source and a photorealistic restoration of the image contents. Decades of research produced a multitude of hand-crafted restoration techniques and, more recently, learned solutions from shadowed and shadow free training image pairs. In this work, we propose a single image shadow removal solution via self-supervised learning by using a conditioned mask. We rely on self-supervision and jointly learn deep models to remove and add shadows to images. We derive two variants for learning from paired images and unpaired images, respectively. Our validation on the recently introduced ISTD and USR datasets demonstrate large quantitative and qualitative improvements over the state-of-the-art for both paired and unpaired learning settings.
暂无评论