Search

In recent years, the convolutional segmentation network has achieved remarkable performance in the computer vision area. However, training a practicable segmentation network is time- and resource-consuming. In this paper, focusing on the semantic image segmentation task, we attempt to disassemble a convolutional segmentation network into category-aware convolution kernels and achieve customizable tasks without additional training by utilizing those kernels. The core of disassembling convolutional segmentation networks is how to identify the relevant convolution kernels for a specific category. According to the encoder-decoder network architecture, the disassembling framework, named Disassembler, is devised to be composed of the forward channel-wise activation attribution and backward gradient attribution. In the forward channel-wise activation attribution process, for each image, the activation values of each feature map in the high-confidence mask area are summed into category-aware probability vectors. In the backward gradient attribution process, the positive gradients w.r.t. each feature map in the high-confidence mask area are summed into a relative coefficient vector for each category. With the cooperation of two vectors, the Disassembler can effectively disassemble category-aware convolution kernels. Extensive experiments demonstrate that the proposed Disassembler can accomplish the category-customizable task without additional training. The disassembled category-aware sub-network achieves comparable performance without any finetuning and will outperform existing state-of-the-art methods with one epoch of finetuning. [ABSTRACT FROM AUTHOR]

Image-based nondestructive textile fiber identification is a challenging computer vision problem, that is practically useful in fashion, decoration, and design. Although deep learning now outperforms humans in many scenarios such as face and object recognition, image-based fiber identification is still an open problem for deep learning given imbalanced sample and small sample size samples. In this paper, we propose the Component Unmixing Network (CU-Net) for nondestructive textile fiber identification. CU-Net learns effective representations given imbalanced sample and small sample size samples to achieve high-performance textile fiber identification. CU-Net comprises a Deep Feature Extraction Module (DFE-Module) and a Component Unmixing Module (CU-Module). Initially, mixed deep features are extracted by DFE-Module from the input textile patches. Then, CU-Module is employed to extract unmixed representations of different fibers from the mixed deep features. In CU-Module, we introduce a self-interchange and a restraining loss to reduce the mixture between representations of different fibers. Furthermore, we extend CU-Net to the proportion analysis task with very good effect. Extensive experiments demonstrate that: (1) self-interchange and the restraining loss effectively unmix different fiber representations and improve fiber identification accuracy; and (2) CU-Net achieves more accurate fiber identification than the current state-of-the-art multi-label classification methods. [ABSTRACT FROM AUTHOR]

Recent advances in object detection have led to the development of segmentation by detection approaches that integrate top-down geometric priors for multiclass object segmentation. A key yet under-addressed issue in utilizing top-down cues for the problem of multiclass object segmentation by detection is efficiently generating robust and accurate geometric priors. In this paper, we propose a random geometric prior forest scheme to obtain object-adaptive geometric priors efficiently and robustly. In the scheme, a testing object first searches for training neighbors with similar geometries using the random geometric prior forest, and then the geometry of the testing object is reconstructed by linearly combining the geometries of its neighbors. Our scheme enjoys several favorable properties when compared with conventional methods. First, it is robust and very fast because its inference does not suffer from bad initializations, poor local minimums or complex optimization. Second, the figure/ground geometries of training samples are utilized in a multitask manner. Third, our scheme is object-adaptive but does not require the labeling of parts or poselets, and thus, it is quite easy to implement. To demonstrate the effectiveness of the proposed scheme, we integrate the obtained top-down geometric priors with conventional bottom-up color cues in the frame of graph cut. The proposed random geometric prior forest achieves the best segmentation results of all of the methods tested on VOC2010/2012 and is 90 times faster than the current state-of-the-art method. [ABSTRACT FROM PUBLISHER]

Eye detection plays an important role in many practical applications. This paper presents a novel two-step scheme for eye detection. The first step models an eye by a newly defined visual-context pattern (VCP), and the second step applies semisupervised boosting for precise detection. VCP describes both the space and appearance relations between an eye region (region of eye) and a reference region (region of reference). The context feature of a VCP is extracted by using the integral image. Aiming to reduce the human labeling efforts, we apply semisupervised boosting, which integrates the context feature and the Haar-like features for precise eye detection. Experimental results on several standard face data sets demonstrate that the proposed approach is effective, robust, and efficient. We finally show that this approach is ready for practical applications. [ABSTRACT FROM AUTHOR]

Vision transformers have achieved remarkable success in computer vision tasks by using multi-head self-attention modules to capture long-range dependencies within images. However, the high inference computation cost poses a new challenge. Several methods have been proposed to address this problem, mainly by slimming patches. In the inference stage, these methods classify patches into two classes, one to keep and the other to discard in multiple layers. This approach results in additional computation at every layer where patches are discarded, which hinders inference acceleration. In this study, we tackle the patch slimming problem from a different perspective by proposing a life regression module that determines the lifespan of each image patch in one go. During inference, the patch is discarded once the current layer index exceeds its life. Our proposed method avoids additional computation and parameters in multiple layers to enhance inference speed while maintaining competitive performance. Additionally, our approach 1 1 https://github.com/cjwcommuny/life-regression. requires fewer training epochs than other patch slimming methods. [ABSTRACT FROM AUTHOR]

Object detection is one of the core tasks in computer vision that serves as a crucial underpinning for numerous applications. In recent years, deep learning-based methods have achieved remarkable performance in object detection. However, the performance of small objects still remains unsatisfactory. Therefore, some specific architectures have been proposed to address this issue in certain areas, such as remote-sensing and UAV images. In this paper, we aim to design a pluggable and non-intrusive method, termed as PatchDetector, to improve the performance of small object detection, which can effectively avoid the time and resource overhead of retraining the entire network. To achieve that, we first analyze why the mainstream networks perform poorly on small objects and find out that the fundamental reason is that the features of small are superseded by the background, which leads to a significant semantic gap in multi-level layers. Then, significance analysis is conducted to find the essential features for improving the small object detection. Next, with the located significant features, we devise a pluggable patch network for extracting essential features for small objects, which is non-intrusive to the original network. Experiments on mainstream detectors, including YOLO series and Faster RCNN, show that the proposed PatchDetector achieves 0. 4 % ∼ 2. 0 % mAP on small objects while not compromising the performance of medium and large objects. • The first pluggable and non-intrusive patch for small object detection performance. • We analyze the small object poor performance and locate the essential features. • Experiments demonstrate that the PatchDetector achieves 0. 4 % ∼ 2. 0 % mAP on small object. [ABSTRACT FROM AUTHOR]

Abstract: Human action recognition has been an active topic in computer vision. Currently, most of the approaches to this problem can be categorized into two classes. One is based on local features, and the other is based on global features. Meanwhile, manifold learning has become successful in many problems in computer vision, but because of the high variability of human body, the application of manifold learning to human action recognition is limited. We propose a framework based on Elastic Manifold Embedding (EME), a new sparse manifold learning algorithm, together with local interest point features to handle human action recognition. The result of the new framework is very promising in comparison with state-of-the-art methods. [Copyright &y& Elsevier]

Abstract: Motion deblurring is a challenging problem in computer vision. Most previous blind deblurring approaches usually assume that the Point Spread Function (PSF) is spatially invariant. However, non-uniform motions exist ubiquitously and cannot be handled successfully. In this paper, we present an automatic method for object motion deblurring based on non-uniform motion information from video. First, the feature points of the object are tracked throughout a video sequence. Then, the object motion between frames is estimated and the circular blurring paths (i.e. PSFs) of each point are computed along the linear moving path in polar coordinates. Finally, an alpha matte of the blurred object is extracted to separate the foreground from the background, and an iterative Richardson–Lucy algorithm is carried out on the foreground using the obtained blurring paths. Experimental results show our proposed approach outperforms the state-of-the-art motion deblurring algorithms. [Copyright &y& Elsevier]

Recent advances in sensor manufacture and computer vision technologies have simulated the applications of intelligent transportation systems, while a key yet under-addressed issue in these systems is the semantic summarization of large scale surveillance video. The main difficulty of large scale surveillance video summarization arises from the contradiction between the high-degree spatiotemporal redundancies and the limited storage budget. In this paper, we propose a novel approach of large scale surveillance video summarization on the basis of event detection. In the proposed approach, we firstly obtain the trajectories of vehicles and pedestrians in a tracking-by-detection manner, and then detect the abnormal events using the trajectories. Finally, we design a disjoint max-coverage algorithm to generate a summarized sequence with maximum coverage of interested events and minimum number of frames. Compared with traditional key frame-based approaches, our approach enjoys the following favorable features. First, important information can be efficiently extracted from the redundant contents since the approach is event-centric and those interested events contain almost all the important information. Second, abnormal events are successfully detected by combining the Random Forest classifier and the trajectory features. Third, the abnormal events are designed to display, and hence further reduces the compression ratio. Due to the above features, the proposed approach is suitable for different scenarios, ranges from highway to crowded crossings. Experiments on 12 surveillance sequences validate the effectiveness and efficiency of the proposed approach. [ABSTRACT FROM AUTHOR]

Abstract: With the popularity of cameras and rapid development of computer vision technology, vision-based HCI is attracting extensive interests. In this paper, we present a system for controlling avatars by natural body movement via a single web-camera. A pose database and a set of color markers are utilized to make ill-posed vision problem tractable for real game applications. Based on the proposed algorithms for indexing pose samples and estimating human pose, we build a prototype system that is responsive, easy to manipulate and runs automatically in real time. User study shows that the system is user-friendly and provides immersive experiences. [Copyright &y& Elsevier]