In the last two years, convolutional neural networks (CNNs) have achieved an impressive suite of results on standard recognition datasets and tasks. CNN-based features seem poised to quickly replace engineered representations, such as SIFT and HOG. However, compared to SIFT and HOG, we understand much less about the nature of the features learned by large CNNs. In this paper, we experimentally probe several aspects of CNN feature learning in an attempt to help practitioners gain useful, evidence-backed intuitions about how to apply CNNs to computer vision problems.
Jadavpur University（jadavpur大学）；Tripura University (A Central University)（特里普拉大学（中央大学））
Artificial neural networks have already shown their success in face recognition and similar complex pattern recognition tasks. However, a major disadvantage of the technique is that it is extremely slow during training for larger classes and hence not suitable for real-time complex problems such as pattern recognition. This is an attempt to develop a parallel framework for the training algorithm of a perceptron. In this paper, two general architectures for a Multilayer Perceptron (MLP) have been demonstrated. The first architecture is All-Class-in-One-Network (ACON) where all the classes are p…
This paper presents a novel approach to handle the challenges of face recognition. In this work thermal face images are considered, which minimizes the affect of illumination changes and occlusion due to moustache, beards, adornments etc. The proposed approach registers the training and testing thermal face images in polar coordinate, which is capable to handle complicacies introduced by scaling and rotation. Polar images are projected into eigenspace and finally classified using a multi-layer perceptron. In the experiments we have used Object Tracking and Classification Beyond Visible Spectru…
Ulm University（乌尔姆大学）；Otto von Guericke University Magdeburg（马格德堡奥托·冯·格里克大学）
Gesture recognition is essential for the interaction of autonomous vehicles with humans. While the current approaches focus on combining several modalities like image features, keypoints and bone vectors, we present neural network architecture that delivers state-of-the-art results only with body skeleton input data. We propose the spatio-temporal multilayer perceptron for gesture recognition in the context of autonomous vehicles. Given 3D body poses over time, we define temporal and spatial mixing operations to extract features in both domains. Additionally, the importance of each time step i…
Institute of Technology, Nirma University（尼尔玛大学理工学院）
Human action recognition involves the characterization of human actions through the automated analysis of video data and is integral in the development of smart computer vision systems. However, several challenges like dynamic backgrounds, camera stabilization, complex actions, occlusions etc. make action recognition in a real time and robust fashion difficult. Several complex approaches exist but are computationally intensive. This paper presents a novel approach of using a combination of good features along with iterative optical flow algorithm to compute feature vectors which are classified…
In this paper we present a simple novel approach to tackle the challenges of scaling and rotation of face images in face recognition. The proposed approach registers the training and testing visual face images by log-polar transformation, which is capable to handle complicacies introduced by scaling and rotation. Log-polar images are projected into eigenspace and finally classified using an improved multi-layer perceptron. In the experiments we have used ORL face database and Object Tracking and Classification Beyond Visible Spectrum (OTCBVS) database for visual face images. Experimental resul…
Faculty of Engineering & Technology, Mody Institute of Technology & Science（Mody科技与科学学院工程与技术系）
The biggest challenge in the field of image processing is to recognize documents both in printed and handwritten format. Optical Character Recognition OCR is a type of document image analysis where scanned digital image that contains either machine printed or handwritten script input into an OCR software engine and translating it into an editable machine readable digital text format. A Neural network is designed to model the way in which the brain performs a particular task or function of interest: The neural network is simulated in software on a digital computer. Character Recognition refers …
University of São Paulo（圣保罗大学）；University of Campinas（坎皮纳斯大学）
Convolutional neural networks have shown successful results in image classification achieving real-time results superior to the human level. However, texture images still pose some challenge to these models due, for example, to the limited availability of data for training in several problems where these images appear, high inter-class similarity, the absence of a global viewpoint of the object represented, and others. In this context, the present paper is focused on improving the accuracy of convolutional neural networks in texture classification. This is done by extracting features from mult…
One of the most arduous and captivating domains under image processing is handwritten character recognition. In this paper we have proposed a feature extraction technique which is a combination of unique features of geometric, zone-based hybrid, gradient features extraction approaches and three different neural networks namely the Multilayer Perceptron network using Backpropagation algorithm (MLP BP), the Multilayer Perceptron network using Levenberg-Marquardt algorithm (MLP LM) and the Convolutional neural network (CNN) which have been implemented along with the Minimum Distance Classifier (M…
This work presents an analysis of the efficiency of image augmentations for the face recognition problem from limited data. We considered basic manipulations, generative methods, and their combinations for augmentations. Our results show that augmentations, in general, can considerably improve the quality of face recognition systems and the combination of generative and basic approaches performs better than the other tested techniques.
This paper presents a concept of image pixel fusion of visual and thermal faces, which can significantly improve the overall performance of a face recognition system. Several factors affect face recognition performance including pose variations, facial expression changes, occlusions, and most importantly illumination changes. So, image pixel fusion of thermal and visual images is a solution to overcome the drawbacks present in the individual thermal and visual face images. Fused images are projected into eigenspace and finally classified using a multi-layer perceptron. In the experiments we ha…
This paper presents a novel hierarchical spatiotemporal orientation representation for spacetime image analysis. It is designed to combine the benefits of the multilayer architecture of ConvNets and a more controlled approach to spacetime analysis. A distinguishing aspect of the approach is that unlike most contemporary convolutional networks no learning is involved; rather, all design decisions are specified analytically with theoretical motivations. This approach makes it possible to understand what information is being extracted at each stage and layer of processing as well as to minimize h…
Rich semantic relations are important in a variety of visual recognition problems. As a concrete example, group activity recognition involves the interactions and relative spatial relations of a set of people in a scene. State of the art recognition methods center on deep learning approaches for training highly effective, complex classifiers for interpreting images. However, bridging the relatively low-level concepts output by these methods to interpret higher-level compositional scenes remains a challenge. Graphical models are a standard tool for this task. In this paper, we propose a method …
Samsung Research America（三星美国研究院）；University of Notre Dame（圣母大学）
In this article, we analyze how changing the underlying 3D shape of the base identity in face images can distort their overall appearance, especially from the perspective of deep face recognition. As done in popular training data augmentation schemes, we graphically render real and synthetic face images with randomly chosen or best-fitting 3D face models to generate novel views of the base identity. We compare deep features generated from these images to assess the perturbation these renderings introduce into the original identity. We perform this analysis at various degrees of facial yaw with…
Meghnad Saha Institute of Technology（梅格纳德·萨哈技术学院）；Jadavpur University（贾达普大学）
In this paper a scheme for offline Handwritten Devnagari Character Recognition is proposed, which uses different feature extraction methodologies and recognition algorithms. The proposed system assumes no constraints in writing style or size. First the character is preprocessed and features namely : Chain code histogram and moment invariant features are extracted and fed to Multilayer Perceptrons as a preliminary recognition step. Finally the results of both MLP's are combined using weighted majority scheme. The proposed system is tested on 1500 handwritten devnagari character database collect…
University of Parma（帕尔马大学）；University of Florence（佛罗伦萨大学）
Deep learning advanced face recognition to an unprecedented accuracy. However, understanding how local parts of the face affect the overall recognition performance is still mostly unclear. Among others, face swap has been experimented to this end, but just for the entire face. In this paper, we propose to swap facial parts as a way to disentangle the recognition relevance of different face parts, like eyes, nose and mouth. In our method, swapping parts from a source face to a target one is performed by fitting a 3D prior, which establishes dense pixels correspondence between parts, while also …
The vast progress in synthetic image synthesis enables the generation of facial images in high resolution and photorealism. In biometric applications, the main motivation for using synthetic data is to solve the shortage of publicly-available biometric data while reducing privacy risks when processing such sensitive information. These advantages are exploited in this work by simulating human face ageing with recent face age modification algorithms to generate mated samples, thereby studying the impact of ageing on the performance of an open-source biometric recognition system. Further, a real …
Real-world face recognition applications often deal with suboptimal image quality or resolution due to different capturing conditions such as various subject-to-camera distances, poor camera settings, or motion blur. This characteristic has an unignorable effect on performance. Recent cross-resolution face recognition approaches used simple, arbitrary, and unrealistic down- and up-scaling techniques to measure robustness against real-world edge-cases in image quality. Thus, we propose a new standardized benchmark dataset and evaluation protocol derived from the famous Labeled Faces in the Wild…
Many videos depict people, and it is their interactions that inform us of their activities, relation to one another and the cultural and social setting. With advances in human action recognition, researchers have begun to address the automated recognition of these human-human interactions from video. The main challenges stem from dealing with the considerable variation in recording setting, the appearance of the people depicted and the coordinated performance of their interaction. This survey provides a summary of these challenges and datasets to address these, followed by an in-depth discussi…
Meghnad Saha Institute of Technology（梅格纳德·萨哈技术学院）；G.H. Raisoni College of Engineering（G.H.拉伊索尼工程学院）；University Of Calcutta（加尔各答大学）；Jadavpur University（贾达普大学）
A novel, generic scheme for off-line handwritten English alphabets character images is proposed. The advantage of the technique is that it can be applied in a generic manner to different applications and is expected to perform better in uncertain and noisy environments. The recognition scheme is using a multilayer perceptron(MLP) neural networks. The system was trained and tested on a database of 300 samples of handwritten characters. For improved generalization and to avoid overtraining, the whole available dataset has been divided into two subsets: training set and test set. We achieved 99.1…
Czech Technical University in Prague（捷克布拉格技术大学）；Universitat Oberta de Catalunya（加泰罗尼亚开放大学）；Computer Vision Center（计算机视觉中心）；Universitat de Barcelona（巴塞罗那大学）；The Queen’s University of Belfast（贝尔法斯特女王大学）；Anyvision
This work summarizes the 2020 ChaLearn Looking at People Fair Face Recognition and Analysis Challenge and provides a description of the top-winning solutions and analysis of the results. The aim of the challenge was to evaluate accuracy and bias in gender and skin colour of submitted algorithms on the task of 1:1 face verification in the presence of other confounding attributes. Participants were evaluated using an in-the-wild dataset based on reannotated IJB-C, further enriched by 12.5K new images and additional labels. The dataset is not balanced, which simulates a real world scenario where …
Ulm University（乌尔姆大学）；Otto von Guericke University Magdeburg（马格德堡奥托·冯·格里克大学）
We present a joint camera and radar approach to enable autonomous vehicles to understand and react to human gestures in everyday traffic. Initially, we process the radar data with a PointNet followed by a spatio-temporal multilayer perceptron (stMLP). Independently, the human body pose is extracted from the camera frame and processed with a separate stMLP network. We propose a fusion neural network for both modalities, including an auxiliary loss for each modality. In our experiments with a collected dataset, we show the advantages of gesture recognition with two modalities. Motivated by adver…
Human affective recognition is an important factor in human-computer interaction. However, the method development with in-the-wild data is not yet accurate enough for practical usage. In this paper, we introduce the affective recognition method focusing on valence-arousal (VA) and expression (EXP) that was submitted to the Affective Behavior Analysis in-the-wild (ABAW) 2020 Contest. Since we considered that affective behaviors have many observable features that have their own time frames, we introduced multiple optimized time windows (short-term, middle-term, and long-term) into our analyzing …
Department of Mathematics and Computer Science University of Basel（巴塞尔大学数学与计算机科学系（注：此处机构粒度为大学级别，部门“Department of Mathematics and Computer Science”可视为大学内的学院/系，但根据规则提取到大学/学院级别即可，这里原文本中“University of Basel”是明确的大学机构，而“Department of Mathematics and Computer Science”属于大学内的部门，按规则是否需要提取？仔细看规则：“机构粒度：提取到大学/学院/公司/研究院级别即可，不要细拆到系、专业、课题组、实验室（除非实验室本身就是独立机构）。” 所以“Department of Mathematics and Computer Science”属于系，不应提取，只提取“University of Basel”？但原HTML文本中作者后面跟着的是“Department of Mathematics and Computer Science University of Basel”，即作者所属机构是该大学的该系，而规则说不要细拆到系，所以只取大学级别？但原文本中作者后面直接跟着的是系和大学，那么机构应该是该大学，还是该系？规则说“不要细拆到系、专业、课题组、实验室（除非实验室本身就是独立机构）”，所以如果系不是独立机构，只提取大学。因此这里的机构是“University of Basel”（巴塞尔大学），而“Department of Mathematics and Computer Science”是系，不提取。所以最终应该输出{）
It is unknown what kind of biases modern in the wild face datasets have because of their lack of annotation. A direct consequence of this is that total recognition rates alone only provide limited insight about the generalization ability of a Deep Convolutional Neural Networks (DCNNs). We propose to empirically study the effect of different types of dataset biases on the generalization ability of DCNNs. Using synthetically generated face images, we study the face recognition rate as a function of interpretable parameters such as face pose and light. The proposed method allows valuable details …
Singapore University of Technology and Design（新加坡科技设计大学）；Lancaster University（兰卡斯特大学）；University of Melbourne（墨尔本大学）；Xidian University（西安电子科技大学）；Jiangnan University（江南大学）；Wuhan University（武汉大学）；Tsinghua University（清华大学）；Sun Yat-sen University（中山大学）；BOE Technology Group Co., Ltd（京东方科技集团股份有限公司）
In this paper, we introduce the Multi-Modal Video Reasoning and Analyzing Competition (MMVRAC) workshop in conjunction with ICCV 2021. This competition is composed of four different tracks, namely, video question answering, skeleton-based action recognition, fisheye video-based action recognition, and person re-identification, which are based on two datasets: SUTD-TrafficQA and UAV-Human. We summarize the top-performing methods submitted by the participants in this competition and show their results achieved in the competition.
Prince Sultan University（苏丹亲王大学）；Universiti Teknologi Malaysia（马来西亚理工大学）
Online Arabic cursive character recognition is still a big challenge due to the existing complexities including Arabic cursive script styles, writing speed, writer mood and so forth. Due to these unavoidable constraints, the accuracy of online Arabic character's recognition is still low and retain space for improvement. In this research, an enhanced method of detecting the desired critical points from vertical and horizontal direction-length of handwriting stroke features of online Arabic script recognition is proposed. Each extracted stroke feature divides every isolated character into some m…
One of the challenges in pattern recognition is open set recognition. Compared with closed set recognition, open set recognition needs to reduce not only the empirical risk, but also the open space risk, and the reduction of these two risks corresponds to classifying the known classes and identifying the unknown classes respectively. How to reduce the open space risk is the key of open set recognition. This paper explores the origin of the open space risk by analyzing the distribution of known and unknown classes features. On this basis, the spatial location constraint prototype loss function …
Azad University（阿扎德大学）；Babol University（巴博勒大学）；University of medical sciences of Babol（巴博勒医科大学）；Islamic Azad University - Babol branch（伊斯兰阿扎德大学巴博勒分校）；young researcher club（青年研究者俱乐部）
Neural Networks are being used for character recognition from last many years but most of the work was confined to English character recognition. Till date, a very little work has been reported for Handwritten Farsi Character recognition. In this paper, we have made an attempt to recognize handwritten Farsi characters by using a multilayer perceptron with one hidden layer. The error backpropagation algorithm has been used to train the MLP network. In addition, an analysis has been carried out to determine the number of hidden nodes to achieve high performance of backpropagation network in the …
In spite of the advancements made in the periocular recognition, the dataset and periocular recognition in the wild remains a challenge. In this paper, we propose a multilayer fusion approach by means of a pair of shared parameters (dual-stream) convolutional neural network where each network accepts RGB data and a novel colour-based texture descriptor, namely Orthogonal Combination-Local Binary Coded Pattern (OC-LBCP) for periocular recognition in the wild. Specifically, two distinct late-fusion layers are introduced in the dual-stream network to aggregate the RGB data and OC-LBCP. Thus, the …
Training convolutional neural networks (CNNs) with back-propagation (BP) is time-consuming and resource-intensive particularly in view of the need to visit the dataset multiple times. In contrast, analytic learning attempts to obtain the weights in one epoch. However, existing attempts to analytic learning considered only the multilayer perceptron (MLP). In this article, we propose an analytic convolutional neural network learning (ACnnL). Theoretically we show that ACnnL builds a closed-form solution similar to its MLP counterpart, but differs in their regularization constraints. Consequently…
University of Colorado at Colorado Springs（科罗拉多大学科罗拉多斯普林斯分校）
For applications such as airport border control, biometric technologies that can process many capture subjects quickly, efficiently, with weak supervision, and with minimal discomfort are desirable. Facial recognition is particularly appealing because it is minimally invasive yet offers relatively good recognition performance. Unfortunately, the combination of weak supervision and minimal invasiveness makes even highly accurate facial recognition systems susceptible to spoofing via presentation attacks. Thus, there is great demand for an effective and low cost system capable of rejecting such …
Human action recognition as an important application of computer vision has been studied for decades. Among various approaches, skeleton-based methods recently attract increasing attention due to their robust and superior performance. However, existing skeleton-based methods ignore the potential action relationships between different persons, while the action of a person is highly likely to be impacted by another person especially in complex events. In this paper, we propose a novel group-skeleton-based human action recognition method in complex events. This method first utilizes multi-scale s…
Analyzing and Boosting the Power of Fine-Grained Visual Recognition for Multi-modal Large Language Models
Wangxuan Institute of Computer Technology, Peking University（北京大学王选计算机研究所）；School of Intelligence Science and Technology, University of Science and Technology Beijing（北京科技大学智能科学与技术学院）
Satbayev University（萨特巴耶夫大学）；National Open Research Laboratory for Information and Space Technologies（国家信息与空间技术开放研究实验室）
This article discusses the problem of handwriting recognition in Kazakh and Russian languages. This area is poorly studied since in the literature there are almost no works in this direction. We have tried to describe various approaches and achievements of recent years in the development of handwritten recognition models in relation to Cyrillic graphics. The first model uses deep convolutional neural networks (CNNs) for feature extraction and a fully connected multilayer perceptron neural network (MLP) for word classification. The second model, called SimpleHTR, uses CNN and recurrent neural n…
This paper demonstrates two different fusion techniques at two different levels of a human face recognition process. The first one is called data fusion at lower level and the second one is the decision fusion towards the end of the recognition process. At first a data fusion is applied on visual and corresponding thermal images to generate fused image. Data fusion is implemented in the wavelet domain after decomposing the images through Daubechies wavelet coefficients (db2). During the data fusion maximum of approximate and other three details coefficients are merged together. After that Prin…
Goethe University（歌德大学）；Frankfurt Institute for Advanced Studies（法兰克福高等研究院）
A classification algorithm that combines the components of k-nearest neighbours and multilayer neural networks has been designed and tested. With this method the computational time required for training the dataset has been reduced substancially. Gabor filters were used for the feature extraction to ensure a better performance. This algorithm is tested with MNIST dataset and it will be integrated as a module in the object recognition software which is currently under development.
In many practical visual recognition scenarios, feature distribution in the source domain is generally different from that of the target domain, which results in the emergence of general cross-domain visual recognition problems. To address the problems of visual domain mismatch, we propose a novel semi-supervised adversarial transfer learning approach, which is called Coupled adversarial transfer Domain Adaptation (CatDA), for distribution alignment between two domains. The proposed CatDA approach is inspired by cycleGAN, but leveraging multiple shallow multilayer perceptrons (MLPs) instead of…
School of Engineering and Materials Science, Queen Mary University of London（伦敦玛丽女王大学工程与材料科学学院）
This paper presents a successful application of deep learning for object recognition based on acoustic data. The shortcomings of previously employed approaches where handcrafted features describing the acoustic data are being used, include limiting the capability of the found representation to be widely applicable and facing the risk of capturing only insignificant characteristics for a task. In contrast, there is no need to define the feature representation format when using multilayer/deep learning architecture methods: features can be learned from raw sensor data without defining discrimina…
Bridging Ears and Eyes: Analyzing Audio and Visual Large Language Models to Humans in Visible Sound Recognition and Reducing Their Sensory Gap via Cross-Modal Distillation
Columbia University（哥伦比亚大学）；University of Washington（华盛顿大学）
Recurrent networks have been successful in analyzing temporal data and have been widely used for video analysis. However, for video face recognition, where the base CNNs trained on large-scale data already provide discriminative features, using Long Short-Term Memory (LSTM), a popular recurrent network, for feature learning could lead to overfitting and degrade the performance instead. We propose a Recurrent Embedding Aggregation Network (REAN) for set to set face recognition. Compared with LSTM, REAN is robust against overfitting because it only learns how to aggregate the pre-trained embeddi…
University of Chinese Academy of Sciences（中国科学院大学）
Scene recognition with RGB images has been extensively studied and has reached very remarkable recognition levels, thanks to convolutional neural networks (CNN) and large scene datasets. In contrast, current RGB-D scene data is much more limited, so often leverages RGB large datasets, by transferring pretrained RGB CNN models and fine-tuning with the target RGB-D dataset. However, we show that this approach has the limitation of hardly reaching bottom layers, which is key to learn modality-specific features. In contrast, we focus on the bottom layers, and propose an alternative strategy to lea…
In this paper, we investigate the problem of grasping novel objects in unstructured environments. To address this problem, consideration of the object geometry, reachability and force closure analysis are required. We propose a framework for grasping unknown objects by localizing contact regions on the contours formed by a set of depth edges in a single view 2D depth image. According to the edge geometric features obtained from analyzing the data of the depth map, the contact regions are determined. Finally,We validate the performance of the approach by applying it to the scenes with both sing…
A challenge of skeleton-based action recognition is the difficulty to classify actions with similar motions and object-related actions. Visual clues from other streams help in that regard. RGB data are sensible to illumination conditions, thus unusable in the dark. To alleviate this issue and still benefit from a visual stream, we propose a modular network (FUSION) combining skeleton and infrared data. A 2D convolutional neural network (CNN) is used as a pose module to extract features from skeleton data. A 3D CNN is used as an infrared module to extract visual cues from videos. Both feature v…
Spatiotemporal action recognition is the task of locating and classifying actions in videos. Our project applies this task to analyzing video footage of restaurant workers preparing food, for which potential applications include automated checkout and inventory management. Such videos are quite different from the standardized datasets that researchers are used to, as they involve small objects, rapid actions, and notoriously unbalanced data classes. We explore two approaches. The first approach involves the familiar object detector You Only Look Once, and another applying a recently proposed a…
