In 3D shape recognition, multi-view based methods leverage human's perspective to analyze 3D shapes and have achieved significant outcomes. Most existing research works in deep learning adopt handcrafted networks as backbones due to their high capacity of feature extraction, and also benefit from ImageNet pretraining. However, whether these network architectures are suitable for 3D analysis or not remains unclear. In this paper, we propose a neural architecture search method named Auto-MVCNN which is particularly designed for optimizing architecture in multi-view 3D shape recognition. Auto-MVCNN extends gradient-based frameworks to process multi-view images, by automatically searching the fusion cell to explore intrinsic correlation among view features. Moreover, we develop an end-to-end scheme to enhance retrieval performance through the trade-off parameter search. Extensive experimental results show that the searched architectures significantly outperform manually designed counterparts in various aspects, and our method achieves state-of-the-art performance at the same time.
SlimEdge: Performance and Device Aware Distributed DNN Deployment on Resource-Constrained Edge Hardware
Amrita Vishwa Vidyapeetham（阿姆里塔印度教学院）；Intel Corporation（英特尔公司）；Indian Institute of Science（印度科学研究院）；Analog Devices, Inc.（模拟器件公司）；Birla Institute of Technology and Science-Pilani, Dubai Campus（比拉技术科学学院-迪拜校区）
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
This paper investigates the automated recognition of structural bridge components using video data. Although understanding video data for structural inspections is straightforward for human inspectors, the implementation of the same task using machine learning methods has not been fully realized. In particular, single-frame image processing techniques, such as convolutional neural networks (CNNs), are not expected to identify structural components accurately when the image is a close-up view, lacking contextual information regarding where on the structure the image originates. Inspired by the …
Southern University of Science and Technology（南方科技大学）
Recent learning-based image classification and speech recognition approaches make extensive use of attention mechanisms to achieve state-of-the-art recognition power, which demonstrates the effectiveness of attention mechanisms. Motivated by the fact that the frequency and time information of modulated radio signals are crucial for modulation mode recognition, this paper proposes a time-frequency attention mechanism for a convolutional neural network (CNN)-based modulation recognition framework. The proposed time-frequency attention module is designed to learn which channel, frequency and time…
High-resolution fingerprint recognition often relies on sophisticated matching algorithms based on hand-crafted keypoint descriptors, with pores being the most common keypoint choice. Our method is the opposite of the prevalent approach: we use instead a simple matching algorithm based on robust local pore descriptors that are learned from the data using a CNN. In order to train this CNN in a fully supervised manner, we describe how the automatic alignment of fingerprint images can be used to obtain the required training annotations, which are otherwise missing in all publicly available datase…
Carnegie Mellon University（卡内基梅隆大学）；University of California San Diego（加州大学圣地亚哥分校）
Place recognition is the fundamental module that can assist Simultaneous Localization and Mapping (SLAM) in loop-closure detection and re-localization for long-term navigation. The place recognition community has made astonishing progress over the last $20$ years, and this has attracted widespread research interest and application in multiple fields such as computer vision and robotics. However, few methods have shown promising place recognition performance in complex real-world scenarios, where long-term and large-scale appearance changes usually result in failures. Additionally, there is a l…
We evaluated a lightweight Convolutional Neural Network (CNN) called LPRNet [1] for automatic License Plate Recognition (LPR). We evaluated the algorithm on two datasets, one composed of real license plate images and the other of synthetic license plate images. In addition, we compared its performance against Tesseract [2], an Optical Character Recognition engine. We measured performance based on recognition accuracy and Levenshtein Distance. LPRNet is an end-to-end framework and demonstrated robust performance on both datasets, delivering 90 and 89 percent recognition accuracy on test sets of…
COMSATS University Islamabad（COMSATS伊斯兰堡大学）；National University of Ireland, Galway（爱尔兰国立高威大学）；Lambe Institute of Translational Research（兰贝转化研究所）
Automatic recognition of Urdu handwritten digits and characters, is a challenging task. It has applications in postal address reading, bank's cheque processing, and digitization and preservation of handwritten manuscripts from old ages. While there exists a significant work for automatic recognition of handwritten English characters and other major languages of the world, the work done for Urdu lan-guage is extremely insufficient. This paper has two goals. Firstly, we introduce a pioneer dataset for handwritten digits and characters of Urdu, containing samples from more than 900 individuals. S…
COMSATS Institute of Information Technology（COMSATS信息技术研究所）；Information Technology University (ITU)（信息技术大学）；National University of Sciences and Technology (NUST)（国立科学技术大学）
Feature descriptors involved in image processing are generally manually chosen and high dimensional in nature. Selecting the most important features is a very crucial task for systems like facial expression recognition. This paper investigates the performance of deep autoencoders for feature selection and dimension reduction for facial expression recognition on multiple levels of hidden layers. The features extracted from the stacked autoencoder outperformed when compared to other state-of-the-art feature selection and dimension reduction techniques.
We present in this paper a biometric system of face detection and recognition in color images. The face detection technique is based on skin color information and fuzzy classification. A new algorithm is proposed in order to detect automatically face features (eyes, mouth and nose) and extract their correspondent geometrical points. These fiducial points are described by sets of wavelet components which are used for recognition. To achieve the face recognition, we use neural networks and we study its performances for different inputs. We compare the two types of features used for recognition: …
Nankai University（南开大学）；Bytedance Inc.（字节跳动公司）；University of Science and Technology Beijing（北京科技大学）
Contrastive Masked Autoencoder (CMAE), as a new self-supervised framework, has shown its potential of learning expressive feature representations in visual image recognition. This work shows that CMAE also trivially generalizes well on video action recognition without modifying the architecture and the loss criterion. By directly replacing the original pixel shift with the temporal shift, our CMAE for visual action recognition, CMAE-V for short, can generate stronger feature representations than its counterpart based on pure masked autoencoders. Notably, CMAE-V, with a hybrid architecture, can…
Indian Institute of Technology Bhubaneswar（布巴内斯瓦尔印度理工学院）；TU Berlin（柏林工业大学）
This paper is devoted to improve automatic emotion recognition from speech by incorporating rhythm and temporal features. Research on automatic emotion recognition so far has mostly been based on applying features like MFCCs, pitch and energy or intensity. The idea focuses on borrowing rhythm features from linguistic and phonetic analysis and applying them to the speech signal on the basis of acoustic knowledge only. In addition to this we exploit a set of temporal and loudness features. A segmentation unit is employed in starting to separate the voiced/unvoiced and silence parts and features …
Recent approaches for end-to-end text spotting have achieved promising results. However, most of the current spotters were plagued by the inconsistency problem between text detection and recognition. In this work, we introduce and prove the existence of the inconsistency problem and analyze it from two aspects: (1) inconsistency of text recognition features between training and testing, and (2) inconsistency of optimization targets between text detection and recognition. To solve the aforementioned issues, we propose a differentiable Auto-Rectification Module (ARM) together with a new training…
In this research, a fully neural network based visual perception framework for autonomous apple harvesting is proposed. The proposed framework includes a multi-function neural network for fruit recognition and a Pointnet grasp estimation to determine the proper grasp pose to guide the robotic execution. Fruit recognition takes raw input of RGB images from the RGB-D camera to perform fruit detection and instance segmentation, and Pointnet grasp estimation take point cloud of each fruit as input and output the prediction of grasp pose for each of fruits. The proposed framework is validated by us…
Paradigm Inc.（第四范式公司）；Huazhong University of Science and Technology（华中科技大学）
Scene text recognition (STR) is very challenging due to the diversity of text instances and the complexity of scenes. The community has paid increasing attention to boost the performance by improving the pre-processing image module, like rectification and deblurring, or the sequence translator. However, another critical module, i.e., the feature sequence extractor, has not been extensively explored. In this work, inspired by the success of neural architecture search (NAS), which can identify better architectures than human-designed ones, we propose automated STR (AutoSTR) to search data-depend…
A car driver knows how to react on the gestures of the traffic officers. Clearly, this is not the case for the autonomous vehicle, unless it has road traffic control gesture recognition functionalities. In this work, we address the limitation of the existing autonomous driving datasets to provide learning data for traffic control gesture recognition. We introduce a dataset that is based on 3D body skeleton input to perform traffic control gesture classification on every time step. Our dataset consists of 250 sequences from several actors, ranging from 16 to 90 seconds per sequence. To evaluate…
The objective of this work is to automatically recognize faces from video sequences in a realistic, unconstrained setup in which illumination conditions are extreme and greatly changing, viewpoint and user motion pattern have a wide variability, and video input is of low quality. At the centre of focus are face appearance manifolds: this thesis presents a significant advance of their understanding and application in the sphere of face recognition. The two main contributions are the Generic Shape-Illumination Manifold recognition algorithm and the Anisotropic Manifold Space clustering. The Gene…
Institute of Huaqiao University（华侨大学研究院）；Industrial Engineering Research Center, universities and intelligent systems in Fujian Province（福建省高校智能系统工业工程研究中心）
We designed a gangue sorting system,and built a convolutional neural network model based on AlexNet. Data enhancement and transfer learning are used to solve the problem which the convolution neural network has insufficient training data in the training stage. An object detection and region clipping algorithm is proposed to adjust the training image data to the optimum size. Compared with traditional neural network and SVM algorithm, this algorithm has higher recognition rate for coal and coal gangue, and provides important reference for identification and separation of coal and gangue.
Cameras play a crucial role in modern driver assistance systems and are an essential part of the sensor technology for automated driving. The quality of images captured by in-vehicle cameras highly influences the performance of visual perception systems. This paper presents a feature-based algorithm to detect certain effects that can degrade image quality in automotive applications. The algorithm is based on an intelligent selection of significant features. Due to the small number of features, the algorithm performs well even with small data sets. Experiments with different data sets show that…
Coins are integral part of our day to day life. We use coins everywhere like grocery store, banks, buses, trains etc. So it becomes a basic need that coins can be sorted and counted automatically. For this it is necessary that coins can be recognized automatically. In this paper we have developed an ANN (Artificial Neural Network) based Automated Coin Recognition System for the recognition of Indian Coins of denomination Rs. 1, 2, 5 and 10 with rotation invariance. We have taken images from both sides of coin. So this system is capable of recognizing coins from both sides. Features are extract…
Phase recognition plays an essential role for surgical workflow analysis in computer assisted intervention. Transformer, originally proposed for sequential data modeling in natural language processing, has been successfully applied to surgical phase recognition. Existing works based on transformer mainly focus on modeling attention dependency, without introducing auto-regression. In this work, an Auto-Regressive Surgical Transformer, referred as ARST, is first proposed for on-line surgical phase recognition from laparoscopic videos, modeling the inter-phase correlation implicitly by conditiona…
Indraprastha Institute of Information Technology（因德拉普拉斯信息技术学院）
Conventionally, autoencoders are unsupervised representation learning tools. In this work, we propose a novel discriminative autoencoder. Use of supervised discriminative learning ensures that the learned representation is robust to variations commonly encountered in image datasets. Using the basic discriminating autoencoder as a unit, we build a stacked architecture aimed at extracting relevant representation from the training data. The efficiency of our feature extraction algorithm ensures a high classification accuracy with even simple classification schemes like KNN (K-nearest neighbor). W…
REsearch Groups in Intelligent Machines Laboratory（智能机器研究组实验室）；ENIS-Sfax（斯法克斯国立工程师学院）；Higher Institute of Computer Science and Communication Techniques（高等计算机科学与通信技术学院）；University of Sousse（苏塞大学）；Al Baha University（巴哈大学）；Laboratoire d’InfoRmatique en Images et Systmes d’information (LIRIS)（图像与信息系统信息学实验室（LIRIS））；INSA of Lyon（里昂国立应用科学学院）
The recognition of texts existing in camera-captured images has become an important issue for a great deal of research during the past few decades. This give birth to Scene Character Recognition (SCR) which is an important step in scene text recognition pipeline. In this paper, we extended the Bag of Features (BoF)-based model using deep learning for representing features for accurate SCR of different languages. In the features coding step, a deep Sparse Auto-encoder (SAE)-based strategy was applied to enhance the representative and discriminative abilities of image features. This deep learnin…
Elevator button recognition is considered an indispensable function for enabling the autonomous elevator operation of mobile robots. However, due to unfavorable image conditions and various image distortions, the recognition accuracy remains to be improved. In this paper, we present a novel algorithm that can autonomously correct perspective distortions of elevator panel images. The algorithm first leverages the Gaussian Mixture Model (GMM) to conduct a grid fitting process based on button recognition results, then utilizes the estimated grid centers as reference features to estimate camera mo…
Uncertain recognition success, unfavorable scaling of connection complexity or dependence on complex external input impair the usefulness of current oscillatory neural networks for pattern recognition or restrict technical realizations to small networks. We propose a new network architecture of coupled oscillators for pattern recognition which shows none of the mentioned aws. Furthermore we illustrate the recognition process with simulation results and analyze the new dynamics analytically: Possible output patterns are isolated attractors of the system. Additionally, simple criteria for recogn…
University at Buffalo, The State University of New York（纽约州立大学布法罗分校）；Binghamton University, The State University of New York（纽约州立大学宾汉姆顿分校）
Accurate real-time object recognition from sensory data has long been a crucial and challenging task for autonomous driving. Even though deep neural networks (DNNs) have been successfully applied in this area, most existing methods still heavily rely on the pre-processing of the pulse signals derived from LiDAR sensors, and therefore introduce additional computational overhead and considerable latency. In this paper, we propose an approach to address the object recognition problem directly with raw temporal pulses utilizing the spiking neural network (SNN). Being evaluated on various datasets …
The problem of domain generalization is to take knowledge acquired from a number of related domains where training data is available, and to then successfully apply it to previously unseen domains. We propose a new feature learning algorithm, Multi-Task Autoencoder (MTAE), that provides good generalization performance for cross-domain object recognition. Our algorithm extends the standard denoising autoencoder framework by substituting artificially induced corruption with naturally occurring inter-domain variability in the appearance of objects. Instead of reconstructing images from noisy vers…
