Italy

3D shape recognition has attracted more and more attention as a task of 3D vision research. The proliferation of 3D data encourages various deep learning methods based on 3D data. Now there have been many deep learning models based on point- cloud data or multi-view data alone. However, in the era of big data, integrating data of two different modals to obtain a unified 3D shape descriptor is bound to improve the recognition accuracy. Therefore, this paper proposes a fusion network based on multimodal attention mechanism for 3D shape recognition. Considering the limitations of multi-view data, we introduce a soft attention scheme, which can use the global point-cloud features to filter the multi-view features, and then realize the effective fusion of the two features. More specifically, we obtain the enhanced multi-view features by mining the contribution of each multi-view image to the overall shape recognition, and then fuse the point-cloud features and the enhanced multi-view features to obtain a more discriminative 3D shape descriptor. We have performed relevant experiments on the ModelNet40 dataset, and experimental results verify the effectiveness of our method.

ICPR 2020

MANet : Multimodal Attention Network based Point- View fusion for 3D Shape Recognition

multimodel attention network

point-view fusion

3d shape recognition

ICPR 2020 is the premier international conference on Pattern Recognition, gathering leading researchers from around the world to present their latest achievements in Pattern Analysis and Recognition, applied Artificial Intelligence and Machine Learning. The topic of the year is " Putting Artificial intelligence to work on Patterns". 
For the first time, ICPR has employed a two-round review process similar to journal submissions, with new papers allowed to be submitted in either the first or second round and papers submitted in the first round and not accepted allowed to be revised and re-submitted for second round review. 

In this edition of the **ICPR 2020** Conference, there are 1407 Oral/Poster presentations organized in five Tracks: 
- Artificial Intelligence, Machine Learning for Pattern Analysis; 
- Biometrics, Human Analysis and Behavior Understanding; Computer Vision, Robotics and Intelligent Systems; 
- Document and Media Analysis; and 
- Image and Signal Processing. 

The **ICPR 2020** Main Conference program also includes 7 Keynotes from prominent world-renowned scientists, 8 Tutorials, 28 Demos, 8 Challenges, 2 Panels, as well as an Industry/Sponsor Exhibition. In addition, 41 Workshops on a range of important current and emerging research topics complete the ICPR 2020 program. 


poster

In this paper, we use fully convolutional neural networks for the semantic segmentation of eye tracking data. We also use these networks for reconstruction, and in conjunction with a variational auto-encoder to generate eye movement data. 
The first improvement of our approach is that no input window is necessary, due to the use of fully convolutional networks and therefore any input size can be processed directly. The second improvement is that the used and generated data is raw eye tracking data (position X, Y and time) without preprocessing. This is achieved by pre-initializing the filters in the first layer and by building the input tensor along the z axis. We evaluated our approach on three publicly available datasets and compare the results to the state of the art.


Fully Convolutional Neural Networks for Raw Eye Tracking Data Segmentation, Generation, and Reconstruction

Substantial efforts have been made on improving the generalization abilities of deep neural networks (DNNs) in order to obtain better performances without introducing more parameters. On the other hand, meta-learning approaches exhibit powerful generalization on new tasks in few-shot learning. Intuitively, few-shot learning is more challenging than the standard supervised learning as each target class only has a very few or no training samples. The natural question that arises is whether the meta-learning idea can be used for improving the generalization of DNNs on the standard supervised learning. In this paper, we propose a novel meta-learning based training procedure (MLTP) for DNNs and demonstrate that the meta-learning idea can indeed improve the generalization abilities of DNNs. MLTP simulates the
meta-training process by considering a batch of training samples as a task. The key idea is that the gradient descent step for improving the current task performance should also improve a new task performance, which is ignored by the current standard procedure for training neural networks. MLTP also benefits from all the existing training techniques such as dropout, weight decay, and batch normalization.

Is the Meta-Learning Idea Able to Improve the Generalization of Deep Neural Networks on the Standard Supervised Learning?


We present a suite of tasks requiring complex reasoning and exploration in continuous, partially observable 3D environments. 
The objective is to provide challenging scenarios and a robust baseline agent architecture that can be trained on mid-range consumer hardware in under 24h. Our scenarios combine two key advantages: (i) they are based on a simple but highly efficient 3D environment (ViZDoom) which allows high speed simulation (12000fps);
(ii) the scenarios provide the user with a range of difficulty settings, in order to identify the limitations of current state of the art algorithms and network architectures.

Deep Reinforcement Learning on a Budget: 3D Control and Reasoning Without a Supercomputer

In this paper, we propose a joint network for 3D brain images registration with super-resolution to reduce deformable image registration errors caused by low resolution. Basically, the task of deformable image registration is to find the displacement field between the reference image and the moving image. Many research works have been done for deformable image registration, under the assumption that the image resolution is high enough. However, due to the limited level of current acquisition instruments, the resolution of images is not high enough usually. As low resolution images might cause large registration errors, this paper presents a new approach that performs joint super-resolution and deformable image registration. Experiments with 3D brain images show that the joint network does help to reduce the registration errors significantly.

A Joint Super-Resolution and Deformable Registration Network for 3D Brain Images


Dense pixel matching is required for many computer vision algorithms such as disparity, optical flow or scene flow estimation. Feature Pyramid Networks (FPN) have proven to be a suitable feature extractor for CNN-based dense matching tasks. FPN generates well localized and semantically strong features at multiple scales. However, the generic FPN is not utilizing its full potential, due to its reasonable but limited localization accuracy. Thus, we present ResFPN - a multi-resolution feature pyramid network with multiple residual skip connections, where at any scale, we leverage the information from higher resolution maps for stronger and better localized features. In our ablation study, we demonstrate the effectiveness of our novel architecture with clearly higher accuracy than FPN. In addition, we verify the superior accuracy of ResFPN in many different pixel matching applications on established datasets like KITTI, Sintel, and FlyingThings3D.

ResFPN: Residual Skip Connections in Multi-Resolution Feature Pyramid Networks for Accurate Dense Pixel Matching

Video captioning is a challenging task which aims at automatically generating a natural language description of a given video. Recent researches have shown that exploiting the intrinsic multi-modalities of videos significantly promotes captioning performance. However, how to integrate multi-modalities to generate effective semantic representations for video captioning is still an open issue. Some researchers proposed to learn multimodal features in parallel during the encoding stage. The downside of these methods lies in the neglect of the interaction among multi-modalities and their rich contextual information. In this study, inspired by the fact that visual contents are generally more important for comprehending videos, we propose a novel Visual Oriented Encoder (VOE) to integrate multimodal features in an interactive manner. Specifically, VOE is designed as a hierarchical structure, where bottom layers are utilized to extract multi-scale contexts from auxiliary modalities while the top layer is exploited to generate joint representations by considering both visual and contextual information. Following the encoder-decoder framework, we systematically develop a VOE-LSTM model and evaluate it on two mainstream benchmarks: MSVD and MSR-VTT. Experimental results show that the proposed VOE surpasses conventional encoders and our VOE-LSTM model achieves competitive results compared with state-of-the-art approaches.

Visual Oriented Encoder: Integrating Multimodal and Multi-Scale Contexts for Video Captioning

Few-shot learning is a machine learning problem in which new categories are learned from only a few samples. One approach for few-shot learning is metric learning, which learns an embedding space in which learning is efficient for few-shot samples. In this paper, we focus on metric learning and demonstrate that the number of classes in the training data used for metric learning has a greater impact on the accuracy of few-shot learning than the number of samples per class. We propose a few-shot learning approach based on metric learning in which the number of classes in the training data for performing metric learning is increased. The number of classes is augmented by synthesizing samples of imaginary classes at a feature level from the original training data. The proposed method is evaluated on the miniImageNet dataset using the nearest neighbor method or a support vector machine as the classifier, and the effectiveness of the approach is demonstrated.

Few-Shot Learning Based on Metric Learning Using Class Augmentation


Considering the fact that a license plate (LP) can only generate
perspective distortion in the image due to its rigid feature, in
this paper we propose a novel perspective rectification network
(PRN) to automatically estimate the perspective transformation
and rectify the distorted LP accordingly. For recognition, we
propose a location-aware 2D attention based recognition network
that is capable of recognizing both single-line and double-line
plates with perspective deformation. The rectification network
and recognition network are connected for end-to-end training.
Experiments on common datasets show the effectiveness of the proposed approach.

2D License Plate Recognition based on Automatic Perspective Rectification


This paper studies the problem of Person Re-Identification (ReID)
for large-scale applications. Recent research efforts have been devoted
to building complicated part models, which introduce considerably
high computational cost and memory consumption, inhibiting its practicability
in large-scale applications. This paper aims to develop a novel learning
strategy to find efficient feature embeddings while maintaining the
balance of accuracy and model complexity. More specifically, we find
by enhancing the classical triplet loss together with cross-entropy
loss, our method can explore the hard examples and build a discriminant
feature embedding yet compact enough for large-scale applications.
Our method is carried out progressively using Bayesian optimization,
and we call it the Progressive Learning Algorithm (PLA). Extensive
experiments on three large-scale datasets show that our PLA is comparable
or better than the state-of-the-arts. Especially, on the challenging
Market-1501 dataset, we achieve Rank-1=94.7%/mAP=89.4% while saving
at least 30\% parameters than strong part models.

Automatic Classification of Human Granulosa Cells in Assisted Reproductive Technology using vibrational spectroscopy imaging

Object detection in remote sensing images is a challenging task due to objects in the bird-view perspective appearing with arbitrary orientations. Though considerable progress has been made, there still exist challenges with the interference from complex backgrounds, dense arrangement, and large-scale variations. In this paper, we propose an oriented detector named Cascade Saliency Attention Network (CSAN), designed for comprehensively suppressing interference in remote sensing images. Specifically, we first combine context and pixel attention on feature maps to enhance saliency of objects for suppressing interference from backgrounds. Then, in cascade network, we apply instance segmentation on ROI to increase saliency of the central object, thus preventing object features from mutual interference in dense arrangement. Additionally, to alleviate large-scale variations, we devise a multi-scale merge module during FPN merging process to learn richer scale representations. Experimental results on DOTA and HRSC2016 datasets outperform other state-of-the-art object detection methods and verify the effectiveness of our method.

Premium content

MANet : Multimodal Attention Network based Point- View fusion for 3D Shape Recognition

Downloads

Next from ICPR 2020

Fully Convolutional Neural Networks for Raw Eye Tracking Data Segmentation, Generation, and Reconstruction

Similar lecture

Calibration and Absolute Pose Estimation of Trinocular Linear Camera Array for Smart City Applications