Italy

Lip-reading methods and fusion strategy are crucial for audio-visual speech recognition. In recent years, most approaches involve two separate audio and visual streams with early or late fusion strategies. Such a single-stage fusion method may fail to guarantee the integrity and representativeness of fusion information simultaneously. This paper extends a traditional single-stage fusion network to a two-step feature fusion network by adding an audio-visual early feature fusion (AVEFF) stream to the baseline model. This method can learn the fusion information of different stages, preserving the original features as much as possible and ensuring the independence of different features. Besides, to capture long-range dependencies of video information, a non-local block is added to the feature extraction part of the visual stream (NL-Visual) to obtain the long-term spatio-temporal features. Experimental results on the two largest public datasets in English (LRW) and Mandarin (LRW-1000) demonstrate our method is superior to other state-of-the-art methods.

ICPR 2020

Audio-Visual Speech Recognition Using A Two-Step Feature Fusion Strategy

non-local

feature fusion

speech recognition


IWSSIP is an international conference that brings together researchers and developers from both academia and industry reporting the latest scientific and theoretical advances to discuss and debate major issues and state-of-the-art aspects on systems, signals and image processing.

###### For the session discussion, each author will be seated at individual breakout tables.  Please find which table they will be at here:
###### [QA table assignments in Gather.town](https://drive.google.com/file/d/1hBHOD_KF7NSsaTcpYcHCZslXJvQVxJQe/view?usp=sharing)

IWSSIP 2021

poster

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. 


Person re-identification (ReID) aims to identify the specific pedestrian in a series of images or videos. Recently, ReID is receiving more and more attention in the fields of computer vision research and application like intelligent security. One major issue downgrading the ReID model performance lies in that various subjects in the same body orientations look too similar to distinguish by the model, while the same subject viewed in different orientations looks rather different. However, most of the current studies do not particularly differentiate pedestrians in orientation when designing the network, so we rethink this problem particularly from the perspective of person orientation and propose a new network structure by including two branches: one handling samples with the same body orientations and the other handling samples with different body orientations. Correspondingly, we also propose an orientation classifier that can accurately distinguish the orientation of each person. At the same time, the three-part loss functions are introduced for orientation constraint and combined to optimize the network simultaneously. Also, we use global and local features int the training stage in order to make use of multi-level information. Therefore, our network can derive its efficacy from orientation constraints and multiple features. Experiments show that our method not only has competitive performance on multiple datasets, but also can let retrieval results aligned with the orientation of the query sample rank higher, which may have great potential in the practical applications.

Rethinking ReID：Multi-Feature Fusion Person Re-identification Based On Orientation Constraints

Semantic segmentation is an essential task in plenty of real-life applications such as virtual reality, video analysis, autonomous driving, etc. Recent advancements in fundamental vision-based tasks ranging from image classiﬁcation to semantic segmentation have demonstrated deep learning-based models’ high capability in learning complicated representation on large datasets. Nevertheless, manually labeling semantic segmentation dataset with pixel-level annotation is extremely labor-intensive. To address this problem, we propose a novel multi-level feature alignment framework for cross-domain semantic segmentation of urban scenes by exploiting generative adversarial networks. In the proposed multi-level feature alignment method, we ﬁrst translate images from one domain to another one. Then the discriminative feature representations extracted by the deep neural network are concatenated, followed by domain adversarial learning to make the intermediate feature distribution of the target domain images close to those in the source domain. With these domain adaptation techniques, models trained with images in the source domain where the labels are easy to acquire can be deployed to the target domain where the labels are scarce. Experimental evaluations on various mainstream benchmarks conﬁrm the effectiveness as well as robustness of our approach.

Cross-Domain Semantic Segmentation of Urban Scenes via Multi-Level Feature Alignment


Automatic medical image segmentation has wide applications for disease diagnosing. However, it is much more challenging than natural optical image segmentation due to the high-resolution of medical images and the corresponding huge computation cost. The sliding window is a commonly used technique for whole slide image (WSI) segmentation, however, for these methods based on the sliding window, the main drawback is lacking global contextual information for supervision. In this paper, we propose a dual-inputs attention network (denoted as DA-RefineNet) for WSI segmentation, where both local fine-grained information and global coarse information can be efficiently utilized. Sufficient comparative experiments are conducted to evaluate the effectiveness of the proposed method, the results prove that the proposed method can achieve better performance on WSI segmentation compared to methods relying on single-input.

DA-RefineNet: Dual-inputs Attention RefineNet for Whole Slide Image Segmentation

With the development of deep convolutional neural networks (CNNs), the object detection accuracy has been greatly improved. But the performance of small object detection is still far from satisfactory, mainly because small objects are so tiny that the information contained in the feature map is limited. Existing methods focus on improving classification accuracy but still suffer from the limitation of bounding box prediction. To solve this issue, we propose a detection framework by generative and discriminative learning. First, a reconstruction generator network is designed to reconstruct the mapping from low frequency to high frequency for anchor box prediction. Then, a detector module extracts the regions of interest (ROIs) from generated results and implements a RoI-Head to predict object category and refine bounding box. In order to guide the reconstructed image related to the corresponding one, a discriminator module is adopted to tell from the generated result and the original image. Extensive evaluations on the challenging MS-COCO dataset demonstrate that our model outperforms most state-of-the-art models in detecting small objects, especially the reconstruction module improves the average precision for small object (APs) by 7.7%.

Small Object Detection by Generative and Discriminative Learning


The appearance of tumor cell clusters in pleural effusion is usually a vital sign of cancer metastasis. Segmentation, as an indispensable basis, is of crucial importance for diagnosing, chemical treatment, and prognosis in patients. However, accurate segmentation of unstained cell clusters containing more detailed features than the fluorescent staining images remains to be a challenging problem due to the complex background and unclear boundary.

Fused 3-Stage Image Segmentation for Pleural Effusion Cell Clusters

Generative adversarial nets (GANs) have been successfully applied in many fields like image generation, inpainting, super-resolution, and drug discovery, etc. By now, the inner process of GANs is far from being understood. To get a deeper insight into the intrinsic mechanism of GANs, in this paper, a method for interpreting the latent
space of GANs by analyzing the correlation between latent variables and the corresponding semantic contents in generated images is proposed. Unlike previous methods that focus on dissecting models via feature visualization, the emphasis of this work is put on the variables in latent space, i.e. how the latent variables affect the quantitative analysis of generated results. Given a pre-trained GAN model with weights fixed, the latent variables are intervened to analyze their effect on the semantic content in generated images. A set of controlling latent variables can be derived for specific content generation, and the controllable semantic content manipulation is achieved. The proposed method is testified on the datasets Fashion-MNIST and UT Zappos50K, experiment results show its effectiveness

Interpreting the Latent Space of GANs via Correlation Analysis for Controllable Concept Manipulation 



Fast and accurate landmark location and bounding box detection are important steps in 3D medical imaging. In this paper, we propose a novel multi-task learning framework, for real-time, simultaneous landmark location and bounding box detection in 3D space. Our method extends the famous singleshot multibox detector (SSD) from single-task learning to multitask learning and from 2D to 3D. Furthermore, we propose a post-processing approach to refine the network landmark output, by averaging the candidate landmarks. Owing to these settings, the proposed framework is fast and accurate. For 3D cardiac magnetic resonance (MR) images with size 224 × 224 × 64, our framework runs 128 volumes per second (VPS) on GPU and achieves 6.75mm average point-to-point distance error for landmark location, which outperforms both state-of-the-art and baseline methods. We also show that segmenting the 3D image cropped with the bounding box results in both improved performance and efficiency.

One-stage Multi-task Detector for 3D Cardiac MR Imaging

Crowd counting plays an increasingly important role in public security. Recently, many crowd counting methods for a single image have been proposed but few studies have focused on using temporal information from image sequences of videos to improve prediction performance. In the existing methods using videos for crowd estimation, temporal features and spatial features are modeled jointly for the prediction, which makes the model less efficient in extracting spatiotemporal features and difficult to improve the performance of predictions. In order to solve these problems, this paper proposes a Parasite-Host Network (PHNet) which is composed of Parasite branch and Host branch to extract temporal features and spatial features respectively. To specifically extract the transform features in the time domain, we propose a novel architecture termed as “Relational Extractor”(RE) which models the multiplicative interaction features of adjacent frames. In addition, the Host branch extracts the spatial features from a current frame which can be replaced with any model that uses a single image for the prediction. We conducted experiments by using our PHNet on four video crowd counting benchmarks: Venice,UCSD,FDST and CrowdFlow. Experimental results show that PHNet achieves superior performance on these four datasets to the state-of-the- art methods.

PHNet: Parasite-Host Network for Video Crowd Counting

We consider the problem of object segmentation in cultural sites. Since collecting and labeling large datasets of real images is challenging, we investigate whether the use of synthetic images can be useful to achieve good segmentation performance on real data. To perform the study, we collected a new dataset comprising both real and synthetic images of 24 artworks in a cultural site. The synthetic images have been automatically generated from the 3D model of the considered cultural site using a tool developed for that purpose. Real and synthetic images have been labeled for the task of semantic segmentation of artworks. We compare three different approaches to perform object segmentation exploiting real and synthetic data. The experimental results point out that the use of synthetic data helps to improve the performances of segmentation algorithms when tested on real images. Satisfactory performance is achieved exploiting semantic segmentation together with image-to-image translation and including a small amount of real data during training. To encourage research on the topic, we publicly release the proposed dataset at the following url: https://iplab.dmi.unict.it/EGO-CH-OBJ-SEG/

Semantic Object Segmentation in Cultural Sites using Real and Synthetic Data

With the prosperous development of Convolutional Neural Networks, currently they can perform excellently on visual understanding tasks when the input images are high quality and common quality images. However, large degradation in performance always occur when the input images are low quality images. In this paper, we propose a new super-resolution method in order to improve the classification performance for low-resolution images. In an image, the regions in which pixel values vary dramatically contain more abundant high frequency contents compared to other parts. Based on this fact, we design a weight map and integrate it with a super-resolution CNN training framework. During the process of training, this weight map can find out positions of the high frequency pixels in ground truth high-resolution images. After that, the pixel-level loss function takes effect only at these found positions to minimize the difference between reconstructed high-resolution images and ground truth high-resolution images. Compared with other state-of-the-art super-resolution methods, the experiment results show that our method can recover more high frequency contents in high-resolution image reconstructing, and better improve the classification accuracy after low-resolution image preprocessing.

Premium content

Audio-Visual Speech Recognition Using A Two-Step Feature Fusion Strategy

Downloads

Next from ICPR 2020

Rethinking ReID：Multi-Feature Fusion Person Re-identification Based On Orientation Constraints

Similar lecture

Transition from hybrid to end-to-end speech recognition in Slovak utilizing Transformer neural network architecture