Italy

Visual dialog is a typical multi-modal task which involves both vision and language. Nowadays, it faces two major difficulties. In this paper, we propose the Integrating Historical States and Co-attention (HSCA) for visual dialog to solve them. It includes two main modules, Co-ATT and MATCH. Specifically, the main purpose of the Co-ATT module is to guide the image with questions and answers in the early stage to get more specific objects. It tackles the first difficulty of the temporal sequence issue in historical information which may influence the precise answer for multi-round questions. The MATCH module is, based on a question with pronouns, to retrieve the best matching historical information block. It overcomes the second difficulty of the visual reference problem which requires to solve pronouns referring to unknowns in the text message and then to locate the objects in the given image. We quantitatively and qualitatively evaluate our model on VisDial v1.0, at the same time, ablation studies are carried out. The experimental results demonstrate that HSCA outperforms the state-of-the-art methods in many aspects.

ICPR 2020

Integrating Historical States and Co-attention Mechanism for Visual Dialog

visual reference

visual dialog

multi-modal

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


Social online video has emerged as one of the most popular application, where bullet screen comment is one of the favorite features of Asian users. User behavior report finds that most people are used to quickly navigate and locate his concerned video clip according to its corresponding video labels. Traditional scene segmentation algorithms are mostly based on the analysis of frames, which cannot automatically generate labels. Since time-synchronized comments can reflect the episode of current moment, this paper proposed an unsupervised video episode boundary detection model (VEBD) for bullet screen comment video. It could not only automatically identify each episode boundary, but also detect the topic for video tagging. Specifically, a Joint Episode-Topic model is first constructed to detect the hidden topic in initial partitioned time slices. Then, based on the detected topics, temporal and semantic relevancy between adjacent time slices are measured to refine the boundary detection accuracy. Experiments based on real data show that our model outperforms the existing algorithms in both boundary detection and semantic tagging quality.

Video Episode Boundary Detection with Joint Episode-Topic Model

In decades many gait recognition methods have been proposed. However, due to a real-world scenario of clothing variations, a reduction of the recognition rate occurs for most of these methods. Thus in this paper, a part-based spatio-temporal feature learning method is proposed to tackle the problem of clothing variations for gait recognition. First, based on the anatomical properties, human bodies are segmented into two regions, which are affected and unaffected by clothing variations. A learning network is particularly proposed in this paper to grasp principal spatio-temporal features from those unaffected regions. Different from most part-based methods with spatial or temporal features solely being used, in our method these two features are integrated in a more collaborative manner. Snapshots are created for each gait sequence from the H−W and T−W views, and a collaborative spatio-temporal feature can be hybridized by concatenating these correlative spatial and temporal information. The robustness and efficiency of our proposed method are validated by experiments on CASIA Gait Dataset B and OU-ISIR Treadmill Gait Dataset B. Our proposed method both achieves the state-of-the-art results on these two databases.

Part-Based Collaborative Spatio-Temporal Feature Learning for Cloth-Changing Gait Recognition

The next step for the generative adversarial networks (GAN) is to learn representations that allow us to control only a certain factor in the image explicitly. Since such a representation of the factor is independent of other factors, the controllability obtained from these representations leads to interpretability by identifying the variation of the synthesized image and the transferability for downstream tasks by inference. However, since it is difficult to identify and strictly define latent factors, the annotation is laborious. Moreover, learning such representations by a GAN is challenging due to the complex generation process. Therefore, we resolve this limitation using a novel generative model that can disentangle latent space into the appearance, the x-axis, and the y-axis of the object, and reassemble these components in an unsupervised manner. Specifically, based on the concept of packing the appearance and location in each position of the feature map, we introduce a novel structural constraint technique that prevents these representations from interacting with each other. The proposed structural constraint promotes the disentanglement of these factors. In experiments, we found that the proposed method is simple but effective for controllability and allows us to control the appearance and location via latent space without supervision, as compared with the conditional GAN.

Disentangle, Assemble, and Synthesize: Unsupervised Learning to Disentangle Appearance and Location


Automated retinal vessel segmentation plays an important role in the diagnosis of some diseases such as diabetes, arteriosclerosis and hypertension. Recent works attempt to improve segmentation performance by exploring either global or local contexts. However, the context demands are varying from regions in each image and different levels of network. To address these problems, we propose Pyramid Context-aware Network (PCANet), which can adaptively capture multi-scale context representations. Specifically, PCANet is composed of multiple Adaptive Context-aware (ACA) blocks arranged in parallel, each of which can adaptively obtain the context-aware features by estimating affinity coefficients at a specific scale under the guidance of global contextual dependencies. Meanwhile, we import ACA blocks with specific scales in different levels of the network to obtain a coarse-to-fine result. Furthermore, an integrated test-time augmentation method is developed to further boost the performance of PCANet. Finally, extensive experiments demonstrate the effectiveness of the proposed PCANet, and state-of-the-art performances are achieved with AUCs of 0.9866, 0.9886 and F1 Scores of 0.8274, 0.8371 on two public datasets, DRIVE and STARE, respectively.

PCANet: Pyramid Context-aware Network for Retinal Vessel Segmentation


We simulated the exact features of raindrops on a camera lens and conducted an experiment to evaluate the performance of a network trained to remove raindrops using synthetic raindrop data. Although research has been conducted to precisely evaluate methods to remove raindrops, with some evaluation networks trained on images with real raindrops and others trained on images with synthetic raindrops, there have not been any studies that have directly compared the performance of two networks trained on each respective kind of image. In a previous study wherein images with synthetic raindrops were used for training, the network did not work effectively on images with real raindrops because the shapes of the raindrops were simulated using simple arithmetic expressions. In this study, we focused on generating raindrop shapes that are closer to reality with the aim of using these synthetic raindrops in images to develop a technique for removing real-world raindrops. After categorizing raindrops by type, we further separated each raindrop type into its constituent elements, generated each element separately, and finally combined the generated elements. The proposed technique was used to add images with synthetic raindrops to the training data, and when we evaluated the model, we confirmed that the technique’s precision exceeded that of when only images with actual raindrops were used for training. The evaluation results proved that images with synthetic raindrops can be used as training data for real-world images.

Removing Raindrops from a Single Image using Synthetic Data

Semi-supervised video object segmentation aims at segmenting the target of interest throughout a video sequence when only the annotated mask of the first frame is given. A feasible method for segmentation is to capture the spatial-temporal coherence between frames. However, it may suffer from mask drift when the spatial-temporal coherence is unreliable. To relieve this problem, we propose an encoder-decoder-recurrent model for semi-supervised video object segmentation. The model adopts a U-shape architecture that combines atrous convolution and ConvLSTM to establish the coherence in both the spatial and temporal domains. Furthermore, the weight ratio for each block is also reconstructed to make the model more suitable for the VOS task. We evaluate our method on two benchmarks, DAVIS-2017 and Youtube-VOS, where state-of-the-art segmentation accuracy with a real-time inference speed of 21.3 frames per second on a Tesla P100 is obtained.

ACCLVOS: Atrous Convolution with Spatial-Temporal ConvLSTM for Video Object Segmentation



In recent years, convolutional neural networks have achieved rapid development in the field of object detection. However, due to the imbalance of data, high costs in labor and uneven level of data labeling, the overall performance of the previous detection network has dropped sharply when dataset extended to the large-scale with hundreds and thousands of categories. The embedding of external semantic knowledge can bring new additional information to reduce the cost of annotation and improve the performance of large-scale detection. In this paper, the Adaptive Word Embedding Module is proposed to extract the adaptive semantic knowledge graph under the constraint of the semantic consistency. Our method endows the ability to infer global semantic of detection networks without other attribute or relationship annotations. Compared with Faster RCNN, the algorithm on the MSCOCO dataset was significantly improved by 4.1%, and the mAP value has reached 32.8%. On the VG1000 dataset, it increased by 0.9% to 6.7% compared with Faster RCNN. Adaptive Word Embedding Module is lightweight, general-purpose and can be plugged into diverse detection networks.

Adaptive Word Embedding Module for Semantic Reasoning in Large-scale Detection


Melanoma is the deadliest form of skin cancer and it is diagnosed mainly visually, starting from initial clinical screening and followed by dermoscopic analysis, biopsy and histopathological examination. A dermatologist’s recognition of melanoma may be subject to errors and may take some time to diagnose it. In this regard, deep learning can be useful in the study and classification of skin cancer. In particular, by classifying images with Deep Neural Network methodologies, it is possible to obtain comparable or even superior results compared to those of dermatologists. In this paper, we propose a methodology for the classification of melanoma by adopting different deep learning techniques applied to a common dataset, composed of images from the ISIC dataset and consisting of different types of skin diseases, including melanoma on which we applied a specific pre-processing phase. In particular, a comparison of the results is performed in order to select the best effective neural network to be applied to the problem of recognition and classification of melanoma. Moreover, we also evaluate the impact of the preprocessing phase on the final classification. Different metrics such as accuracy, sensitivity, and specificity have been selected to assess the goodness of the adopted neural networks and compare them also with the manual classification of dermatologists.

A Comparison of Neural Network Approaches for Melanoma Classification


Image preprocessing is an important process during pattern recognition which increases the recognition performance. Linear convolution filtering is a primary preprocessing method used to enhance particular local patterns of the image which are essential for recognizing the images. However, because of the vast search space of the preprocessing filter, almost no earlier studies have tackled the problem of identifying an optimal preprocessing filter that yields effective features for input images. This paper proposes a novel design method for the optimal preprocessing filter corresponding to a given task. Our method calculates local image bases of the training dataset and represents the optimal filter as a linear combination of these local image bases with the optimized coefficients to maximize the expected generalization performance. Thereby, the optimization problem of the preprocessing filter is converted to a lower-dimensional optimization problem. Our proposed method combined with a higher-order local auto-correlation (HLAC) feature extraction exhibited the best performance both in the anomaly detection task with the conventional pattern recognition algorithm and in the classification task using the deep convolutional neural network compared with typical preprocessing filters.

AdaFilter: Adaptive Filter Design with Local Image Basis Decomposition for Optimizing Image Recognition Preprocessing

Face recognition system is vulnerable to many kinds of presentation attacks, so how to effectively detect whether the image is from the real face is particularly important. At present, many deep learning-based anti-spoofing methods have been proposed. But these approaches have some limitations, for example, global average pooling (GAP) easily loses local information of faces, single-scale features easily ignore information differences in different scales, while a complex network is prone to be overfitting. In this paper, we propose a face anti-spoofing approach using spatial pyramid pooling (SPP). Firstly, we use ResNet-18 with a small amount of parameter as the basic model to avoid overfitting. Further, we use spatial pyramid pooling module in the single model to enhance local features while fusing multi-scale information. The effectiveness of the proposed method is evaluated on three databases, CASIA-FASD, Replay-Attack and CASIA-SURF. The experimental results show that the proposed approach can achieve state-of-the-art performance.

Premium content

Integrating Historical States and Co-attention Mechanism for Visual Dialog

Downloads

Next from ICPR 2020

Video Episode Boundary Detection with Joint Episode-Topic Model

Similar lecture

Context-Aware Residual Module for Image Classification