ICPR2020 Paper Browser

Paper download is intended for registered attendees only, and is subjected to the IEEE Copyright Policy. Any other use is strongly forbidden.

Multi-Modal Contextual Graph Neural Network for Text Visual Question Answering

Yaoyuan Liang, Xin Wang, Xuguang Duan, Wenwu Zhu

Auto-TLDR; Multi-modal Contextual Graph Neural Network for Text Visual Question Answering

Abstract Slides Poster

Text visual question answering (TextVQA) targets at answering the question related to texts appearing in the given images, posing more challenges than VQA by requiring a deeper recognition and understanding of various shapes of human-readable scene texts as well as their meanings in different contexts. Existing works on TextVQA suffer from two weaknesses: i) scene texts and non-textual objects are processed separately and independently without considering their mutual interactions during the question understanding and answering process, ii) scene texts are encoded only through word embeddings without taking the corresponding visual appearance features as well as their potential relationships with other non-textual objects in the images into account. To overcome the weakness of exiting works, we propose a novel multi-modal contextual graph neural network (MCG) model for TextVQA. The proposed MCG model can capture the relationships between visual features of scene texts and non-textual objects in the given images as well as utilize richer sources of multi-modal features to improve the model performance. In particular, we encode the scene texts into richer features containing textual, visual and positional features, then model the visual relations between scene texts and non-textual objects through a contextual graph neural network. Our extensive experiments on real-world dataset demonstrate the advantages of the proposed MCG model over baseline approaches.

Similar papers

Dual Path Multi-Modal High-Order Features for Textual Content Based Visual Question Answering

Yanan Li, Yuetan Lin, Hongrui Zhao, Donghui Wang

Auto-TLDR; TextVQA: An End-to-End Visual Question Answering Model for Text-Based VQA

Abstract Slides Similar

As a typical cross-modal problem, visual question answering (VQA) has received increasing attention from the communities of computer vision and natural language processing. Reading and reasoning about texts and visual contents in the images is a burgeoning and important research topic in VQA, especially for the visually impaired assistance applications. Given an image, it aims to predict an answer to a provided natural language question closely related to its textual contents. In this paper, we propose a novel end-to-end textual content based VQA model, which grounds question answering both on the visual and textual information. After encoding the image, question and recognized text words, it uses multi-modal factorized high-order modules and the attention mechanism to fuse question-image and question-text features respectively. The complex correlations among different features can be captured efficiently. To ensure the model's extendibility, it embeds candidate answers and recognized texts in a semantic embedding space and adopts semantic embedding based classifier to perform answer prediction. Extensive experiments on the newly proposed benchmark TextVQA demonstrate that the proposed model can achieve promising results.

A Novel Attention-Based Aggregation Function to Combine Vision and Language

Matteo Stefanini, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara

Auto-TLDR; Fully-Attentive Reduction for Vision and Language

Abstract Slides Poster Similar

The joint understanding of vision and language has been recently gaining a lot of attention in both the Computer Vision and Natural Language Processing communities, with the emergence of tasks such as image captioning, image-text matching, and visual question answering. As both images and text can be encoded as sets or sequences of elements - like regions and words - proper reduction functions are needed to transform a set of encoded elements into a single response, like a classification or similarity score. In this paper, we propose a novel fully-attentive reduction method for vision and language. Specifically, our approach computes a set of scores for each element of each modality employing a novel variant of cross-attention, and performs a learnable and cross-modal reduction, which can be used for both classification and ranking. We test our approach on image-text matching and visual question answering, building fair comparisons with other reduction choices, on both COCO and VQA 2.0 datasets. Experimentally, we demonstrate that our approach leads to a performance increase on both tasks. Further, we conduct ablation studies to validate the role of each component of the approach.

Multi-Stage Attention Based Visual Question Answering

Aakansha Mishra, Ashish Anand, Prithwijit Guha

Auto-TLDR; Alternative Bi-directional Attention for Visual Question Answering

Abstract Poster Similar

Recent developments in the field of Visual Question Answering (VQA) have witnessed promising improvements in performance through contributions in attention based networks. Most such approaches have focused on unidirectional attention that leverage over attention from textual domain (question) on visual space. These approaches mostly focused on learning high-quality attention in the visual space. In contrast, this work proposes an alternating bi-directional attention framework. First, a question to image attention helps to learn the robust visual space embedding, and second, an image to question attention helps to improve the question embedding. This attention mechanism is realized in an alternating fashion i.e. question-to-image followed by image-to-question and is repeated for maximizing performance. We believe that this process of alternating attention generation helps both the modalities and leads to better representations for the VQA task. This proposal is benchmark on TDIUC dataset and against state-of-art approaches. Our ablation analysis shows that alternate attention is the key to achieve high performance in VQA.

Integrating Historical States and Co-Attention Mechanism for Visual Dialog

Tianling Jiang, Yi Ji, Chunping Liu

Auto-TLDR; Integrating Historical States and Co-attention for Visual Dialog

Abstract Slides Poster Similar

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 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 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 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.

Multi-Scale Relational Reasoning with Regional Attention for Visual Question Answering

Yuntao Ma, Yirui Wu, Tong Lu

Auto-TLDR; Question-Guided Relational Reasoning for Visual Question Answering

Abstract Slides Poster Similar

The main challenges of visual question answering (VQA) lie in modeling an alignment between image and question to find out informative regions in images that related to the question and reasoning relations among visual objects according to the question. In this paper, we propose question-guided relational reasoning in multi-scales for visual question answering, in which each region is enhanced by regional attention. Specifically, we present regional attention, which consists of a soft attention and a hard attention, to pick up informative regions of the image according to informative evaluations implemented by question-guided soft attention. And combinations of different informative regions are then concatenated with question embedding in different scales to capture relational information. Relational reasoning can extract question-based relational information between regions, and the multi-scale mechanism gives it the ability to analyze relationships in diversity and sensitivity to numbers by modeling scales of relationships. We conduct experiments to show that our proposed architecture is effective and achieves a new state-of-the-art on VQA v2.

Question-Agnostic Attention for Visual Question Answering

Moshiur R Farazi, Salman Hameed Khan, Nick Barnes

Auto-TLDR; Question-Agnostic Attention for Visual Question Answering

Abstract Slides Poster Similar

Visual Question Answering (VQA) models employ attention mechanisms to discover image locations that are most relevant for answering a specific question. For this purpose, several multimodal fusion strategies have been proposed, ranging from relatively simple operations (e.g., linear sum) to more complex ones (e.g., Block). The resulting multimodal representations define an intermediate feature space for capturing the interplay between visual and semantic features, that is helpful in selectively focusing on image content. In this paper, we propose a question-agnostic attention mechanism that is complementary to the existing question-dependent attention mechanisms. Our proposed model parses object instances to obtain an `object map' and applies this map on the visual features to generate Question-Agnostic Attention (QAA) features. In contrast to question-dependent attention approaches that are learned end-to-end, the proposed QAA does not involve question-specific training, and can be easily included in almost any existing VQA model as a generic light-weight pre-processing step, thereby adding minimal computation overhead for training. Further, when used in complement with the question-dependent attention, the QAA allows the model to focus on the regions containing objects that might have been overlooked by the learned attention representation. Through extensive evaluation on VQAv1, VQAv2 and TDIUC datasets, we show that incorporating complementary QAA allows state-of-the-art VQA models to perform better, and provides significant boost to simplistic VQA models, enabling them to performance on par with highly sophisticated fusion strategies.

Answer-Checking in Context: A Multi-Modal Fully Attention Network for Visual Question Answering

Hantao Huang, Tao Han, Wei Han, Deep Yap Deep Yap, Cheng-Ming Chiang

Auto-TLDR; Fully Attention Based Visual Question Answering

Abstract Slides Poster Similar

Visual Question Answering (VQA) is challenging due to the complex cross-modality relations. It has received extensive attention from the research community. From the human perspective, to answer a visual question, one needs to read the question and then refer to the image to generate an answer. Such answer will then be checked against the question and image again for the final confirmation. In this paper, we mimic this process and propose a fully attention based VQA architecture. Moreover, an answer-checking module is proposed to perform a unified attention on the jointly answer, question and image representation to update the answer. This mimics the human answer checking process to consider the answer in the context. With answer-checking modules and transferred BERT layers, our model achieves a state-of-the-art accuracy 71.57\% using less parameters on VQA-v2.0 test-standard split.

Transformer Reasoning Network for Image-Text Matching and Retrieval

Nicola Messina, Fabrizio Falchi, Andrea Esuli, Giuseppe Amato

Auto-TLDR; A Transformer Encoder Reasoning Network for Image-Text Matching in Large-Scale Information Retrieval

Abstract Slides Poster Similar

Image-text matching is an interesting and fascinating task in modern AI research. Despite the evolution of deep-learning-based image and text processing systems, multi-modal matching remains a challenging problem. In this work, we consider the problem of accurate image-text matching for the task of multi-modal large-scale information retrieval. State-of-the-art results in image-text matching are achieved by inter-playing image and text features from the two different processing pipelines, usually using mutual attention mechanisms. However, this invalidates any chance to extract separate visual and textual features needed for later indexing steps in large-scale retrieval systems. In this regard, we introduce the Transformer Encoder Reasoning Network (TERN), an architecture built upon one of the modern relationship-aware self-attentive architectures, the Transformer Encoder (TE). This architecture is able to separately reason on the two different modalities and to enforce a final common abstract concept space by sharing the weights of the deeper transformer layers. Thanks to this design, the implemented network is able to produce compact and very rich visual and textual features available for the successive indexing step. Experiments are conducted on the MS-COCO dataset, and we evaluate the results using a discounted cumulative gain metric with relevance computed exploiting caption similarities, in order to assess possibly non-exact but relevant search results. We demonstrate that on this metric we are able to achieve state-of-the-art results in the image retrieval task. Our code is freely available at https://github.com/mesnico/TERN.

Visual Style Extraction from Chart Images for Chart Restyling

Danqing Huang, Jinpeng Wang, Guoxin Wang, Chin-Yew Lin

Auto-TLDR; Exploiting Visual Properties from Reference Chart Images for Chart Restyling

Abstract Slides Poster Similar

Creating a good looking chart for better visualization is time consuming. There are plenty of well-designed charts on the Web, which are ideal references for imitation of chart style. However, stored as bitmap images, reference charts have hinder machine interpretation of style settings and thus difficult to be directly applied. In this paper, we extract visual properties from reference chart images as style templates to restyle charts. We first construct a large-scale dataset of 187,059 chart images from real world data, labeled with predefined visual property values. Then we introduce an end-to-end learning network to extract the properties based on two image-encoding approaches. Furthermore, in order to capture spatial relationships of chart objects, which are crucial in solving the task, we propose a novel positional encoding method to integrate clues of relative positions between objects. Experimental results show that our model significantly outperforms baseline models. By adding positional features, our model achieves better performance. Finally, we present the application for chart restyling based on our model.

PICK: Processing Key Information Extraction from Documents Using Improved Graph Learning-Convolutional Networks

Wenwen Yu, Ning Lu, Xianbiao Qi, Ping Gong, Rong Xiao

Auto-TLDR; PICK: A Graph Learning Framework for Key Information Extraction from Documents

Abstract Slides Poster Similar

Computer vision with state-of-the-art deep learning models have achieved huge success in the field of Optical Character Recognition (OCR) including text detection and recognition tasks recently. However, Key Information Extraction (KIE) from documents as the downstream task of OCR, having a large number of use scenarios in real-world, remains a challenge because documents not only have textual features extracting from OCR systems but also have semantic visual features that are not fully exploited and play a critical role in KIE. Too little work has been devoted to efficiently make full use of both textual and visual features of the documents. In this paper, we introduce PICK, a framework that is effective and robust in handling complex documents layout for KIE by combining graph learning with graph convolution operation, yielding a richer semantic representation containing the textual and visual features and global layout without ambiguity. Extensive experiments on real-world datasets have been conducted to show that our method outperforms baselines methods by significant margins.

P ≈ NP, at Least in Visual Question Answering

Shailza Jolly, Sebastian Palacio, Joachim Folz, Federico Raue, Jörn Hees, Andreas Dengel

Auto-TLDR; Polar vs Non-Polar VQA: A Cross-over Analysis of Feature Spaces for Joint Training

Abstract Similar

In recent years, progress in the Visual Question Answering (VQA) field has largely been driven by public challenges and large datasets. One of the most widely-used of these is the VQA 2.0 dataset, consisting of polar ("yes/no") and non-polar questions. Looking at the question distribution over all answers, we find that the answers "yes" and "no" account for 38% of the questions, while the remaining 62% are spread over the more than 3000 remaining answers. While several sources of biases have already been investigated in the field, the effects of such an over-representation of polar vs. non-polar questions remain unclear. In this paper, we measure the potential confounding factors when polar and non-polar samples are used jointly to train a baseline VQA classifier, and compare it to an upper bound where the over-representation of polar questions is excluded from the training. Further, we perform cross-over experiments to analyze how well the feature spaces align. Contrary to expectations, we find no evidence of counterproductive effects in the joint training of unbalanced classes. In fact, by exploring the intermediate feature space of visual-text embeddings, we find that the feature space of polar questions already encodes sufficient structure to answer many non-polar questions. Our results indicate that the polar (P) and the non-polar (NP) feature spaces are strongly aligned, hence the expression P ≈ NP.

GCNs-Based Context-Aware Short Text Similarity Model

Xiaoqi Sun

Auto-TLDR; Context-Aware Graph Convolutional Network for Text Similarity

Abstract Slides Poster Similar

Semantic textual similarity is a fundamental task in text mining and natural language processing (NLP), which has profound research value. The essential step for text similarity is text representation learning. Recently, researches have explored the graph convolutional network (GCN) techniques on text representation, since GCN does well in handling complex structures and preserving syntactic information. However, current GCN models are usually limited to very shallow layers due to the vanishing gradient problem, which cannot capture non-local dependency information of sentences. In this paper, we propose a GCNs-based context-aware (GCSTS) model that applies iterated GCN blocks to train deeper GCNs. Recurrently employing the same GCN block prevents over-fitting and provides broad effective input width. Combined with dense connections, GCSTS can be trained more deeply. Besides, we use dynamic graph structures in the block, which further extend the receptive field of each vertex in graphs, learning better sentence representations. Experiments show that our model outperforms existing models on several text similarity datasets, while also verify that GCNs-based text representation models can be trained in a deeper manner, rather than being trained in two or three layers.

MAGNet: Multi-Region Attention-Assisted Grounding of Natural Language Queries at Phrase Level

Amar Shrestha, Krittaphat Pugdeethosapol, Haowen Fang, Qinru Qiu

Auto-TLDR; MAGNet: A Multi-Region Attention-Aware Grounding Network for Free-form Textual Queries

Abstract Slides Poster Similar

Grounding free-form textual queries necessitates an understanding of these textual phrases and its relation to the visual cues to reliably reason about the described locations. Spatial attention networks are known to learn this relationship and focus its gaze on salient objects in the image. Thus, we propose to utilize spatial attention networks for image-level visual-textual fusion preserving local (word) and global (phrase) information to refine region proposals with an in-network Region Proposal Network (RPN) and detect single or multiple regions for a phrase query. We focus only on the phrase query - ground truth pair (referring expression) for a model independent of the constraints of the datasets i.e. additional attributes, context etc. For such referring expression dataset ReferIt game, our Multi- region Attention-assisted Grounding network (MAGNet) achieves over 12% improvement over the state-of-the-art. Without the con- text from image captions and attribute information in Flickr30k Entities, we still achieve competitive results compared to the state- of-the-art.

Named Entity Recognition and Relation Extraction with Graph Neural Networks in Semi Structured Documents

Manuel Carbonell, Pau Riba, Mauricio Villegas, Alicia Fornés, Josep Llados

Auto-TLDR; Graph Neural Network for Entity Recognition and Relation Extraction in Semi-Structured Documents

Abstract Slides Similar

The use of administrative documents to communicate and leave record of business information requires of methods able to automatically extract and understand the content from such documents in a robust and efficient way. In addition, the semi-structured nature of these reports is specially suited for the use of graph-based representations which are flexible enough to adapt to the deformations from the different document templates. Moreover, Graph Neural Networks provide the proper methodology to learn relations among the data elements in these documents. In this work we study the use of Graph Neural Network architectures to tackle the problem of entity recognition and relation extraction in semi-structured documents. Our approach achieves state of the art results on the three tasks involved in the process. Moreover, the experimentation with two datasets of different nature demonstrates the good generalization ability of our approach.

Label or Message: A Large-Scale Experimental Survey of Texts and Objects Co-Occurrence

Koki Takeshita, Juntaro Shioyama, Seiichi Uchida

Auto-TLDR; Large-scale Survey of Co-occurrence between Objects and Scene Text with a State-of-the-art Scene Text detector and Recognizer

Abstract Similar

Our daily life is surrounded by textual information. Nowadays, the automatic collection of textual information becomes possible owing to the drastic improvement of scene text detectors and recognizer. The purpose of this paper is to conduct a large-scale survey of co-occurrence between visual objects (such as book and car) and scene texts with a large image dataset and a state-of-the-art scene text detector and recognizer. Especially, we focus on the function of ``label'' texts, which are attached to objects for detailing the objects. By analyzing co-occurrence between objects and scene texts, it is possible to observe the statistics about the label texts and understand how the scene texts will be useful for recognizing the objects and vice versa.

A Multi-Head Self-Relation Network for Scene Text Recognition

Zhou Junwei, Hongchao Gao, Jiao Dai, Dongqin Liu, Jizhong Han

Auto-TLDR; Multi-head Self-relation Network for Scene Text Recognition

Abstract Slides Poster Similar

The text embedded in scene images can be seen everywhere in our lives. However, recognizing text from natural scene images is still a challenge because of its diverse shapes and distorted patterns. Recently, advanced recognition networks generally treat scene text recognition as a sequence prediction task. Although achieving excellent performance, these recognition networks consider the feature map cells as independent individuals and update cells state without utilizing the information of their neighboring cells. And the local receptive field of traditional convolutional neural network (CNN) makes a single cell that cannot cover the whole text region in an image. Due to these issues, the existing recognition networks cannot extract the global context in a visual scene. To deal with the above problems, we propose a Multi-head Self-relation Network(MSRN) for scene text recognition in this paper. The MSRN consists of several multi-head self-relation layers, which is designed for extracting the global context of a visual scene, so that transforms a cell into a new cell that fuses the information of the related cells. Furthermore, experiments over several public datasets demonstrate that our proposed recognition network achieves superior performance on several benchmark datasets including IC03, IC13, IC15, SVT-Perspective.

Improving Visual Question Answering Using Active Perception on Static Images

Theodoros Bozinis, Nikolaos Passalis, Anastasios Tefas

Auto-TLDR; Fine-Grained Visual Question Answering with Reinforcement Learning-based Active Perception

Abstract Slides Poster Similar

Visual Question Answering (VQA) is one of the most challenging emerging applications of deep learning. Providing powerful attention mechanisms is crucial for VQA, since the model must correctly identify the region of an image that is relevant to the question at hand. However, existing models analyze the input images at a fixed and typically small resolution, often leading to discarding valuable fine-grained details. To overcome this limitation, in this work we propose a reinforcement learning-based active perception approach that works by applying a series of transformation operations on the images (translation, zoom) in order to facilitate answering the question at hand. This allows for performing fine-grained analysis, effectively increasing the resolution at which the models process information. The proposed method is orthogonal to existing attention mechanisms and it can be combined with most existing VQA methods. The effectiveness of the proposed method is experimentally demonstrated on a challenging VQA dataset.

Using Scene Graphs for Detecting Visual Relationships

Anurag Tripathi, Siddharth Srivastava, Brejesh Lall, Santanu Chaudhury

Auto-TLDR; Relationship Detection using Context Aligned Scene Graph Embeddings

Abstract Slides Poster Similar

In this paper we solve the problem of detecting relationships between pairs of objects in an image. We develop spatially aware word embeddings using scene graphs and use joint feature representations containing visual, spatial and semantic embeddings from the input images to train a deep network on the task of relationship detection. Further, we propose to utilize context aligned scene graph embeddings from the train set, without requiring explicit availability of scene graphs at test time. We show that the proposed method outperforms the state-of-the-art methods for predicate detection and provides competing results on relationship detection. We also show the generalization ability of the proposed method by performing predictions under zero shot settings. Further, we also provide an exhaustive empirical evaluation on each component of the proposed network.

Graph Discovery for Visual Test Generation

Neil Hallonquist, Laurent Younes, Donald Geman

Auto-TLDR; Visual Question Answering over Graphs: A Probabilistic Framework for VQA

Abstract Slides Poster Similar

We consider the problem of uncovering an unknown attributed graph, where both its edges and vertices are hidden from view, through a sequence of binary questions about it. In order to select questions efficiently, we define a probability distribution over graphs, with randomness not just over edges, but over vertices as well. We then sequentially select questions so as to: (1) minimize the expected entropy of the random graph, given the answers to the previous questions in the sequence; and (2) to instantiate the vertices that compose the graph. We propose some basic question spaces, from which to select questions, that vary in their capacity. We apply this framework to the problem of test generation in Visual Question Answering (VQA), where semantic questions are used to evaluate vision systems over rich image representations. To do this, we use a restricted question vocabulary, resulting in image representations that take the form of scene graphs; by defining a distribution over them, a consistent set of probabilities is associated with the questions, and used in their selection.

Information Graphic Summarization Using a Collection of Multimodal Deep Neural Networks

Edward Kim, Connor Onweller, Kathleen F. Mccoy

Auto-TLDR; A multimodal deep learning framework that can generate summarization text supporting the main idea of an information graphic for presentation to blind or visually impaired

Abstract Slides Similar

We present a multimodal deep learning framework that can generate summarization text supporting the main idea of an information graphic for presentation to a person who is blind or visually impaired. The framework utilizes the visual, textual, positional, and size characteristics extracted from the image to create the summary. Different and complimentary neural architectures are optimized for each task using crowdsourced training data. From our quantitative experiments and results, we explain the reasoning behind our framework and show the effectiveness of our models. Our qualitative results showcase text generated from our framework and show that Mechanical Turk participants favor them to other automatic and human generated summarizations. We describe the design and of of an experiment to evaluate the utility of our system for people who have visual impairments in the context of understanding Twitter Tweets containing line graphs.

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

Yu Zhang, Xiaoyu Wu, Ruolin Zhu

Auto-TLDR; Adaptive Word Embedding Module for Object Detection

Abstract Slides Poster Similar

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 categories. We present the Adaptive Word Embedding Module, extracting the adaptive semantic knowledge graph to reach semantic consistency within one image. 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. Code will be made available.

Object Detection Using Dual Graph Network

Shengjia Chen, Zhixin Li, Feicheng Huang, Canlong Zhang, Huifang Ma

Auto-TLDR; A Graph Convolutional Network for Object Detection with Key Relation Information

Abstract Slides Similar

Most object detection methods focus only on the local information near the region proposal and ignore the object's global semantic relation and local spatial relation information, resulting in limited performance. To capture and explore these important relations, we propose a detection method based on a graph convolutional network (GCN). Two independent relation graph networks are used to obtain the global semantic information of the object in labels and the local spatial information in images. Semantic relation networks can implicitly acquire global knowledge, and by constructing a directed graph on the dataset, each node is represented by the word embedding of labels and then sent to the GCN to obtain high-level semantic representation. The spatial relation network encodes the relation by the positional relation module and the visual connection module, and enriches the object features through local key information from objects. The feature representation is further improved by aggregating the outputs of the two networks. Instead of directly disseminating visual features in the network, the dual-graph network explores more advanced feature information, giving the detector the ability to obtain key relations in labels and region proposals. Experiments on the PASCAL VOC and MS COCO datasets demonstrate that key relation information significantly improve the performance of detection with better ability to detect small objects and reasonable boduning box. The results on COCO dataset demonstrate our method obtains around 32.3% improvement on AP in terms of small objects.

VSR++: Improving Visual Semantic Reasoning for Fine-Grained Image-Text Matching

Hui Yuan, Yan Huang, Dongbo Zhang, Zerui Chen, Wenlong Cheng, Liang Wang

Auto-TLDR; Improving Visual Semantic Reasoning for Fine-Grained Image-Text Matching

Abstract Slides Poster Similar

Image-text matching has made great progresses recently, but there still remains challenges in fine-grained matching. To deal with this problem, we propose an Improved Visual Semantic Reasoning model (VSR++), which jointly models 1) global alignment between images and texts and 2) local correspondence between regions and words in a unified framework. To exploit their complementary advantages, we also develop a suitable learning strategy to balance their relative importance. As a result, our model can distinguish image regions and text words in a fine-grained level, and thus achieves the current stateof-the-art performance on two benchmark datasets.

Label Incorporated Graph Neural Networks for Text Classification

Yuan Xin, Linli Xu, Junliang Guo, Jiquan Li, Xin Sheng, Yuanyuan Zhou

Auto-TLDR; Graph Neural Networks for Semi-supervised Text Classification

Abstract Slides Poster Similar

Graph Neural Networks (GNNs) have achieved great success on graph-structured data, and their applications on traditional data structures such as natural language processing and semi-supervised text classification have been extensively explored in recent years. While previous works only consider the text information while building the graph, heterogeneous information such as labels is ignored. In this paper, we consider to incorporate the label information while building the graph by adding text-label-text paths, through which the supervision information will propagate among the graph more directly. Specifically, we treat labels as nodes in the graph which also contains text and word nodes, and then connect labels with texts belonging to that label. Through graph convolutions, label embeddings are jointly learned with text embeddings in the same latent semantic space. The newly incorporated label nodes will facilitate learning more accurate text embeddings by introducing the label information, and thus benefit the downstream text classification tasks. Extensive results on several benchmark datasets show that the proposed framework outperforms baseline methods by a significant margin.

Improving Visual Relation Detection Using Depth Maps

Sahand Sharifzadeh, Sina Moayed Baharlou, Max Berrendorf, Rajat Koner, Volker Tresp

Auto-TLDR; Exploiting Depth Maps for Visual Relation Detection

Abstract Slides Poster Similar

State-of-the-art visual relation detection methods mostly rely on object information extracted from RGB images such as 2D bounding boxes, feature maps, and predicted class probabilities. Depth maps can additionally provide valuable information on object relations, e.g. helping to detect not only spatial relations, such as standing behind, but also non-spatial relations, such as holding. In this work, we study the effect of using different object information with a focus on depth maps. To enable this study, we release a new synthetic dataset of depth maps, VG-Depth, as an extension to Visual Genome (VG). We also note that given the highly imbalanced distribution of relations in VG, typical evaluation metrics for visual relation detection cannot reveal improvements of under-represented relations. To address this problem, we propose using an additional metric, calling it Macro Recall@K, and demonstrate its remarkable performance on VG. Finally, our experiments confirm that by effective utilization of depth maps within a simple, yet competitive framework, the performance of visual relation detection can be improved by a margin of up to 8%.

Attentive Visual Semantic Specialized Network for Video Captioning

Jesus Perez-Martin, Benjamin Bustos, Jorge Pérez

Auto-TLDR; Adaptive Visual Semantic Specialized Network for Video Captioning

Abstract Slides Poster Similar

As an essential high-level task of video understanding topic, automatically describing a video with natural language has recently gained attention as a fundamental challenge in computer vision. Previous models for video captioning have several limitations, such as the existence of gaps in current semantic representations and the inexpressibility of the generated captions. To deal with these limitations, in this paper, we present a new architecture that we callAttentive Visual Semantic Specialized Network(AVSSN), which is an encoder-decoder model based on our Adaptive Attention Gate and Specialized LSTM layers. This architecture can selectively decide when to use visual or semantic information into the text generation process. The adaptive gate makes the decoder to automatically select the relevant information for providing a better temporal state representation than the existing decoders. Besides, the model is capable of learning to improve the expressiveness of generated captions attending to their length, using a sentence-length-related loss function. We evaluate the effectiveness of the proposed approach on the Microsoft Video Description(MSVD) and the Microsoft Research Video-to-Text (MSR-VTT) datasets, achieving state-of-the-art performance with several popular evaluation metrics: BLEU-4, METEOR, CIDEr, and ROUGE_L.

Exploring and Exploiting the Hierarchical Structure of a Scene for Scene Graph Generation

Ikuto Kurosawa, Tetsunori Kobayashi, Yoshihiko Hayashi

Auto-TLDR; A Hierarchical Model for Scene Graph Generation

Abstract Slides Poster Similar

The scene graph of an image is an explicit, concise representation of the image; hence, it can be used in various applications such as visual question answering or robot vision. We propose a novel neural network model for generating scene graphs that maintain global consistency, which prevents the generation of unrealistic scene graphs; the performance in the scene graph generation task is expected to improve. Our proposed model is used to construct a hierarchical structure whose leaf nodes correspond to objects depicted in the image, and a message is passed along the estimated structure on the fly. To this end, we aggregate features of all objects into the root node of the hierarchical structure, and the global context is back-propagated to the root node to maintain all the object nodes. The experimental results on the Visual Genome dataset indicate that the proposed model outperformed the existing models in scene graph generation tasks. We further qualitatively confirmed that the hierarchical structures captured by the proposed model seemed to be valid.

Reinforcement Learning with Dual Attention Guided Graph Convolution for Relation Extraction

Zhixin Li, Yaru Sun, Suqin Tang, Canlong Zhang, Huifang Ma

Auto-TLDR; Dual Attention Graph Convolutional Network for Relation Extraction

Abstract Slides Poster Similar

To better learn the dependency relationship between nodes, we address the relationship extraction task by capturing rich contextual dependencies based on the attention mechanism, and using distributional reinforcement learning to generate optimal relation information representation. This method is called Dual Attention Graph Convolutional Network (DAGCN), to adaptively integrate local features with their global dependencies. Specifically, we append two types of attention modules on top of GCN, which model the semantic interdependencies in spatial and relational dimensions respectively. The position attention module selectively aggregates the feature at each position by a weighted sum of the features at all positions of nodes internal features. Meanwhile, the relation attention module selectively emphasizes interdependent node relations by integrating associated features among all nodes. We sum the outputs of the two attention modules and use reinforcement learning to predict the classification of nodes relationship to further improve feature representation which contributes to more precise extraction results. The results on the TACRED and SemEval datasets show that the model can obtain more useful information for relational extraction tasks, and achieve better performances on various evaluation indexes.

Zero-Shot Text Classification with Semantically Extended Graph Convolutional Network

Tengfei Liu, Yongli Hu, Junbin Gao, Yanfeng Sun, Baocai Yin

Auto-TLDR; Semantically Extended Graph Convolutional Network for Zero-shot Text Classification

Abstract Slides Poster Similar

As a challenging task of Natural Language Processing(NLP), zero-shot text classification has attracted more and more attention recently. It aims to detect classes that the model has never seen in the training set. For this purpose, a feasible way is to construct connection between the seen and unseen classes by semantic extension and classify the unseen classes by information propagation over the connection. Although many related zero-shot text classification methods have been exploited, how to realize semantic extension properly and propagate information effectively is far from solved. In this paper, we propose a novel zero-shot text classification method called Semantically Extended Graph Convolutional Network (SEGCN). In the proposed method, the semantic category knowledge from ConceptNet is utilized to semantic extension for linking seen classes to unseen classes and constructing a graph of all classes. Then, we build upon Graph Convolutional Network (GCN) for predicting the textual classifier for each category, which transfers the category knowledge by the convolution operators on the constructed graph and is trained in a semi-supervised manner using the samples of the seen classes. The experimental results on Dbpedia and 20newsgroup datasets show that our method outperforms the state of the art zero-shot text classification methods.

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

Bang Yang, Yuexian Zou

Auto-TLDR; Visual Oriented Encoder for Video Captioning

Abstract Slides Poster Similar

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.

Context for Object Detection Via Lightweight Global and Mid-Level Representations

Mesut Erhan Unal, Adriana Kovashka

Auto-TLDR; Context-Based Object Detection with Semantic Similarity

Abstract Slides Poster Similar

We propose an approach for explicitly capturing context in object detection. We model visual and geometric relationships between object regions, but also model the global scene as a first-class participant. In contrast to prior approaches, both the context we rely on, as well as our proposed mechanism for belief propagation over regions, is lightweight. We also experiment with capturing similarities between regions at a semantic level, by modeling class co-occurrence and linguistic similarity between class names. We show that our approach significantly outperforms Faster R-CNN, and performs competitively with a much more costly approach that also models context.

Enhanced User Interest and Expertise Modeling for Expert Recommendation

Tongze He, Caili Guo, Yunfei Chu

Auto-TLDR; A Unified Framework for Expert Recommendation in Community Question Answering

Abstract Slides Poster Similar

The rapid development of Community Question Answering (CQA) satisfies users' request for professional and personal knowledge. In CQA, one key issue is to recommend users with high expertise and willingness to answer the given questions, namely expert recommendation. However, most of existing methods for expert recommendation ignore some key information, such as time information and historical feedback information, degrading the performance. On the one hand, users' interest are changing over time. It is biased if we don't consider the dynamics. On the other hand, feedback information is critical to estimate users' expertise. To solve these problems, we propose a unified framework for expert recommendation to exploit user interest and expertise more precisely. Considering the inconsistency between them, we propose to learn their embeddings separately. We leverage Long Short-Term Memory (LSTM) to model user's short-term interest and combine it with long-term interest. The user expertise is learned by the designed user expertise network, which explicitly models feedback on users' historical behavior. The extensive experiments on a large-scale dataset from a real-world CQA site demonstrate the superior performance of our method than state-of-the-art solutions to the problem.

Context Visual Information-Based Deliberation Network for Video Captioning

Min Lu, Xueyong Li, Caihua Liu

Auto-TLDR; Context visual information-based deliberation network for video captioning

Abstract Slides Poster Similar

Video captioning is to automatically and accurately generate a textual description for a video. The typical methods following the encoder-decoder architecture directly utilized hidden states to predict words. Nevertheless, these methods did not amend the inaccurate hidden states before feeding those states into word prediction. This led to a cascade of errors on generating word by word. In this paper, the context visual information-based deliberation network is proposed, abbreviated as CVI-DelNet. Its key idea is to introduce the deliberator into the encoder-decoder framework. The encoder-decoder firstly generates a raw hidden state sequence. Unlike the existing methods, the raw hidden state is no more directly used for word prediction but is fed into the deliberator to generate the refined hidden state. The words are then predicted according to the refined hidden states and the contextual visual features. Results on two datasets shows that the proposed method significantly outperforms the baselines.

MEAN: A Multi-Element Attention Based Network for Scene Text Recognition

Ruijie Yan, Liangrui Peng, Shanyu Xiao, Gang Yao, Jaesik Min

Auto-TLDR; Multi-element Attention Network for Scene Text Recognition

Abstract Slides Poster Similar

Scene text recognition is a challenging problem due to the wide variances in content, style, orientation, and image quality of text instances in natural scene images. To learn the intrinsic representation of scene texts, a novel multi-element attention (MEA) mechanism is proposed to exploit geometric structures from local to global levels in the feature map extracted from a scene text image. The MEA mechanism is a generalized form of self-attention technique with the incorporation of graph structure modeling. The elements in feature maps are taken as the nodes of an undirected graph, and three kinds of adjacency matrices are introduced to aggregating information at local, neighborhood and global levels before calculating the attention weights. If only the local adjacency matrix is used, the MEA mechanism degenerates to a self-attention form. A multi-element attention network (MEAN) is implemented which includes a CNN for feature extraction, an encoder with MEA mechanism and a decoder for predicting text codes. Orientation positional encoding information is further added to the feature map output by the CNN, and a feature sequence as the encoder's input is obtained by element-level decomposition of the feature map. Experimental results show that MEAN has achieved state-of-the-art or competitive performance on public English scene text datasets. Further experiments and analyses conducted on both English and Chinese scene text datasets show that MEAN can handle horizontal, vertical, and irregular scene text samples.

End-To-End Hierarchical Relation Extraction for Generic Form Understanding

Tuan Anh Nguyen Dang, Duc-Thanh Hoang, Quang Bach Tran, Chih-Wei Pan, Thanh-Dat Nguyen

Auto-TLDR; Joint Entity Labeling and Link Prediction for Form Understanding in Noisy Scanned Documents

Abstract Slides Poster Similar

Form understanding is a challenging problem which aims to recognize semantic entities from the input document and their hierarchical relations. Previous approaches face a significant difficulty dealing with the complexity of the task, thus treat these objectives separately. To this end, we present a novel deep neural network to jointly perform both Entity Labeling and link prediction in an end-to-end fashion. Our model extends the Multi-stage Attentional U-Net architecture with the Part-Intensity Fields and Part-Association Fields for link prediction, enriching the spatial information flow with the additional supervision from Entity Linking. We demonstrate the effectiveness of the model on the \textit{Form Understanding in Noisy Scanned Documents} \textit{(FUNSD)} dataset, where our method substantially outperforms the original model and state-of-the-art baselines in both Entity Labeling and Entity Linking task.

CKG: Dynamic Representation Based on Context and Knowledge Graph

Xunzhu Tang, Tiezhu Sun, Rujie Zhu

Auto-TLDR; CKG: Dynamic Representation Based on Knowledge Graph for Language Sentences

Abstract Slides Poster Similar

Recently, neural language representation models pre-trained on large corpus can capture rich co-occurrence information and be fine-tuned in downstream tasks to improve the performance. As a result, they have achieved state-of-the-art results in a large range of language tasks. However, there exists other valuable semantic information such as similar, opposite, or other possible meanings in external knowledge graphs (KGs). We argue that entities in KGs could be used to enhance the correct semantic meaning of language sentences. In this paper, we propose a new method CKG: Dynamic Representation Based on \textbf{C}ontext and \textbf{K}nowledge \textbf{G}raph. On the one side, CKG can extract rich semantic information of large corpus. On the other side, it can make full use of inside information such as co-occurrence in large corpus and outside information such as similar entities in KGs. We conduct extensive experiments on a wide range of tasks, including QQP, MRPC, SST-5, SQuAD, CoNLL 2003, and SNLI. The experiment results show that CKG achieves SOTA 89.2 on SQuAD compared with SAN (84.4), ELMo (85.8), and BERT$_{Base}$ (88.5).

ReADS: A Rectified Attentional Double Supervised Network for Scene Text Recognition

Qi Song, Qianyi Jiang, Xiaolin Wei, Nan Li, Rui Zhang

Auto-TLDR; ReADS: Rectified Attentional Double Supervised Network for General Scene Text Recognition

Abstract Slides Poster Similar

In recent years, scene text recognition is always regarded as a sequence-to-sequence problem. Connectionist Temporal Classification (CTC) and Attentional sequence recognition (Attn) are two very prevailing approaches to tackle this problem while they may fail in some scenarios respectively. CTC concentrates more on every individual character but is weak in text semantic dependency modeling. Attn based methods have better context semantic modeling ability while tends to overfit on limited training data. In this paper, we elaborately design a Rectified Attentional Double Supervised Network (ReADS) for general scene text recognition. To overcome the weakness of CTC and Attn, both of them are applied in our method but with different modules in two supervised branches which can make a complementary to each other. Moreover, effective spatial and channel attention mechanisms are introduced to eliminate background noise and extract valid foreground information. Finally, a simple rectified network is implemented to rectify irregular text. The ReADS can be trained end-to-end and only word-level annotations are required. Extensive experiments on various benchmarks verify the effectiveness of ReADS which achieves state-of-the-art performance.

More Correlations Better Performance: Fully Associative Networks for Multi-Label Image Classification

Yaning Li, Liu Yang

Auto-TLDR; Fully Associative Network for Fully Exploiting Correlation Information in Multi-Label Classification

Abstract Slides Poster Similar

Recent researches demonstrate that correlation modeling plays a key role in high-performance multi-label classification methods. However, existing methods do not take full advantage of correlation information, especially correlations in feature and label spaces of each image, which limits the performance of correlation-based multi-label classification methods. With more correlations considered, in this study, a Fully Associative Network (FAN) is proposed for fully exploiting correlation information, which involves both visual feature and label correlations. Specifically, FAN introduces a robust covariance pooling to summarize convolution features as global image representation for capturing feature correlation in the multi-label task. Moreover, it constructs an effective label correlation matrix based on a re-weighted scheme, which is fed into a graph convolution network for capturing label correlation. Then, correlation between covariance representations (i.e., feature correlation ) and the outputs of GCN (i.e., label correlation) are modeled for final prediction. Experimental results on two datasets illustrate the effectiveness and efficiency of our proposed FAN compared with state-of-the-art methods.

Global Context-Based Network with Transformer for Image2latex

Nuo Pang, Chun Yang, Xiaobin Zhu, Jixuan Li, Xu-Cheng Yin

Auto-TLDR; Image2latex with Global Context block and Transformer

Abstract Slides Poster Similar

Image2latex usually means converts mathematical formulas in images into latex markup. It is a very challenging job due to the complex two-dimensional structure, variant scales of input, and very long representation sequence. Many researchers use encoder-decoder based model to solve this task and achieved good results. However, these methods don't make full use of the structure and position information of the formula. %In this paper, we improve the encoder by employing Global Context block and Transformer. To solve this problem, we propose a global context-based network with transformer that can (1) learn a more powerful and robust intermediate representation via aggregating global features and (2) encode position information explicitly and (3) learn latent dependencies between symbols by using self-attention mechanism. The experimental results on the dataset IM2LATEX-100K demonstrate the effectiveness of our method.

Multi-Scale 2D Representation Learning for Weakly-Supervised Moment Retrieval

Ding Li, Rui Wu, Zhizhong Zhang, Yongqiang Tang, Wensheng Zhang

Auto-TLDR; Multi-scale 2D Representation Learning for Weakly Supervised Video Moment Retrieval

Abstract Slides Poster Similar

Video moment retrieval aims to search the moment most relevant to a given language query. However, most existing methods in this community often require temporal boundary annotations which are expensive and time-consuming to label. Hence weakly supervised methods have been put forward recently by only using coarse video-level label. Despite effectiveness, these methods usually process moment candidates independently, while ignoring a critical issue that the natural temporal dependencies between candidates in different temporal scales. To cope with this issue, we propose a Multi-scale 2D Representation Learning method for weakly supervised video moment retrieval. Specifically, we first construct a two-dimensional map for each temporal scale to capture the temporal dependencies between candidates. Two dimensions in this map indicate the start and end time points of these candidates. Then, we select top-K candidates from each scale-varied map with a learnable convolutional neural network. With a newly designed Moments Evaluation Module, we obtain the alignment scores of the selected candidates. At last, the similarity between captions and language query is served as supervision for further training the candidates' selector. Experiments on two benchmark datasets Charades-STA and ActivityNet Captions demonstrate that our approach achieves superior performance to state-of-the-art results.

Cross-Lingual Text Image Recognition Via Multi-Task Sequence to Sequence Learning

Zhuo Chen, Fei Yin, Xu-Yao Zhang, Qing Yang, Cheng-Lin Liu

Auto-TLDR; Cross-Lingual Text Image Recognition with Multi-task Learning

Abstract Slides Poster Similar

This paper considers recognizing texts shown in a source language and translating into a target language, without generating the intermediate source language text image recognition results. We call this problem Cross-Lingual Text Image Recognition (CLTIR). To solve this problem, we propose a multi-task system containing a main task of CLTIR and an auxiliary task of Mono-Lingual Text Image Recognition (MLTIR) simultaneously. Two different sequence to sequence learning methods, a convolution based attention model and a BLSTM model with CTC, are adopted for these tasks respectively. We evaluate the system on a newly collected Chinese-English bilingual movie subtitle image dataset. Experimental results demonstrate the multi-task learning framework performs superiorly in both languages.

Transformer-Encoder Detector Module: Using Context to Improve Robustness to Adversarial Attacks on Object Detection

Faisal Alamri, Sinan Kalkan, Nicolas Pugeault

Auto-TLDR; Context Module for Robust Object Detection with Transformer-Encoder Detector Module

Abstract Slides Poster Similar

Deep neural network approaches have demonstrated high performance in object recognition (CNN) and detection (Faster-RCNN) tasks, but experiments have shown that such architectures are vulnerable to adversarial attacks (FFF, UAP): low amplitude perturbations, barely perceptible by the human eye, can lead to a drastic reduction in labelling performance. This article proposes a new context module, called Transformer-Encoder Detector Module, that can be applied to an object detector to (i) improve the labelling of object instances; and (ii) improve the detector's robustness to adversarial attacks. The proposed model achieves higher mAP, F1 scores and AUC average score of up to 13\% compared to the baseline Faster-RCNN detector, and an mAP score 8 points higher on images subjected to FFF or UAP attacks. The result demonstrates that a simple ad-hoc context module can improve the reliability of object detectors significantly

PIN: A Novel Parallel Interactive Network for Spoken Language Understanding

Peilin Zhou, Zhiqi Huang, Fenglin Liu, Yuexian Zou

Auto-TLDR; Parallel Interactive Network for Spoken Language Understanding

Abstract Slides Poster Similar

Spoken Language Understanding (SLU) is an essential part of the spoken dialogue system, which typically consists of intent detection (ID) and slot filling (SF) tasks. Recently, recurrent neural networks (RNNs) based methods achieved the state-of-the-art for SLU. It is noted that, in the existing RNN-based approaches, ID and SF tasks are often jointly modeled to utilize the correlation information between them. However, we noted that, so far, the efforts to obtain better performance by supporting bidirectional and explicit information exchange between ID and SF are not well studied. In addition, few studies attempt to capture the local context information to enhance the performance of SF. Motivated by these findings, in this paper, Parallel Interactive Network (PIN) is proposed to model the mutual guidance between ID and SF. Specifically, given an utterance, a Gaussian self-attentive encoder is introduced to generate the context-aware feature embedding of the utterance which is able to capture local context information. Taking the feature embedding of the utterance, Slot2Intent module and Intent2Slot module are developed to capture the bidirectional information flow for ID and SF tasks. Finally, a cooperation mechanism is constructed to fuse the information obtained from Slot2Intent and Intent2Slot modules to further reduce the prediction bias. The experiments on two benchmark datasets, i.e., SNIPS and ATIS, demonstrate the effectiveness of our approach, which achieves a competitive result with state-of-the-art models. More encouragingly, by using the feature embedding of the utterance generated by the pre-trained language model BERT, our method achieves the state-of-the-art among all comparison approaches.

Multimodal Side-Tuning for Document Classification

Stefano Zingaro, Giuseppe Lisanti, Maurizio Gabbrielli

Auto-TLDR; Side-tuning for Multimodal Document Classification

Abstract Slides Poster Similar

In this paper, we propose to exploit the side-tuning framework for multimodal document classification. Side-tuning is a methodology for network adaptation recently introduced to solve some of the problems related to previous approaches. Thanks to this technique it is actually possible to overcome model rigidity and catastrophic forgetting of transfer learning by fine-tuning. The proposed solution uses off-the-shelf deep learning architectures leveraging the side-tuning framework to combine a base model with a tandem of two side networks. We show that side-tuning can be successfully employed also when different data sources are considered, e.g. text and images in document classification. The experimental results show that this approach pushes further the limit for document classification accuracy with respect to the state of the art.

Edge-Aware Graph Attention Network for Ratio of Edge-User Estimation in Mobile Networks

Jiehui Deng, Sheng Wan, Xiang Wang, Enmei Tu, Xiaolin Huang, Jie Yang, Chen Gong

Auto-TLDR; EAGAT: Edge-Aware Graph Attention Network for Automatic REU Estimation in Mobile Networks

Abstract Slides Poster Similar

Estimating the Ratio of Edge-Users (REU) is an important issue in mobile networks, as it helps the subsequent adjustment of loads in different cells. However, existing approaches usually determine the REU manually, which are experience-dependent and labor-intensive, and thus the estimated REU might be imprecise. Considering the inherited graph structure of mobile networks, in this paper, we utilize a graph-based deep learning method for automatic REU estimation, where the practical cells are deemed as nodes and the load switchings among them constitute edges. Concretely, Graph Attention Network (GAT) is employed as the backbone of our method due to its impressive generalizability in dealing with networked data. Nevertheless, conventional GAT cannot make full use of the information in mobile networks, since it only incorporates node features to infer the pairwise importance and conduct graph convolutions, while the edge features that are actually critical in our problem are disregarded. To accommodate this issue, we propose an Edge-Aware Graph Attention Network (EAGAT), which is able to fuse the node features and edge features for REU estimation. Extensive experimental results on two real-world mobile network datasets demonstrate the superiority of our EAGAT approach to several state-of-the-art methods.

Weakly Supervised Attention Rectification for Scene Text Recognition

Chengyu Gu, Shilin Wang, Yiwei Zhu, Zheng Huang, Kai Chen

Auto-TLDR; An auxiliary supervision branch for attention-based scene text recognition

Abstract Slides Poster Similar

Scene text recognition has become a hot topic in recent years due to its booming real-life applications. Attention-based encoder-decoder framework has become one of the most popular frameworks especially in the irregular text scenario. However, the “attention drift” problem reduces the recognition performance for most existing attention-based scene text recognition methods. To solve this problem, we propose an auxiliary supervision branch along with the attention-based encoder-decoder framework. A new loss function is designed to refine the feature map and to help the attention region align the target character area. Compared with existing attention rectification mechanisms, our method does not require character-level annotations or introduce any additional trainable parameter. Furthermore, our method can improve the performance for both RNN-Attention and Scaled Dot-Product Attention. The experiment results on various benchmarks have demonstrated that the proposed approach outperforms the state-of-the-art methods in both regular and irregular text recognition scenarios.

Detective: An Attentive Recurrent Model for Sparse Object Detection

Amine Kechaou, Manuel Martinez, Monica Haurilet, Rainer Stiefelhagen

Auto-TLDR; Detective: An attentive object detector that identifies objects in images in a sequential manner

Abstract Slides Poster Similar

In this work, we present Detective – an attentive object detector that identifies objects in images in a sequential manner. Our network is based on an encoder-decoder architecture, where the encoder is a convolutional neural network, and the decoder is a convolutional recurrent neural network coupled with an attention mechanism. At each iteration, our decoder focuses on the relevant parts of the image using an attention mechanism, and then estimates the object’s class and the bounding box coordinates. Current object detection models generate dense predictions and rely on post-processing to remove duplicate predictions. Detective is a sparse object detector that generates a single bounding box per object instance. However, training a sparse object detector is challenging, as it requires the model to reason at the instance level and not just at the class and spatial levels. We propose a training mechanism based on the Hungarian Algorithm and a loss that balances the localization and classification tasks. This allows Detective to achieve promising results on the PASCAL VOC object detection dataset. Our experiments demonstrate that sparse object detection is possible and has a great potential for future developments in applications where the order of the objects to be predicted is of interest.

Text Synopsis Generation for Egocentric Videos

Aidean Sharghi, Niels Lobo, Mubarak Shah

Auto-TLDR; Egocentric Video Summarization Using Multi-task Learning for End-to-End Learning

Abstract Slides Similar

Mass utilization of body-worn cameras has led to a huge corpus of available egocentric video. Existing video summarization algorithms can accelerate browsing such videos by selecting (visually) interesting shots from them. Nonetheless, since the system user still has to watch the summary videos, browsing large video databases remain a challenge. Hence, in this work, we propose to generate a textual synopsis, consisting of a few sentences describing the most important events in a long egocentric videos. Users can read the short text to gain insight about the video, and more importantly, efficiently search through the content of a large video database using text queries. Since egocentric videos are long and contain many activities and events, using video-to-text algorithms results in thousands of descriptions, many of which are incorrect. Therefore, we propose a multi-task learning scheme to simultaneously generate descriptions for video segments and summarize the resulting descriptions in an end-to-end fashion. We Input a set of video shots and the network generates a text description for each shot. Next, visual-language content matching unit that is trained with a weakly supervised objective, identifies the correct descriptions. Finally, the last component of our network, called purport network, evaluates the descriptions all together to select the ones containing crucial information. Out of thousands of descriptions generated for the video, a few informative sentences are returned to the user. We validate our framework on the challenging UT Egocentric video dataset, where each video is between 3 to 5 hours long, associated with over 3000 textual descriptions on average. The generated textual summaries, including only 5 percent (or less) of the generated descriptions, are compared to groundtruth summaries in text domain using well-established metrics in natural language processing.