Abstract: Structured text extraction is one of the most valuable and challenging application directions in the field of Document AI. However, the scenarios of past benchmarks are limited, and the corresponding evaluation protocols usually focus on the submodules of the structured text extraction scheme. In order to eliminate these problems, we organized the ICDAR 2023 competition on Structured text extraction from Visually-Rich Document images (SVRD). We set up two tracks for SVRD including Track 1: HUST-CELL and Track 2: Baidu-FEST, where HUST-CELL aims to evaluate the end-to-end performance of Complex Entity Linking and Labeling, and Baidu-FEST focuses on evaluating the performance and generalization of Zero-shot/Few-shot Structured Text extraction from an end-to-end perspective. Compared to the current document benchmarks, our two tracks of competition benchmark enriches the scenarios greatly and contains more than 50 types of visually-rich document images (mainly from the actual enterprise applications). The competition opened on 30th December, 2022 and closed on 24th March, 2023. There are 35 participants and 91 valid submissions received for Track 1, and 15 participants and 26 valid submissions received for Track 2. In this report we will presents the motivation, competition datasets, task definition, evaluation protocol, and submission summaries. According to the performance of the submissions, we believe there is still a large gap on the expected information extraction performance for complex and zero-shot scenarios. It is hoped that this competition will attract many researchers in the field of CV and NLP, and bring some new thoughts to the field of Document AI.

Abstract: Structural Health Monitoring (SHM) has greatly benefited from computer vision. Recently, deep learning approaches are widely used to accurately estimate the state of deterioration of infrastructure. In this work, we focus on the problem of bridge surface structural damage detection, such as delamination and rebar exposure. It is well known that the quality of a deep learning model is highly dependent on the quality of the training dataset. Bridge damage detection, our application domain, has the following main challenges: (i) labeling the damages requires knowledgeable civil engineering professionals, which makes it difficult to collect a large annotated dataset; (ii) the damage area could be very small, whereas the background area is large, which creates an unbalanced training environment; (iii) due to the difficulty to exactly determine the extension of the damage, there is often a variation among different labelers who perform pixel-wise labeling. In this paper, we propose a novel model for bridge structural damage detection to address the first two challenges. This paper follows the idea of an atrous spatial pyramid pooling (ASPP) module that is designed as a novel network for bridge damage detection. Further, we introduce the weight balanced Intersection over Union (IoU) loss function to achieve accurate segmentation on a highly unbalanced small dataset. The experimental results show that (i) the IoU loss function improves the overall performance of damage detection, as compared to cross entropy loss or focal loss, and (ii) the proposed model has a better ability to detect a minority class than other light segmentation networks.

Abstract: Despite its wide applications in criminal investigations and clinical communications with patients suffering from autism, automatic micro-expression recognition remains a challenging problem because of the lack of training data and imbalanced classes problems. In this study, we proposed a meta-learning-based multi-model fusion network (Meta-MMFNet) to solve the existing problems. The proposed method is based on the metric-based meta-learning pipeline, which is specifically designed for few-shot learning and is suitable for model-level fusion. The frame difference and optical flow features were fused, deep features were extracted from the fused feature, and finally in the meta-learning-based framework, weighted sum model fusion method was applied for micro-expression classification. Meta-MMFNet achieved better results than state-of-the-art methods on four datasets. The code is available at https://github.com/wenjgong/meta-fusion-based-method.

Abstract: Human pose estimation refers to the estimation of the location of body parts and how they are connected in an image. Human pose estimation from monocular images has wide applications (e.g., image indexing). Several surveys on human pose estimation can be found in the literature, but they focus on a certain category; for example, model-based approaches or human motion analysis, etc. As far as we know, an overall review of this problem domain has yet to be provided. Furthermore, recent advancements based on deep learning have brought novel algorithms for this problem. In this paper, a comprehensive survey of human pose estimation from monocular images is carried out including milestone works and recent advancements. Based on one standard pipeline for the solution of computer vision problems, this survey splits the problem into several modules: feature extraction and description, human body models, and modeling
methods. Problem modeling methods are approached based on two means of categorization in this survey. One way to categorize includes top-down and bottom-up methods, and another way includes generative and discriminative methods. Considering the fact that one direct application of human pose estimation is to provide initialization for automatic video surveillance, there are additional sections for motion-related methods in all modules: motion features, motion models, and motion-based methods. Finally, the paper also collects 26 publicly available data sets for validation and provides error measurement methods that are frequently used.

Abstract: We present a novel method for human action recognition (HAR) based on estimated poses from image sequences. We use 3D human pose data as additional information and propose a compact human pose representation, called a weak pose, in a low-dimensional space while still keeping the most discriminative information for a given pose. With predicted poses from image features, we map the problem from image feature space to pose space, where a Bag of Poses (BOP) model is learned for the final goal of HAR. The BOP model is a modified version of the classical bag of words pipeline by building the vocabulary based on the most representative weak poses for a given action. Compared with the standard k-means clustering, our vocabulary selection criteria is proven to be more efficient and robust against the inherent challenges of action recognition. Moreover, since for action recognition the ordering of the poses is discriminative, the BOP model incorporates temporal information: in essence, groups of consecutive poses are considered together when computing the vocabulary and assignment. We tested our method on two well-known datasets: HumanEva and IXMAS, to demonstrate that weak poses aid to improve action recognition accuracies. The proposed method is scene-independent and is comparable with the state-of-art method.