Abstract: The task of image-text matching aims to map representations from different modalities into a common joint visual-textual embedding. However, the most widely used datasets for this task, MSCOCO and Flickr30K, are actually image captioning datasets that offer a very limited set of relationships between images and sentences in their ground-truth annotations. This limited ground truth information forces us to use evaluation metrics based on binary relevance: given a sentence query we consider only one image as relevant. However, many other relevant images or captions may be present in the dataset. In this work, we propose two metrics that evaluate the degree of semantic relevance of retrieved items, independently of their annotated binary relevance. Additionally, we incorporate a novel strategy that uses an image captioning metric, CIDEr, to define a Semantic Adaptive Margin (SAM) to be optimized in a standard triplet loss. By incorporating our formulation to existing models, a large improvement is obtained in scenarios where available training data is limited. We also demonstrate that the performance on the annotated image-caption pairs is maintained while improving on other non-annotated relevant items when employing the full training set. The code for our new metric can be found at github. com/furkanbiten/ncsmetric and the model implementation at github. com/andrespmd/semanticadaptive_margin.

Abstract: This paper presents a complete pipeline to perform deep learning-based instance segmentation of different types of grains (e.g., corn, sunflower, soybeans, lentils, chickpeas, mote, and beans). The proposed approach consists of using synthesized image datasets for the training process, which are easily generated according to the category of the instance to be segmented. The synthesized imaging process allows generating a large set of well-annotated grain samples with high variability—as large and high as the user requires. Instance segmentation is performed through a popular deep learning based approach, the Mask R-CNN architecture, but any learning-based instance segmentation approach can be considered. Results obtained by the proposed pipeline show that the strategy of using synthesized image datasets for training instance segmentation helps to avoid the time-consuming image annotation stage, as well as to achieve higher intersection over union and average precision performances. Results obtained with different varieties of grains are shown, as well as comparisons with manually annotated images, showing both the simplicity of the process and the improvements in the performance.

Abstract: Praxis test is a gesture-based diagnostic test which has been accepted as diagnostically indicative of cortical pathologies such as Alzheimer’s disease. Despite being simple, this test is oftentimes skipped by the clinicians. In this paper, we propose a novel framework to investigate the potential of static and dynamic upper-body gestures based on the Praxis test and their potential in a medical framework to automatize the test procedures for computer-assisted cognitive assessment of older adults.
In order to carry out gesture recognition as well as correctness assessment of the performances we have recollected a novel challenging RGB-D gesture video dataset recorded by Kinect v2, which contains 29 specific gestures suggested by clinicians and recorded from both experts and patients performing the gesture set. Moreover, we propose a framework to learn the dynamics of upper-body gestures, considering the videos as sequences of short-term clips of gestures. Our approach first uses body part detection to extract image patches surrounding the hands and then, by means of a fine-tuned convolutional neural network (CNN) model, it learns deep hand features which are then linked to a long short-term memory to capture the temporal dependencies between video frames.
We report the results of four developed methods using different modalities. The experiments show effectiveness of our deep learning based approach in gesture recognition and performance assessment tasks. Satisfaction of clinicians from the assessment reports indicates the impact of framework corresponding to the diagnosis.

Abstract: This work investigates the problem of sketch-guided object localization (SGOL), where human sketches are used as queries to conduct the object localization in natural images. In this cross-modal setting, we first contribute with a tough-to-beat baseline that without any specific SGOL training is able to outperform the previous works on a fixed set of classes. The baseline is useful to analyze the performance of SGOL approaches based on available simple yet powerful methods. We advance prior arts by proposing a sketch-conditioned DETR (DEtection TRansformer) architecture which avoids a hard classification and alleviates the domain gap between sketches and images to localize object instances. Although the main goal of SGOL is focused on object detection, we explored its natural extension to sketch-guided instance segmentation. This novel task allows to move towards identifying the objects at pixel level, which is of key importance in several applications. We experimentally demonstrate that our model and its variants significantly advance over previous state-of-the-art results. All training and testing code of our model will be released to facilitate future researchhttps://github.com/priba/sgol_wild.

Abstract: One of the major prerequisites for any deep learning approach is the availability of large-scale training data. When dealing with scanned document images in real world scenarios, the principal information of its content is stored in the layout itself. In this work, we have proposed an automated deep generative model using Graph Neural Networks (GNNs) to generate synthetic data with highly variable and plausible document layouts that can be used to train document interpretation systems, in this case, specially in digital mailroom applications. It is also the first graph-based approach for document layout generation task experimented on administrative document images, in this case, invoices.

Abstract: Document images can be affected by many degradation scenarios, which cause recognition and processing difficulties. In this age of digitization, it is important to denoise them for proper usage. To address this challenge, we present a new encoder-decoder architecture based on vision transformers to enhance both machine-printed and handwritten document images, in an end-to-end fashion. The encoder operates directly on the pixel patches with their positional information without the use of any convolutional layers, while the decoder reconstructs a clean image from the encoded patches. Conducted experiments show a superiority of the proposed model compared to the state-of the-art methods on several DIBCO benchmarks. Code and models will be publicly available at: https://github.com/dali92002/DocEnTR

Abstract: A signed distance function (SDF) as the 3D shape description is one of the most effective approaches to represent 3D geometry for rendering and reconstruction. Our work is inspired by the state-of-the-art method DeepSDF [17] that learns and analyzes the 3D shape as the iso-surface of its shell and this method has shown promising results especially in the 3D shape reconstruction and compression domain. In this paper, we consider the degeneration problem of reconstruction coming from the capacity decrease of the DeepSDF model, which approximates the SDF with a neural network and a single latent code. We propose Local Geometry Code Learning (LGCL), a model that improves the original DeepSDF results by learning from a local shape geometry of the full 3D shape. We add an extra graph neural network to split the single transmittable latent code into a set of local latent codes distributed on the 3D shape. Mentioned latent codes are used to approximate the SDF in their local regions, which will alleviate the complexity of the approximation compared to the original DeepSDF. Furthermore, we introduce a new geometric loss function to facilitate the training of these local latent codes. Note that other local shape adjusting methods use the 3D voxel representation, which in turn is a problem highly difficult to solve or even is insolvable. In contrast, our architecture is based on graph processing implicitly and performs the learning regression process directly in the latent code space, thus make the proposed architecture more flexible and also simple for realization. Our experiments on 3D shape reconstruction demonstrate that our LGCL method can keep more details with a significantly smaller size of the SDF decoder and outperforms considerably the original DeepSDF method under the most important quantitative metrics.