Human pose estimation (HPE) is one of the most challenging tasks in computer vision as humans are deformable by nature and thus their pose has so much variance. HPE aims to correctly identify the main joint locations of a single person or multiple people in a given image or video. Locating joints of a person in images or videos is an important task that can be applied in action recognition and object tracking. As have many computer vision tasks, HPE has advanced massively with the introduction of deep learning to the field. In this paper, we focus on one of the deep learning-based approaches of HPE proposed by Newell et al., which they named the stacked hourglass network. Their approach is widely used in many applications and is regarded as one of the best works in this area. The main focus of their approach is to capture as much information as it can at all possible scales so that a coherent understanding of the local features and full-body location is achieved. Their findings demonstrate that important cues such as orientation of a person, arrangement of limbs, and adjacent joints' relative location can be identified from multiple scales at different resolutions. To do so, they makes use of a single pipeline to process images in multiple resolutions, which comprises a skip layer to not lose spatial information at each resolution. The resolution of the images stretches as lower as 4x4 to make sure that a smaller spatial feature is included. In this study, we study the effect of architectural modifications on the computational speed and accuracy of the network.
The demosaicking provokes the spatial and color correlation of noise, which is afterwards enhanced by the imaging pipeline. The correct removal previous or simultaneously with the demosaicking process is not usually considered in the literature. We present a novel imaging chain including a denoising of the Bayer CFA and a demosaicking method for image sequences. The proposed algorithm uses a spatio-temporal patch method for the noise removal and demosaicking of the CFA. The experimentation, including real examples, illustrates the superior performance of the proposed chain, avoiding the creation of artifacts and colored spots in the final image.
As one of the fundamental techniques for image editing, image cropping discards unrelevant contents and remains the pleasing portions of the image to enhance the overall composition and achieve better visual/aesthetic perception. In this paper, we primarily focus on improving the accuracy of automatic image cropping, and on further exploring its potential in public datasets with high efficiency. From this respect, we propose a deep learning based framework to learn the objects composition from photos with high aesthetic qualities, where an anchor region is detected through a convolutional neural network (CNN) with the Gaussian kernel to maintain the interested objects' integrity. This initial detected anchor area is then fed into a light weighted regression network to obtain the final cropping result. Unlike the conventional methods that multiple candidates are proposed and evaluated iteratively, only a single anchor region is produced in our model, which is mapped to the final output directly. Thus, low computational resources are required for the proposed approach. The experimental results on the public datasets show that both cropping accuracy and efficiency achieve the state-ofthe-art performances.
Visual Question Answering (VQA) is of tremendous interest to the research community with important applications such as aiding visually impaired users and image-based search. In this work, we explore the use of scene graphs for solving the VQA task. We conduct experiments on the GQA dataset which presents a challenging set of questions requiring counting, compositionality and advanced reasoning capability, and provides scene graphs for a large number of images. We adopt image + question architectures for use with scene graphs, evaluate various scene graph generation techniques for unseen images, propose a training curriculum to leverage human-annotated and auto-generated scene graphs, and build late fusion architectures to learn from multiple image representations. We present a multi-faceted study into the use of scene graphs for VQA, making this work the first of its kind.
Visual grounding is a promising path toward more robust and accurate Natural Language Processing (NLP) models. Many multimodal extensions of BERT (e.g., VideoBERT, LXMERT, VL-BERT) allow a joint modeling of texts and images that lead to state-of-the-art results on multimodal tasks such as Visual Question Answering. Here, we leverage multimodal modeling for purely textual tasks (language modeling and classification) with the expectation that the multimodal pretraining provides a grounding that can improve text processing accuracy. We propose possible strategies in this respect. A first type of strategy, referred to as {\it transferred grounding} consists in applying multimodal models to text-only tasks using a placeholder to replace image input. The second one, which we call {\it associative grounding}, harnesses image retrieval to match texts with related images during both pretraining and text-only downstream tasks. We draw further distinctions into both strategies and then compare them according to their impact on language modeling and commonsense-related downstream tasks, showing improvement over text-only baselines.
Zero-shot learning, the task of learning to recognize new classes not seen during training, has received considerable attention in the case of 2D image classification. However, despite the increasing ubiquity of 3D sensors, the corresponding 3D point cloud classification problem has not been meaningfully explored and introduces new challenges. In this paper, we identify some of the challenges and apply 2D Zero-Shot Learning (ZSL) methods in the 3D domain to analyze the performance of existing models. Then, we propose a novel approach to address the issues specific to 3D ZSL. We first present an inductive ZSL process and then extend it to the transductive ZSL and Generalized ZSL (GZSL) settings for 3D point cloud classification. To this end, a novel loss function is developed that simultaneously aligns seen semantics with point cloud features and takes advantage of unlabeled test data to address some known issues (e.g., the problems of domain adaptation, hubness, and data bias). While designed for the particularities of 3D point cloud classification, the method is shown to also be applicable to the more common use-case of 2D image classification. An extensive set of experiments is carried out, establishing state-of-the-art for ZSL and GZSL on synthetic (ModelNet40, ModelNet10, McGill) and real (ScanObjectNN) 3D point cloud datasets.
Currently, deep learning methods have been widely applied in and thus promoted the development of different fields. In the financial accounting field, the rapid increase in the number of financial tickets dramatically increases labor costs; hence, using a deep learning method to relieve the pressure on accounting is necessary. At present, a few works have applied deep learning methods to financial ticket recognition. However, first, their approaches only cover a few types of tickets. In addition, the precision and speed of their recognition models cannot meet the requirements of practical financial accounting systems. Moreover, none of the methods provides a detailed analysis of both the types and content of tickets. Therefore, this paper first analyzes the different features of 482 kinds of financial tickets, divides all kinds of financial tickets into three categories and proposes different recognition patterns for each category. These recognition patterns can meet almost all types of financial ticket recognition needs. Second, regarding the fixed format types of financial tickets (accounting for 68.27\% of the total types of tickets), we propose a simple yet efficient network named the Financial Ticket Faster Detection network (FTFDNet) based on a Faster RCNN. Furthermore, according to the characteristics of the financial ticket text, in order to obtain higher recognition accuracy, the loss function, Region Proposal Network (RPN), and Non-Maximum Suppression (NMS) are improved to make FTFDNet focus more on text. Finally, we perform a comparison with the best ticket recognition model from the ICDAR2019 invoice competition. The experimental results illustrate that FTFDNet increases the processing speed by 50\% while maintaining similar precision.
In this paper a new formulation of event recognition task is examined: it is required to predict event categories in a gallery of images, for which albums (groups of photos corresponding to a single event) are unknown. We propose the novel two-stage approach. At first, features are extracted in each photo using the pre-trained convolutional neural network. These features are classified individually. The scores of the classifier are used to group sequential photos into several clusters. Finally, the features of photos in each group are aggregated into a single descriptor using neural attention mechanism. This algorithm is optionally extended to improve the accuracy for classification of each image in an album. In contrast to conventional fine-tuning of convolutional neural networks (CNN) we proposed to use image captioning, i.e., generative model that converts images to textual descriptions. They are one-hot encoded and summarized into sparse feature vector suitable for learning of arbitrary classifier. Experimental study with Photo Event Collection and Multi-Label Curation of Flickr Events Dataset demonstrates that our approach is 9-20% more accurate than event recognition on single photos. Moreover, proposed method has 13-16% lower error rate than classification of groups of photos obtained with hierarchical clustering. It is experimentally shown that the image captions trained on Conceptual Captions dataset can be classified more accurately than the features from object detector, though they both are obviously not as rich as the CNN-based features. However, it is possible to combine our approach with conventional CNNs in an ensemble to provide the state-of-the-art results for several event datasets.
The data distribution commonly evolves over time leading to problems such as concept drift that often decrease classifier performance. We seek to predict unseen data (and their labels) allowing us to tackle challenges due to a non-constant data distribution in a \emph{proactive} manner rather than detecting and reacting to already existing changes that might already have led to errors. To this end, we learn a domain transformer in an unsupervised manner that allows generating data of unseen domains. Our approach first matches independently learned latent representations of two given domains obtained from an auto-encoder using a Cycle-GAN. In turn, a transformation of the original samples can be learned that can be applied iteratively to extrapolate to unseen domains. Our evaluation on CNNs on image data confirms the usefulness of the approach. It also achieves very good results on the well-known problem of unsupervised domain adaption, where labels but not samples have to be predicted.
This work develops and demonstrates the integration of the SCAMP-5d vision system into the CoppeliaSim robot simulator, creating a semi-simulated environment. By configuring a camera in the simulator and setting up communication with the SCAMP python host through remote API, sensor images from the simulator can be transferred to the SCAMP vision sensor, where on-sensor image processing such as CNN inference can be performed. SCAMP output is then fed back into CoppeliaSim. This proposed platform integration enables rapid prototyping validations of SCAMP algorithms for robotic systems. We demonstrate a car localisation and tracking task using this proposed semi-simulated platform, with a CNN inference on SCAMP to command the motion of a robot. We made this platform available online.