Computer Science

Recently, Zero-shot Sketch-based Image Retrieval (ZS-SBIR) has attracted the attention of the computer vision community due to it's real-world applications, and the more realistic and challenging setting than found in SBIR. ZS-SBIR inherits the main challenges of multiple computer vision problems including content-based Image Retrieval (CBIR), zero-shot learning and domain adaptation. The majority of previous studies using deep neural networks have achieved improved results through either projecting sketch and images into a common low-dimensional space or transferring knowledge from seen to unseen classes. However, those approaches are trained with complex frameworks composed of multiple deep convolutional neural networks (CNNs) and are dependent on category-level word labels. This increases the requirements on training resources and datasets. In comparison, we propose a simple and efficient framework that does not require high computational training resources, and can be trained on datasets without semantic categorical labels. Furthermore, at training and inference stages our method only uses a single CNN. In this work, a pre-trained ImageNet CNN (e.g., ResNet50) is fine-tuned with three proposed learning objects: domain-aware quadruplet loss, semantic classification loss, and semantic knowledge preservation loss. The domain-aware quadruplet and semantic classification losses are introduced to learn discriminative, semantic and domain invariant features through considering ZS-SBIR as object detection and verification problem. ...

Affective Computing has recently attracted the attention of the research community, due to its numerous applications in diverse areas. In this context, the emergence of video-based data allows to enrich the widely used spatial features with the inclusion of temporal information. However, such spatio-temporal modelling often results in very high-dimensional feature spaces and large volumes of data, making training difficult and time consuming. This paper addresses these shortcomings by proposing a novel model that efficiently extracts both spatial and temporal features of the data by means of its enhanced temporal modelling based on latent features. Our proposed model consists of three major networks, coined Generator, Discriminator, and Combiner, which are trained in an adversarial setting combined with curriculum learning to enable our adaptive attention modules. In our experiments, we show the effectiveness of our approach by reporting our competitive results on both the AFEW-VA and SEWA datasets, suggesting that temporal modelling improves the affect estimates both in qualitative and quantitative terms. Furthermore, we find that the inclusion of attention mechanisms leads to the highest accuracy improvements, as its weights seem to correlate well with the appearance of facial movements, both in terms of temporal localisation and intensity. Finally, we observe the sequence length of around 160\,ms to be the optimum one for temporal modelling, which is consistent with other relevant findings utilising similar lengths.

We proposed a new modeling method to promote the performance of prohibited items recognition via X-ray image. We analyzed the characteristics of prohibited items and X-ray images. We found the fact that the scales of some items are too small to be recognized which encumber the model performance. Then we adopted a set of data augmentation and modified the model to adapt the field of prohibited items recognition. The Convolutional Block Attention Module(CBAM) and rescoring mechanism has been assembled into the model. By the modification, our model achieved a mAP of 89.9% on SIXray10, mAP of 74.8%.

In this work, we present a novel methodology for texture image recognition using a partial differential equation modeling. More specifically, we employ the pseudo-parabolic Buckley-Leverett equation to provide a dynamics to the digital image representation and collect local descriptors from those images evolving in time. For the local descriptors we employ the magnitude and signal binary patterns and a simple histogram of these features was capable of achieving promising results in a classification task. We compare the accuracy over well established benchmark texture databases and the results demonstrate competitiveness, even with the most modern deep learning approaches. The achieved results open space for future investigation on this type of modeling for image analysis, especially when there is no large amount of data for training deep learning models and therefore model-based approaches arise as suitable alternatives.

Binocular stereo vision is an important branch of machine vision, which imitates the human eye and matches the left and right images captured by the camera based on epipolar constraints. The matched disparity map can be calculated according to the camera imaging model to obtain a depth map, and then the depth map is converted to a point cloud image to obtain spatial point coordinates, thereby achieving the purpose of ranging. However, due to the influence of illumination under water, the captured images no longer meet the epipolar constraints, and the changes in imaging models make traditional calibration methods no longer applicable. Therefore, this paper proposes a new underwater real-time calibration method and a matching method based on the best search domain to improve the accuracy of underwater distance measurement using binoculars.

Interpolation and internal painting are one of the basic approaches in image internal painting, which is used to eliminate undesirable parts that occur in digital images or to enhance faulty parts. This study was designed to compare the interpolation algorithms used in image in-painting in the literature. Errors and noise generated on the colour and grayscale formats of some of the commonly used standard images in the literature were corrected by using Cubic, Kriging, Radial based function and High dimensional model representation approaches and the results were compared using standard image comparison criteria, namely, PSNR (peak signal-to-noise ratio), SSIM (Structural SIMilarity), Mean Square Error (MSE). According to the results obtained from the study, the absolute superiority of the methods against each other was not observed. However, Kriging and RBF interpolation give better results both for numerical data and visual evaluation for image in-painting problems with large area losses.

When the input to a deep neural network (DNN) is a video signal, a sequence of feature tensors is produced at the intermediate layers of the model. If neighboring frames of the input video are related through motion, a natural question is, "what is the relationship between the corresponding feature tensors?" By analyzing the effect of common DNN operations on optical flow, we show that the motion present in each channel of a feature tensor is approximately equal to the scaled version of the input motion. The analysis is validated through experiments utilizing common motion models. %These results will be useful in collaborative intelligence applications where sequences of feature tensors need to be compressed or further analyzed.

Class imbalance poses a challenge for developing unbiased, accurate predictive models. In particular, in image segmentation neural networks may overfit to the foreground samples from small structures, which are often heavily under-represented in the training set, leading to poor generalization. In this study, we provide new insights on the problem of overfitting under class imbalance by inspecting the network behavior. We find empirically that when training with limited data and strong class imbalance, at test time the distribution of logit activations may shift across the decision boundary, while samples of the well-represented class seem unaffected. This bias leads to a systematic under-segmentation of small structures. This phenomenon is consistently observed for different databases, tasks and network architectures. To tackle this problem, we introduce new asymmetric variants of popular loss functions and regularization techniques including a large margin loss, focal loss, adversarial training, mixup and data augmentation, which are explicitly designed to counter logit shift of the under-represented classes. Extensive experiments are conducted on several challenging segmentation tasks. Our results demonstrate that the proposed modifications to the objective function can lead to significantly improved segmentation accuracy compared to baselines and alternative approaches.

In this paper, we propose a novel framework to translate a portrait photo-face into an anime appearance. Our aim is to synthesize anime-faces which are style-consistent with a given reference anime-face. However, unlike typical translation tasks, such anime-face translation is challenging due to complex variations of appearances among anime-faces. Existing methods often fail to transfer the styles of reference anime-faces, or introduce noticeable artifacts/distortions in the local shapes of their generated faces. We propose AniGAN, a novel GAN-based translator that synthesizes high-quality anime-faces. Specifically, a new generator architecture is proposed to simultaneously transfer color/texture styles and transform local facial shapes into anime-like counterparts based on the style of a reference anime-face, while preserving the global structure of the source photo-face. We propose a double-branch discriminator to learn both domain-specific distributions and domain-shared distributions, helping generate visually pleasing anime-faces and effectively mitigate artifacts. Extensive experiments on selfie2anime and a new face2anime dataset qualitatively and quantitatively demonstrate the superiority of our method over state-of-the-art methods. The new dataset is available at this https URL .

The video captioning task is to describe the video contents with natural language by the machine. Many methods have been proposed for solving this task. A large dataset called MSR Video to Text (MSR-VTT) is often used as the benckmark dataset for testing the performance of the methods. However, we found that the human annotations, i.e., the descriptions of video contents in the dataset are quite noisy, e.g., there are many duplicate captions and many captions contain grammatical problems. These problems may pose difficulties to video captioning models for learning. We cleaned the MSR-VTT annotations by removing these problems, then tested several typical video captioning models on the cleaned dataset. Experimental results showed that data cleaning boosted the performances of the models measured by popular quantitative metrics. We recruited subjects to evaluate the results of a model trained on the original and cleaned datasets. The human behavior experiment demonstrated that trained on the cleaned dataset, the model generated captions that were more coherent and more relevant to contents of the video clips. The cleaned dataset is publicly available.