ISTR: Mask-Embedding-Based Instance Segmentation Transformer.

Transformer-based instance-level recognition has attracted increasing research attention recently due to the superior performance. However, although attempts have been made to encode masks as embeddings into Transformer-based frameworks, how to combine mask embeddings and spatial information for a transformer-based approach is still not fully explored. In this paper, we revisit the design of mask-embedding-based pipelines and propose an Instance Segmentation TRansformer (ISTR) with Mask Meta-Embeddings (MME), leveraging the strengths of transformer models in encoding embedding information and incorporating spatial information from mask embeddings.

Backdoor Attack against Face Sketch Synthesis.

Deep neural networks (DNNs) are easily exposed to backdoor threats when training with poisoned training samples. Models using backdoor attack have normal performance for benign samples, and possess poor performance for poisoned samples manipulated with pre-defined trigger patterns. Currently, research on backdoor attacks focuses on image classification and object detection.

Joint segmentation and detection of COVID-19 via a sequential region generation network.

The fast pandemics of coronavirus disease (COVID-19) has led to a devastating influence on global public health. In order to treat the disease, medical imaging emerges as a useful tool for diagnosis. However, the computed tomography (CT) diagnosis of COVID-19 requires experts' extensive clinical experience.

Shale Brittleness Index Based on the Energy Evolution Theory and Evaluation with Logging Data: A Case Study of the Guandong Block.

Shale brittleness is a key index that indicates the shale fracability, provides a basis for selecting wells and intervals to be fractured, and guarantees the good fracturing effect. The available models are not accurate in evaluating the shale brittleness when considering the confining pressure, and it is necessary to establish a new shale brittleness model under the geo-stress. In this study, the variation of elastic energy, fracture energy, and residual elastic energy in the whole process of rock compression and failure is analyzed based on the stress-strain curve in the experiments, and a shale brittleness index reflecting the energy evolution characteristics during rock failure under different confining pressures is established; a method of directly evaluating the shale brittleness with logging data by combining the rock mechanic experiment results with logging interpretation results is proposed.

Face Sketch Synthesis by Multidomain Adversarial Learning.

Given a training set of face photo-sketch pairs, face sketch synthesis targets at learning a mapping from the photo domain to the sketch domain. Despite the exciting progresses made in the literature, it retains as an open problem to synthesize high-quality sketches against blurs and deformations. Recent advances in generative adversarial training provide a new insight into face sketch synthesis, from which perspective the existing synthesis pipelines can be fundamentally revisited.

Robust Face Sketch Style Synthesis.

Heterogeneous image conversion is a critical issue in many computer vision tasks, among which example-based face sketch style synthesis provides a convenient way to make artistic effects for photos. However, existing face sketch style synthesis methods generate stylistic sketches depending on many photo-sketch pairs. This requirement limits the generalization ability of these methods to produce arbitrarily stylistic sketches.

Face sketch synthesis via sparse representation-based greedy search.

Face sketch synthesis has wide applications in digital entertainment and law enforcement. Although there is much research on face sketch synthesis, most existing algorithms cannot handle some nonfacial factors, such as hair style, hairpins, and glasses if these factors are excluded in the training set. In addition, previous methods only work on well controlled conditions and fail on images with different backgrounds and sizes as the training set.