No abstract

Current light field (LF) occlusion removal approaches usually select only a part of sub-aperture images (SAIs) or simply stack all SAIs to reconstruct the center view, which destroys the spatial layout of SAIs. In this paper, we present a simple yet effective LF occlusion removal method name Mask4D, which is a 4D convolution-based encoder-decoder network. We propose to keep the spatial layout of SAIs and construct all SAIs as a 5D input tensor to fully exploit the spatial connection information between SAIs. In particular, except for center view reconstruction, we jointly predict the occlusion mask to disentangle the occlusion mask from the occluded content. Extensive evaluations demonstrate that our Mask4D surpasses the state-of-the-art approaches across different datasets. Moreover, visualizations show that Mask4D predicts the occlusion mask precisely and the reconstructed center view looks more realistic than other approaches. Our code will be publicly available.

CC chemokine ligand-2 (CCL2), a proinflammatory chemokine that mediates chemotaxis of multiple immune cells, plays a crucial role in the tumor microenvironment (TME) and promotes tumorigenesis and development. Recently, accumulating evidence has indicated that CCL2 contributes to the development of drug resistance to a broad spectrum of anticancer agents, including chemotherapy, hormone therapy, targeted therapy, and immunotherapy. It has been reported that CCL2 can reduce tumor sensitivity to drugs by inhibiting drug-induced apoptosis, antiangiogenesis, and antitumor immunity. In this review, we mainly focus on elucidating the relationship between CCL2 and resistance as well as the underlying mechanisms. A comprehensive understanding of the role and mechanism of CCL2 in anticancer drug resistance may provide new therapeutic targets for reversing cancer resistance.

Deep neural networks are extremely vulnerable to malicious input data. As 3D data is increasingly used in vision tasks such as robots, autonomous driving and drones, the internal robustness of the classification models for 3D point cloud has received widespread attention. In this paper, we propose a novel method named SPGA (Shape Prior Guided Attack) to generate adversarial point cloud examples. We use shape prior information to make perturbations sparser and thus achieve imperceptible attacks. In particular, we propose a Spatially Logical Block (SLB) to apply adversarial points through sliding in the oriented bounding box. Moreover, we design an algorithm called FOFA for this type of task, which further refines the adversarial attack in the process of breaking down complicated problems into sub-problems. Compared with the methods of global perturbation, our attack method consumes significantly fewer computations, making it more efficient. Most importantly of all, SPGA can generate examples with a higher attack success rate (even in a defensive situation), less perturbation budget and stronger transferability.