BiSTNet: Semantic Image Prior Guided Bidirectional Temporal Feature Fusion for Deep Exemplar-Based Video Colorization.

How to effectively explore the colors of exemplars and propagate them to colorize each frame is vital for exemplar-based video colorization. In this article, we present a BiSTNet to explore colors of exemplars and utilize them to help video colorization by a bidirectional temporal feature fusion with the guidance of semantic image prior. We first establish the semantic correspondence between each frame and the exemplars in deep feature space to explore color information from exemplars. Then, we develop a simple yet effective bidirectional temporal feature fusion module to propagate the colors of exemplars into each frame and avoid inaccurate alignment. We note that there usually exist color-bleeding artifacts around the boundaries of important objects in videos. To overcome this problem, we develop a mixed expert block to extract semantic information for modeling the object boundaries of frames so that the semantic image prior can better guide the colorization process. In addition, we develop a multi-scale refinement block to progressively colorize frames in a coarse-to-fine manner. Extensive experimental results demonstrate that the proposed BiSTNet performs favorably against state-of-the-art methods on the benchmark datasets and real-world scenes. Moreover, the BiSTNet obtains one champion in NTIRE 2023 video colorization challenge (Kang et al. 2023).

Graph MADDPG with RNN for multiagent cooperative environment.

Multiagent systems face numerous challenges due to environmental uncertainty, with scalability being a critical issue. To address this, we propose a novel multi-agent cooperative model based on a graph attention network. Our approach considers the relationship between agents and continuous action spaces, utilizing graph convolution and recurrent neural networks to define these relationships. Graph convolution is used to define the relationship between agents, while recurrent neural networks define continuous action spaces. We optimize and model the multiagent system by encoding the interaction weights among agents using the graph neural network and the weights between continuous action spaces using the recurrent neural network. We evaluate the performance of our proposed model by conducting experimental simulations using a 3D wargame engine that involves several unmanned air vehicles (UAVs) acting as attackers and radar stations acting as defenders, where both sides have the ability to detect each other. The results demonstrate that our proposed model outperforms the current state-of-the-art methods in terms of scalability, robustness, and learning efficiency.

Study of the genus Meleonoma Meyrick, 1914 (Lepidoptera: Autostichidae) from China (III), with descriptions of eighteen new species.

Eighteen new species of the genus Meleonoma Meyrick are described: M. arcivalvata sp. nov., M. chongqingensis sp. nov., M. curvativa sp. nov., M. curvitaeniana sp. nov., M. dilatifasciata sp. nov., M. fasciptera sp. nov., M. globoidea sp. nov., M. graciliclavata sp. nov., M. grandivalvula sp. nov., M. lunata sp. nov., M. medispinea sp. nov., M. proapicalis sp. nov., M. raphidacantha sp. nov., M. sinuaclavata sp. nov., M. tenuiclavata sp. nov., M. tetrodonta sp. nov. M. ventridentata sp. nov. and M. ventrisinuata sp. nov. The female of M. similifloralis (Wang, 2006) is described for the first time. Images of both adults and genitalia are provided. All species are divided into two species-groups, the dentivalvata species-group and the fasciptera species-group. A key to each group and maps showing the distribution of each group in China are given.

Taxonomy of the genus Autosticha Meyrick (Lepidoptera: Autostichidae) in China: Descriptions of fifteen new species.

Fifteen new species of the genus Autosticha Meyrick are described from China: A. annulata sp. nov., A. flabellata sp. nov., A. rhombea sp. nov., A. auriculata sp. nov., A. apicilata sp. nov., A. bomiensis sp. nov., A. longispina sp. nov., A. angustivalva sp. nov., A. basiprocessa sp. nov., A. semicircularia sp. nov., A. trapeziformis sp. nov., A. turriformis sp. nov., A. ventericoncava sp. nov., A. furcillata sp. nov. and A. ornithorhyncha sp. nov. Images of adults and genitalia are provided.

Taxonomic study of the genus Punctulata Wang (Lepidoptera: Autostichidae) from China, with descriptions of two new species.

The genus Punctulata Wang, 2006 is transferred from Oecophoridae to Autostichidae based on morphological characters and molecular data. Punctulata guangxiensis sp. nov. and P. novipalliptera sp. nov. are described as new based on the specimens collected in China. The females of P. palliptera Wang, 2006 and P. trunciformis Wang, 2006 are described for the first time. Images of male adults and male and female genitalia are provided for all the six Punctulata species along with a key to separate its species and a map showing their distribution.

Salient Region Guided Blind Image Sharpness Assessment.

Salient regions provide important cues for scene understanding to the human vision system. However, whether the detected salient regions are helpful in image blur estimation is unknown. In this study, a salient region guided blind image sharpness assessment (BISA) framework is proposed, and the effect of the detected salient regions on the BISA performance is investigated. Specifically, three salient region detection (SRD) methods and ten BISA models are jointly explored, during which the output saliency maps from SRD methods are re-organized as the input of BISA models. Consequently, the change in BISA metric values can be quantified and then directly related to the difference in BISA model inputs. Finally, experiments are conducted on three Gaussian blurring image databases, and the BISA prediction performance is evaluated. The comparison results indicate that salient region input can help achieve a close and sometimes superior performance to a BISA model over the whole image input. When using the center region input as the baseline, the detected salient regions from the saliency optimization from robust background detection (SORBD) method lead to consistently better score prediction, regardless of the BISA model. Based on the proposed hybrid framework, this study reveals that saliency detection benefits image blur estimation, while how to properly incorporate SRD methods and BISA models to improve the score prediction will be explored in our future work.

The genus emLocheutis/em Meyrick (Lepidoptera: Oecophoridae) from the Palaearctic and Oriental regions, with descriptions of four new species.

Four new species of the genus Locheutis Meyrick, 1883 are described. Locheutis pingxiangensis Wang, sp. nov., L. similempolaea Wang, sp. nov. and L. spinellosa Wang, sp. nov. are described from China; L. elliptica Wang, sp. nov. is described from Thailand. Locheutis jiangkouensis Wang, 2004 and L. tianmushana Wang, 2002 are redescribed, with the female of L. tianmushana described for the first time. Images of adults and available genitalia are provided as well as a key to the species based on male genitalia.

The genus Meleonoma Meyrick (Lepidoptera: Autostichidae) from Thailand.

Two new species of the genus Meleonoma Meyrick, 1914 from Thailand are described: M. segregacantha sp. nov. and M. fornicalis sp. nov. A checklist and a key to all the seven species from Thailand are given. Images of adults and genitalia of the new species are provided.