Text-to-Image (T2I) generation models have achieved significant advancements. Correspondingly, many automated methods emerge to evaluate the image-text alignment capabilities of generative models. However, the performance comparison among these automated methods is constrained by the limited scale of existing datasets. Additionally, existing datasets lack the capacity to assess the performance of automated methods at a fine-grained level. In this study, we contribute an EvalMuse-40K dataset, gathering 40K image-text pairs with fine-grained human annotations for image-text alignment-related tasks. In the construction process, we employ various strategies such as balanced prompt sampling and data re-annotation to ensure the diversity and reliability of our dataset. This allows us to comprehensively evaluate the performance of image-text alignment methods for T2I models. Based on this dataset, we introduce an efficient automated evaluation method termed FGA-BLIP2, which enables Fine-Grained Alignment evaluation solely by inputting images and text leveraging BLIP2, without visual question answering for each fine-grained element. Experimental results show the proposed FGA-BLIP2 efficiently achieves good performance on multiple image-text alignment datasets. Meanwhile, benefiting from the high efficiency and fine-grained evaluation capability of FGA-BLIP2, we apply it as a reward model to improve text-to-image models, which effectively enhances the image-text alignment ability of text-to-image models.

Abstract The command line interface is a crucial way of interacting with Linux, many programs such as ls, pwd and netstat are used on it and it is also the primary way to access a server remotely. However, the command line interface is not user friendly and thus it is difficult to use; there are many programs and users do not know which one is appropriate for finishing their task. To help users find useful commands efficiently, the authors propose FindCmd that retrieves commands based on the local data and user familiarity with commands. Then the local command data are collected including user manual such as man , info and strings extracted from the binary ELF (executable and linkable format) file. Based on the characteristics of local data, an enhanced command retrieval framework is proposed. In addition, the authors marginally decreased the priority of familiar commands when retrieving commands since users tend to use command retrieval tool to find an unfamiliar command. To the best of our knowledge, this is the first local tool for personalised command retrieval. In the evaluation section, the authors compare FindCmd with retrieval tools apropos and howdoi ; our experimental results show that FindCmd outperforms the other two tools in retrieving commands. In addition, the experiments demonstrate the effectiveness of personalised search of FindCmd.

Design procedures of two-element monopole slot antenna arrays are presented in this paper. We proposed several array topologies utilizing different feeding structures and injecting in-phase or out-of-phase signals to achieve power-combining radiation patterns. The sum and difference radiation patterns are successfully achieved and are theoretically analyzed. Furthermore, the power-combining characteristics are also presented by two proposed antenna arrays. The proposed antenna arrays can be candidates of the radiator for the base station or access point of the wireless local area network system.

In this paper, a wideband CPW-fed slot antenna based on the L-shaped is proposed. In order to simplify the antenna configuration and fabrication process, the slot antenna and the feeding structure are etched on the same plane of the substrate. By changing the geometry of the L-slot, an additional mode with two orthogonal electrical fields with 90 degree phase difference is excited, thus causing the circularly polarization (CP). Furthermore, introducing a protruded stub at the feedline, adding one finger slit and tuning the dimension of the ground plane improve the impedance matching condition. Finally, after the size optimization, the measured bandwidth of 22% (2.23-2.78 GHz) is achieved with an axial ratio <; 3 dB.