MOTIVATION: Splicing, a critical co-transcriptional process in eukaryotes, enhances transcriptome diversity by generating isoforms specific to cell types, tissues, or developmental stages. Recent advancements in splicing modulators have opened new avenues for targeting previously undruggable genes by inducing significant perturbations in splicing events. These developments underscore the need for comprehensive methods to accurately identify and compare splicing events. While several tools have been developed to detect local splice variants, inconsistencies across methods remain a significant challenge. To address this, we present SpliceHarmonization, an integrated approach that combines the strengths of rMATS, LeafCutter, and MAJIQ, enabling robust and reliable splicing analysis with event type annotations. RESULTS: In a comprehensive evaluation using diverse simulated datasets, SpliceHarmonization streamlined and standardized the outputs from three detection methods into a unified format, thereby improving splicing detection with event type annotation and outperforming individual methods. By integrating the outputs from rMATS, LeafCutter, and MAJIQ, our approach not only enhanced identification of a wide range of splicing events but also effectively mitigated method-specific discrepancies. This integration led to an accuracy exceeding 0.8 and a recall of up to 0.5, with an observed increase in AUC of up to 10%. Furthermore, SpliceHarmonization demonstrated high sensitivity in detecting low-abundance and complex splicing events, providing annotations including genomic coordinates and event type. AVAILABILITY AND IMPLEMENTATION: SpliceHarmonization is available at https://github.com/interactivereport/SpliceHarmonization.

The extraordinary ability of generative models emerges as a new trend in image editing and generating realistic images, posing a serious threat to the trustworthiness of multimedia data and driving the research of image manipulation detection and location (IMDL). However, the lack of a large-scale data foundation makes the IMDL task unattainable. In this paper, we build a local manipulation data generation pipeline that integrates the powerful capabilities of SAM, LLM, and generative models. Upon this basis, we propose the GIM dataset, which has the following advantages: 1) Large scale, GIM includes over one million pairs of AI-manipulated images and real images. 2) Rich image content, GIM encompasses a broad range of image classes. 3) Diverse generative manipulation, the images are manipulated images with state-of-the-art generators and various manipulation tasks. The aforementioned advantages allow for a more comprehensive evaluation of IMDL methods, extending their applicability to diverse images. We introduce the GIM benchmark with two settings to evaluate existing IMDL methods. In addition, we propose a novel IMDL framework, termed GIMFormer, which consists of a ShadowTracer, Frequency-Spatial block (FSB), and a Multi-Window Anomalous Modeling (MWAM) module. Extensive experiments on the GIM demonstrate that GIMFormer surpasses the previous state-of-the-art approach on two different benchmarks.

Producing traversability maps and understanding the surroundings are crucial prerequisites for autonomous navigation. In this paper, we address the problem of traversability assessment using point clouds. We propose a novel pillar feature extraction module that utilizes PointNet to capture features from point clouds organized in vertical volume and a 2D encoder-decoder structure to conduct traversability classification instead of the widely used 3D convolutions. This results in less computational cost while even better performance is achieved at the same time. We then propose a new spatio-temporal attention module to fuse multi-frame information, which can properly handle the varying density problem of LIDAR point clouds, and this makes our module able to assess distant areas more accurately. Comprehensive experimental results on augmented Semantic KITTI and RELLIS-3D datasets show that our method is able to achieve superior performance over existing approaches both quantitatively and quantitatively. Our code is publicly available at https://github.com/chenyirui/FASTC.