Video-to-audio synthesis, which generates synchronized audio for visual content, critically enhances viewer immersion and narrative coherence in film and interactive media.However, video-to-audio dubbing for long-form content remains an unsolved challenge due to dynamic semantic shifts, audio diversity and the absence of dedicated datasets.While existing methods excel in short videos, they falter in long scenarios (e.g., movies) due to fragmented synthesis and inadequate cross-scene consistency.We propose LVAS-Agent, a multi-agent framework that offers a coordinated, multi-component approach to long-video audio generation.Our approach decomposes long-video synthesis into four steps including scene segmentation, script generation, audio design and audio synthesis.To enable systematic evaluation, we introduce LVAS-Bench, the first benchmark with 207 professionally curated long videos spanning diverse scenarios.Experiments show that our method outperforms state-of-the-art V2A models in overall audio synthesis quality.

The complementary nature of depth images and infrared amplitude images enables their fusion to enhance target detection accuracy in vehicle cockpits. Existing detection algorithms primarily focus on single-modal inputs, while multi-modal fusion methods often lack global perception and fail to address cross-modal interaction and redundancy. Moreover, depth maps typically contain noise, limiting the effectiveness of fusion. To overcome these issues, we propose DALFNet, a lightweight CNN-Transformer-based object detection network that enhances depth map quality and effectively integrates depth and infrared amplitude modalities. TransLiteFusion (TLF) is designed to combine self-attention and cross-attention mechanisms to fuse and facilitate interaction between multimodal information. The Depth Restoration Sub-network (DRSN) is employed for ToF depth denoising and enhancement, assisting TLF in achieving accurate fusion. Experiments conducted on several public datasets indicate that DALFNet outperforms state-of-the-art algorithms. The core code is available at https://github.com/ZYH-Lightyear/DALFNet.

Despite great progress, previous stereo matching algorithms still lack the ability to match textureless regions and slender structure areas. To tackle this problem, we propose ASM-Net, an attention stereo matching network. Attention module and disparity refinement module are constructed in the ASMNet. The attention module can improve correlation information between two images by channels and spatial attention. The feature-guided disparity refinement module learns more geometry information in different feature levels to refine the coarse prediction resolution constantly. The proposed approach was evaluated on several benchmark datasets. Experiments show that the proposed method achieves competitive results on KITTI and Scene-Flow datasets while running in real-time at 14ms.