Yi Wan

QiMeng-EvoPartition: Rethinking the Impact of Partitioning for Automated Pipeline Design

Yi Wan, Rui Zhang, Shuyao Cheng, Chongxiao Li et autres

As a key technique for improving throughput by increasing clock frequency and reducing Cycles per Instruction (CPI), pipeline design increasingly relies on automated methods with the growing scale of modern circuits. However, existing automated pipelining methods often decouple partitioning from CPI optimization, …

cn (code pays fourni par la source)

MapGlue: Multimodal remote sensing image matching

Peihao Wu, Yongxiang Yao, Wenfei Zhang, Wei Dong et autres

cn (code pays fourni par la source)

An Algorithm for Fine-Grained Content Extraction and Understanding in Short Videos

Yi Wan, Shuya Zhang, Yaqi Xu, K Y Zhang et autres

This study integrates communication theory with advanced computer vision techniques to propose a novel approach for fine-grained content extraction in short videos. Unlike methods focused on summarization or subtitle generation for longer videos, our approach emphasizes extracting detailed content and understanding the …

cn (code pays fourni par la source)

SenseGeo : A Cross‐View Geo‐Localization Method With Perspective‐Aware Encoding and Cross‐Regional Generalization

Xiaoyu Zhang, Qiong Wu, Zhenyu Zhao, Kun Hu et autres

ABSTRACT Cross‐view geolocation aims to localize a ground‐view query image by retrieving the best match from a database of geo‐tagged aerial‐view and satellite‐view images. The perspective gap and urban complexity lead to appearance variations and spatial misalignment between query and reference images, …

cn, Rwanda (code pays fourni par la source)

High temperature lubrication performance of halogen-free deep eutectic solvents based on trioctylphosphine oxide: A tribological investigation

Z K Li, Yi Wan, Yue Wang, Jingxin ZHAO et autres

cn (code pays fourni par la source)

Water-Induced Lubrication Challenges in Engine Oils: A Review with H2-ICE as a Proxy for Alternative-Fuel Engines

Le Ma, Yunfeng Zang, Zhancheng Dou, Lingyan Guo et autres

Hydrogen-fueled internal combustion engines (H2-ICEs) impose unique challenges on engine lubrication because water is an inevitable combustion product. This review summarizes the current understanding of water-induced degradation mechanisms in engine oils for H2-ICEs, with emphasis on physicochemical property variation, additive depletion, tribofilm …

cn (code pays fourni par la source)

FreNTS: Neural Texture Synthesis in Frequency Domain

Dongdong Yue, Xinyi Liu, Yongjun Zhang, Jinming Zhang et autres

Although existing texture synthesis methods perform well in generating large images with irregularly repeated textures to avoid visually unrealistic repetitions, they still face significant challenges in synthesizing regular textures with densely interconnected structures. In this paper, we propose a novel neural texture …

cn (code pays fourni par la source)

Automatic Pipelining for Arbitrary Circuits via Gate-level Forwarding and Customized Scheduling

Chongxiao Li, Shuyao Cheng, Rui Zhang, Yi Wan et autres

Circuit pipelining is essential for improving the frequency and throughput of sequential circuits, yet it still largely relies on manual design at the behavioral level, which is effort-intensive, error-prone, and fails to exploit fine-grained gate-level opportunities. Existing automatic approaches analyze feedforward paths …

cn (code pays fourni par la source)

KMamba: Modality-flexible Feature Decoupling and KAN-Guided Fusion for Disaster Change Detection

Yongjun Zhang, Zeyu Liu, Zhi Zheng, Haoyu Guo et autres

cn (code pays fourni par la source)

Robust Multimodal Image Matching via Structural Congruency Feature Transform

H Yang, Haojie Wang, Yongxiang Yao, Peihao Wu et autres

cn, jp (code pays fourni par la source)

HIMOSA: Efficient Remote Sensing Image Super-Resolution with Hierarchical Mixture of Sparse Attention

Yi Liu, Yi Wan, Xinyi Liu, Qiong Wu et autres

In remote sensing applications, such as disaster detection and response, real-time efficiency and model lightweighting are of critical importance. Consequently, existing remote sensing image super-resolution methods often face a trade-off between model performance and computational efficiency. In this paper, we propose a …

StereoINR: Cross-View Geometry Consistent Stereo Super Resolution with Implicit Neural Representation

Yi Liu, Xinyi Liu, Yi Wan, Panwang Xia et autres

Stereo image super-resolution (SSR) aims to enhance high-resolution details by leveraging information from stereo image pairs. However, existing stereo super-resolution (SSR) upsampling methods (e.g., pixel shuffle) often overlook cross-view geometric consistency and are limited to fixed-scale upsampling. The key issue is that …

cn, Rwanda (code pays fourni par la source)