扫兴 发表于 2025-3-26 22:52:49

PBTR: Pre-training and Bidirectional Semantic Enhanced Trajectory Recoveryental factors often result in missing track records, significantly impacting the trajectory data quality. It is a fundamental task to restore the missing vehicle tracks within the traffic network structure. Existing research has attempted to address this issue through the construction of neural netw

Servile 发表于 2025-3-27 04:58:18

Event-Aware Document-Level Event Extraction via Multi-granularity Event Encoder the prior research has largely concentrated on sentence-level event extraction (SEE), while disregarding the increasing requirements for document-level event extraction (DEE) in real-world scenarios. The latter presents two significant challenges, namely the arguments scattering problem and the mul

Afflict 发表于 2025-3-27 05:49:34

http://reply.papertrans.cn/67/6636/663585/663585_33.png

moribund 发表于 2025-3-27 12:45:50

http://reply.papertrans.cn/67/6636/663585/663585_34.png

烧烤 发表于 2025-3-27 17:38:16

Instance-Aware and Semantic-Guided Prompt for Few-Shot Learning in Large Language ModelstGPT). However, current prompt learning methods usually use a unified template for the same tasks, and the template is difficult to capture significant information from different instances. To integrate the semantic attention dynamically on the instance level, We propose ISPrompt, an .nstance-.emant

迅速成长 发表于 2025-3-27 19:38:57

http://reply.papertrans.cn/67/6636/663585/663585_36.png

patriarch 发表于 2025-3-27 22:58:10

SODet: A LiDAR-Based Object Detector in Bird’s-Eye Views from a bird’s-eye view perspective remains challenging. To address this issue, the paper presents ., an efficient single-stage 3D object detector designed to enhance the perception of small objects like pedestrians and cyclists. SODet incorporates several key components and techniques. To capture

没有准备 发表于 2025-3-28 05:03:58

Landmark-Assisted Facial Action Unit Detection with Optimal Attention and Contrastive Learningtention-based landmark features as well as contrastive learning to improve the performance of AU detection. Firstly, the backbone is a weakly-supervised algorithm since AU datasets in the wild are scarce and the utilization of other public datasets can capture robust basic facial features and landma

极小 发表于 2025-3-28 07:04:12

Multi-scale Local Region-Based Facial Action Unit Detection with Graph Convolutional Networks at different scales, and may interact with each other. However, most existing methods fail to extract the multi-scale feature at local facial region, or consider the AU relationship in the classifiers. In this paper, we propose a novel multi-scale local region-based facial AU detection framework w

MAOIS 发表于 2025-3-28 14:05:17

http://reply.papertrans.cn/67/6636/663585/663585_40.png
页: 1 2 3 [4] 5 6 7
查看完整版本: Titlebook: Neural Information Processing; 30th International C Biao Luo,Long Cheng,Chaojie Li Conference proceedings 2024 The Editor(s) (if applicable