Titlebook: PRICAI 2024: Trends in Artificial Intelligence; 21st Pacific Rim Int Rafik Hadfi,Patricia Anthony,Quan Bai Conference proceedings 2025 The

Sad570

RSANet: Relationship-Aware Symmetric Alignment Network for Fine-Grained Video-Text Retrievalample enhanced ranking loss is proposed to optimize the RSANet, which promotes the model output with a larger inter-class variation and a smaller intra-class variation. Extensive experiments on three public datasets, namely MSR-VTT, VATEX, and PKU FG-XMedia, show the effectiveness of RSANet surpasses state-of-the-art methods.

WITH

Zero-Shot Referring Image Segmentation with Hierarchical Prompts and Frequency Domain Fusion visual and text feature separately in the frequency domain to fully utilize feature information. Our method has been extensively tested on the RefCOCO, RefCOCO+, and RefCOCOg datasets, demonstrating significant improvements over existing zero-shot referring image segmentation methods.

GIST

Multi-scale Traffic Camera Image Detection Network Based on Improved YOLOv8These results surpass the performance of leading detection algorithms. In addition, the model takes only 12.5 milliseconds to complete an inference, which makes it highly deployable and valuable for real-world applications.

愤怒事实

Baitong Cui,Shuai Li,Jiayi Gui,Konglin Zhu,Shengchu Wang

有特色

Chao Wang,Zhongyuan Wang,Ruimin Hu,Xiaochen Wang,Wen Zhou

表示问

Query-Efficient Stealing Attacks Against Image Encodersbustness and generalization. Linear evaluation results on image datasets of various settings show that the proposed method achieves comparable or even better performance compared to existing attacks with only 25% of the query cost.

教育学

不能妥协

清晰

Video-Audio Multimodal Fall Detection Method model using Le2i and UP-Fall datasets. Additionally, we compared our findings with other fall detection methods. The outstanding results of our multimodal model indicate its superior performance compared to single fall detection models.

Picks-Disease