Výsledky vyhledávání - "Peng, Yansong"

Report

D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinement

Autor: Peng, Yansong, Li, Hebei, Wu, Peixi, Zhang, Yueyi, Sun, Xiaoyan, Wu, Feng

We introduce D-FINE, a powerful real-time object detector that achieves outstanding localization precision by redefining the bounding box regression task in DETR models. D-FINE comprises two key components: Fine-grained Distribution Refinement (FDR)

Externí odkaz: http://arxiv.org/abs/2410.13842

Zobrazit plný text záznamu

Report

Enhanced Object Detection: A Study on Vast Vocabulary Object Detection Track for V3Det Challenge 2024

Autor: Wu, Peixi, Chai, Bosong, Nie, Xuan, Yan, Longquan, Wang, Zeyu, Zhou, Qifan, Wang, Boning, Peng, Yansong, Li, Hebei

Publikováno v: Second Place in CVPR 2024 Vast Vocabulary Visual Detection Challenge

In this technical report, we present our findings from the research conducted on the Vast Vocabulary Visual Detection (V3Det) dataset for Supervised Vast Vocabulary Visual Detection task. How to deal with complex categories and detection boxes has be

Externí odkaz: http://arxiv.org/abs/2406.09201

Zobrazit plný text záznamu

Report

Event-assisted Low-Light Video Object Segmentation

Autor: Li, Hebei, Wang, Jin, Yuan, Jiahui, Li, Yue, Weng, Wenming, Peng, Yansong, Zhang, Yueyi, Xiong, Zhiwei, Sun, Xiaoyan

In the realm of video object segmentation (VOS), the challenge of operating under low-light conditions persists, resulting in notably degraded image quality and compromised accuracy when comparing query and memory frames for similarity computation. E

Externí odkaz: http://arxiv.org/abs/2404.01945

Zobrazit plný text záznamu

Report

Scene Adaptive Sparse Transformer for Event-based Object Detection

Autor: Peng, Yansong, Li, Hebei, Zhang, Yueyi, Sun, Xiaoyan, Wu, Feng

While recent Transformer-based approaches have shown impressive performances on event-based object detection tasks, their high computational costs still diminish the low power consumption advantage of event cameras. Image-based works attempt to reduc

Externí odkaz: http://arxiv.org/abs/2404.01882

Zobrazit plný text záznamu

Report

GET: Group Event Transformer for Event-Based Vision

Autor: Peng, Yansong, Zhang, Yueyi, Xiong, Zhiwei, Sun, Xiaoyan, Wu, Feng

Event cameras are a type of novel neuromorphic sen-sor that has been gaining increasing attention. Existing event-based backbones mainly rely on image-based designs to extract spatial information within the image transformed from events, overlooking

Externí odkaz: http://arxiv.org/abs/2310.02642

Zobrazit plný text záznamu