Výsledky vyhledávání - "Li, Guozhang"

Report

CLIP-Driven Cloth-Agnostic Feature Learning for Cloth-Changing Person Re-Identification

Autor: Li, Shuang, Leng, Jiaxu, Li, Guozhang, Gan, Ji, chen, Haosheng, Gao, Xinbo

Contrastive Language-Image Pre-Training (CLIP) has shown impressive performance in short-term Person Re-Identification (ReID) due to its ability to extract high-level semantic features of pedestrians, yet its direct application to Cloth-Changing Pers

Externí odkaz: http://arxiv.org/abs/2406.09198

Zobrazit plný text záznamu

Report

EtC: Temporal Boundary Expand then Clarify for Weakly Supervised Video Grounding with Multimodal Large Language Model

Autor: Li, Guozhang, Ding, Xinpeng, Cheng, De, Li, Jie, Wang, Nannan, Gao, Xinbo

Early weakly supervised video grounding (WSVG) methods often struggle with incomplete boundary detection due to the absence of temporal boundary annotations. To bridge the gap between video-level and boundary-level annotation, explicit-supervision me

Externí odkaz: http://arxiv.org/abs/2312.02483

Zobrazit plný text záznamu

Report

Boosting Weakly-Supervised Temporal Action Localization with Text Information

Autor: Li, Guozhang, Cheng, De, Ding, Xinpeng, Wang, Nannan, Wang, Xiaoyu, Gao, Xinbo

Due to the lack of temporal annotation, current Weakly-supervised Temporal Action Localization (WTAL) methods are generally stuck into over-complete or incomplete localization. In this paper, we aim to leverage the text information to boost WTAL from

Externí odkaz: http://arxiv.org/abs/2305.00607

Zobrazit plný text záznamu

Report

Weakly-Supervised Temporal Action Localization with Bidirectional Semantic Consistency Constraint

Autor: Li, Guozhang, Cheng, De, Ding, Xinpeng, Wang, Nannan, Li, Jie, Gao, Xinbo

Weakly Supervised Temporal Action Localization (WTAL) aims to classify and localize temporal boundaries of actions for the video, given only video-level category labels in the training datasets. Due to the lack of boundary information during training

Externí odkaz: http://arxiv.org/abs/2304.12616

Zobrazit plný text záznamu

Akademický článek

DETR Novel Small Target Detection Algorithm Based on Swin Transformer

Autor: Xu Fengchang, Rayner Alfred, Rayner Henry Pailus, Lyu Ge, Du Shifeng, Jackel Vui Lung Vui Lung Chew, Li Guozhang, Wang Xinliang

Publikováno v: IEEE Access, Vol 12, Pp 115838-115852 (2024)

A small target object refers to an object whose relative size of the bounding box is very small, usually the ratio of the width of the bounding box to the width and height of the original image is less than 0.1, or the ratio of the area of the boundi

Externí odkaz: https://doaj.org/article/21d8d486c8ca4fd0907c08dc4742ae21