Zhengbo Zhang

Unleashing the Power of Text-to-Image Diffusion Models for Category-Agnostic Pose Estimation

Duo Peng, Zhengbo Zhang, Ping Hu, Qiuhong Ke et autres

Category-Agnostic Pose Estimation (CAPE) aims to detect keypoints of unseen object categories in a few-shot setting, where the scarcity of labeled data poses significant challenges to generalization. In this work, we propose Prompt Pose Matching (PPM), a novel framework that unleashes the …

sg, cn, au, gb (code pays fourni par la source)

Performing Defocus Deblurring by Modeling its Formation Process

Zhengbo Zhang, Lin Geng Foo, Hossein Rahmani, Jun Liu et autres

sg, gb (code pays fourni par la source)

Visual Prompting for One-shot Controllable Video Editing without Inversion

Zhengbo Zhang, Yuxi Zhou, Duo Peng, Joo-Hwee Lim et autres

One-shot controllable video editing (OCVE) is an important yet challenging task, aiming to propagate user edits that are made – using any image editing tool – on the first frame of a video to all subsequent frames, while ensuring content consistency between …

sg, cn (code pays fourni par la source)

FADE: A Dataset for Detecting Falling Objects Around Buildings in Video

Zhigang Tu, Zhengbo Zhang, Zitao Gao, Chunluan Zhou et autres

Objects falling from buildings, a frequently occurring event in daily life, can cause severe injuries to pedestrians due to the high impact force they exert. Surveillance cameras are often installed around buildings to detect falling objects, but such detection remains challenging due …

cn, us (code pays fourni par la source)

Informative Sample Selection Model for Skeleton-Based Action Recognition With Limited Training Samples

Zhigang Tu, Zhengbo Zhang, Jia Gong, Junsong Yuan et autres

Skeleton-based human action recognition aims to classify human skeletal sequences, which are spatiotemporal representations of actions, into predefined categories. To reduce the reliance on costly annotations of skeletal sequences while maintaining competitive recognition accuracy, the task of 3D Action Recognition with Limited …

cn, sg, us (code pays fourni par la source)

Diff-Tracker: Text-to-Image Diffusion Models are Unsupervised Trackers

Zhengbo Zhang, Li Xu, Duo Peng, Hossein Rahmani et autres

sg, gb (code pays fourni par la source)

Harnessing Text-to-Image Diffusion Models for Category-Agnostic Pose Estimation

Duo Peng, Zhengbo Zhang, Ping Hu, Qiuhong Ke et autres

sg, cn, au, gb (code pays fourni par la source)

Gait recognition for farm workers via multi-scale temporal feature perception

Zhengbo Zhang, Yaxu Xiao, Zizhi Chen, Xin Chen et autres

cn (code pays fourni par la source)

Diff-Tracker: Text-to-Image Diffusion Models are Unsupervised Trackers

Zhengbo Zhang, Xu Li, Duo Peng, Hossein Rahmani et autres

We introduce Diff-Tracker, a novel approach for the challenging unsupervised visual tracking task leveraging the pre-trained text-to-image diffusion model. Our main idea is to leverage the rich knowledge encapsulated within the pre-trained diffusion model, such as the understanding of image semantics and …

Five Philosophical Faces of the Modern Avant-garde Arts

Zhengbo Zhang, Qiuping Li

Real Situation and Inner Image Analysis on the Urban Cultural Image of the Drama “I Am Waiting for You in Chengdu”, the First Drama of Dream Seekers’ Life in Chengdu

Zhengbo Zhang, Miao Wang, Huang Hao

In July 2018, the first drama of dream seekers' life in Chengdu "I am waiting for you in Chengdu" was performed in Wuhou Theater and Sanhe Classic Car Museum in Chengdu, Sichuan Province.The continuous hot scene completely exceeded the team's expectations.Major domestic …

id, cn (code pays fourni par la source)