Zobrazeno 1 - 10
of 647
pro vyhledávání: '"An-Ke Lei"'
Autor:
Li, Siyuan, Ke, Lei, Yang, Yung-Hsu, Piccinelli, Luigi, Segù, Mattia, Danelljan, Martin, Van Gool, Luc
Open-vocabulary Multiple Object Tracking (MOT) aims to generalize trackers to novel categories not in the training set. Currently, the best-performing methods are mainly based on pure appearance matching. Due to the complexity of motion patterns in t
Externí odkaz:
http://arxiv.org/abs/2409.11235
Autor:
Li, Siyuan, Ke, Lei, Danelljan, Martin, Piccinelli, Luigi, Segu, Mattia, Van Gool, Luc, Yu, Fisher
The robust association of the same objects across video frames in complex scenes is crucial for many applications, especially Multiple Object Tracking (MOT). Current methods predominantly rely on labeled domain-specific video datasets, which limits t
Externí odkaz:
http://arxiv.org/abs/2406.04221
Autor:
Wang, Ke-Lei, Chou, Pin-Hsuan, Chou, Young-Ching, Liu, Chia-Jen, Lin, Cheng-Kuan, Tseng, Yu-Chee
While there are a lot of models for instance segmentation, PolarMask stands out as a unique one that represents an object by a Polar coordinate system. With an anchor-box-free design and a single-stage framework that conducts detection and segmentati
Externí odkaz:
http://arxiv.org/abs/2406.01356
View-predictive generative models provide strong priors for lifting object-centric images and videos into 3D and 4D through rendering and score distillation objectives. A question then remains: what about lifting complete multi-object dynamic scenes?
Externí odkaz:
http://arxiv.org/abs/2405.02280
Autor:
Wang, Junchi, Ke, Lei
Understanding human instructions to identify the target objects is vital for perception systems. In recent years, the advancements of Large Language Models (LLMs) have introduced new possibilities for image segmentation. In this work, we delve into r
Externí odkaz:
http://arxiv.org/abs/2404.08767
The recent Gaussian Splatting achieves high-quality and real-time novel-view synthesis of the 3D scenes. However, it is solely concentrated on the appearance and geometry modeling, while lacking in fine-grained object-level scene understanding. To ad
Externí odkaz:
http://arxiv.org/abs/2312.00732
Autor:
Fan, Qi, Tao, Xin, Ke, Lei, Ye, Mingqiao, Zhang, Yuan, Wan, Pengfei, Wang, Zhongyuan, Tai, Yu-Wing, Tang, Chi-Keung
The Segment Anything Model (SAM) achieves remarkable promptable segmentation given high-quality prompts which, however, often require good skills to specify. To make SAM robust to casual prompts, this paper presents the first comprehensive analysis o
Externí odkaz:
http://arxiv.org/abs/2311.15776
Autor:
Ye, Mingqiao, Ke, Lei, Li, Siyuan, Tai, Yu-Wing, Tang, Chi-Keung, Danelljan, Martin, Yu, Fisher
Object localization in general environments is a fundamental part of vision systems. While dominating on the COCO benchmark, recent Transformer-based detection methods are not competitive in diverse domains. Moreover, these methods still struggle to
Externí odkaz:
http://arxiv.org/abs/2307.11035
The Segment Anything Model (SAM) has established itself as a powerful zero-shot image segmentation model, enabled by efficient point-centric annotation and prompt-based models. While click and brush interactions are both well explored in interactive
Externí odkaz:
http://arxiv.org/abs/2307.01197
Autor:
Ke, Lei, Ye, Mingqiao, Danelljan, Martin, Liu, Yifan, Tai, Yu-Wing, Tang, Chi-Keung, Yu, Fisher
The recent Segment Anything Model (SAM) represents a big leap in scaling up segmentation models, allowing for powerful zero-shot capabilities and flexible prompting. Despite being trained with 1.1 billion masks, SAM's mask prediction quality falls sh
Externí odkaz:
http://arxiv.org/abs/2306.01567