Zobrazeno 1 - 10
of 2 818
pro vyhledávání: '"Chen Jiayi"'
For the task of hanging clothes, learning how to insert a hanger into a garment is crucial but has been seldom explored in robotics. In this work, we address the problem of inserting a hanger into various unseen garments that are initially laid out f
Externí odkaz:
http://arxiv.org/abs/2412.01083
Embedding models have become essential tools in both natural language processing and computer vision, enabling efficient semantic search, recommendation, clustering, and more. However, the high memory and computational demands of full-precision embed
Externí odkaz:
http://arxiv.org/abs/2411.15438
Topological Data Analysis (TDA) has recently gained significant attention in the field of financial prediction. However, the choice of point cloud construction methods, topological feature representations, and classification models has a substantial
Externí odkaz:
http://arxiv.org/abs/2411.13881
Autor:
Zhang, Jialiang, Liu, Haoran, Li, Danshi, Yu, Xinqiang, Geng, Haoran, Ding, Yufei, Chen, Jiayi, Wang, He
Grasping in cluttered scenes remains highly challenging for dexterous hands due to the scarcity of data. To address this problem, we present a large-scale synthetic benchmark, encompassing 1319 objects, 8270 scenes, and 427 million grasps. Beyond ben
Externí odkaz:
http://arxiv.org/abs/2410.23004
Autor:
Wei, Songlin, Geng, Haoran, Chen, Jiayi, Deng, Congyue, Cui, Wenbo, Zhao, Chengyang, Fang, Xiaomeng, Guibas, Leonidas, Wang, He
Depth sensing is an important problem for 3D vision-based robotics. Yet, a real-world active stereo or ToF depth camera often produces noisy and incomplete depth which bottlenecks robot performances. In this work, we propose D3RoMa, a learning-based
Externí odkaz:
http://arxiv.org/abs/2409.14365
Autor:
Zeng, Zheni, Chen, Jiayi, Chen, Huimin, Yan, Yukun, Chen, Yuxuan, Liu, Zhenghao, Liu, Zhiyuan, Sun, Maosong
Large language models exhibit aspects of human-level intelligence that catalyze their application as human-like agents in domains such as social simulations, human-machine interactions, and collaborative multi-agent systems. However, the absence of d
Externí odkaz:
http://arxiv.org/abs/2407.12393
Autor:
Zhang, Jifan, Jain, Lalit, Guo, Yang, Chen, Jiayi, Zhou, Kuan Lok, Suresh, Siddharth, Wagenmaker, Andrew, Sievert, Scott, Rogers, Timothy, Jamieson, Kevin, Mankoff, Robert, Nowak, Robert
We present a novel multimodal preference dataset for creative tasks, consisting of over 250 million human ratings on more than 2.2 million captions, collected through crowdsourcing rating data for The New Yorker's weekly cartoon caption contest over
Externí odkaz:
http://arxiv.org/abs/2406.10522
Cross-Domain Few-shot Semantic Segmentation (CD-FSS) aims to train generalized models that can segment classes from different domains with a few labeled images. Previous works have proven the effectiveness of feature transformation in addressing CD-F
Externí odkaz:
http://arxiv.org/abs/2405.15265
Autor:
Chen, Jiayi, Deng, Chunhua
With the advancement of video analysis technology, the multi-object tracking (MOT) problem in complex scenes involving pedestrians is gaining increasing importance. This challenge primarily involves two key tasks: pedestrian detection and re-identifi
Externí odkaz:
http://arxiv.org/abs/2405.07272
We conduct an in-depth spectral analysis of $\sim1{\rm ~Ms}$ XMM-Newton data of the narrow line Seyfert 1 galaxy RE J1034+396. The long exposure ensures high spectral quality and provides us with a detailed look at the intrinsic absorption and emissi
Externí odkaz:
http://arxiv.org/abs/2404.01377