Zobrazeno 1 - 10
of 440
pro vyhledávání: '"Jing, Liping"'
We propose a unified object-aware temporal learning framework for multi-view 3D detection and tracking tasks. Having observed that the efficacy of the temporal fusion strategy in recent multi-view perception methods may be weakened by distractors and
Externí odkaz:
http://arxiv.org/abs/2407.03240
We propose UAD, a method for vision-based end-to-end autonomous driving (E2EAD), achieving the best open-loop evaluation performance in nuScenes, meanwhile showing robust closed-loop driving quality in CARLA. Our motivation stems from the observation
Externí odkaz:
http://arxiv.org/abs/2406.17680
Children with Autism Spectrum Disorder (ASD) often misunderstand social situations and struggle to participate in daily routines. Psychology experts write Social Stories under strict constraints of structural clarity, descriptive orientation, and sit
Externí odkaz:
http://arxiv.org/abs/2406.15695
Pre-trained large language models can perform natural language processing downstream tasks by conditioning on human-designed prompts. However, a prompt-based approach often requires "prompt engineering" to design different prompts, primarily hand-cra
Externí odkaz:
http://arxiv.org/abs/2405.16571
Autor:
Min, Chen, Zhao, Dawei, Xiao, Liang, Zhao, Jian, Xu, Xinli, Zhu, Zheng, Jin, Lei, Li, Jianshu, Guo, Yulan, Xing, Junliang, Jing, Liping, Nie, Yiming, Dai, Bin
Vision-centric autonomous driving has recently raised wide attention due to its lower cost. Pre-training is essential for extracting a universal representation. However, current vision-centric pre-training typically relies on either 2D or 3D pre-text
Externí odkaz:
http://arxiv.org/abs/2405.04390
Humans can easily distinguish the known and unknown categories and can recognize the unknown object by learning it once instead of repeating it many times without forgetting the learned object. Hence, we aim to make deep learning models simulate the
Externí odkaz:
http://arxiv.org/abs/2403.02637
Posts in software Q\&A sites often consist of three main parts: title, description and code, which are interconnected and jointly describe the question. Existing tag recommendation methods often treat different modalities as a whole or inadequately c
Externí odkaz:
http://arxiv.org/abs/2402.03635
Zero-shot keyphrase extraction aims to build a keyphrase extractor without training by human-annotated data, which is challenging due to the limited human intervention involved. Challenging but worthwhile, zero-shot setting efficiently reduces the ti
Externí odkaz:
http://arxiv.org/abs/2312.15156
Continual learning entails learning a sequence of tasks and balancing their knowledge appropriately. With limited access to old training samples, much of the current work in deep neural networks has focused on overcoming catastrophic forgetting of ol
Externí odkaz:
http://arxiv.org/abs/2310.08855
With the development of Internet technology and the expansion of social networks, online platforms have become an important way for people to obtain information. The introduction of tags facilitates information categorization and retrieval. Meanwhile
Externí odkaz:
http://arxiv.org/abs/2310.05423