Zobrazeno 1 - 10
of 336
pro vyhledávání: '"Li, Kehan"'
Autor:
Wang, XuDong, Zhang, Shaolun, Li, Shufan, Kallidromitis, Konstantinos, Li, Kehan, Kato, Yusuke, Kozuka, Kazuki, Darrell, Trevor
We present SegLLM, a novel multi-round interactive reasoning segmentation model that enhances LLM-based segmentation by exploiting conversational memory of both visual and textual outputs. By leveraging a mask-aware multimodal LLM, SegLLM re-integrat
Externí odkaz:
http://arxiv.org/abs/2410.18923
Autor:
Cheng, Zesen, Zhang, Hang, Li, Kehan, Leng, Sicong, Hu, Zhiqiang, Wu, Fei, Zhao, Deli, Li, Xin, Bing, Lidong
Contrastive loss is a powerful approach for representation learning, where larger batch sizes enhance performance by providing more negative samples to better distinguish between similar and dissimilar data. However, scaling batch sizes is constraine
Externí odkaz:
http://arxiv.org/abs/2410.17243
Autor:
Jin, Zeyu, Jia, Jia, Wang, Qixin, Li, Kehan, Zhou, Shuoyi, Zhou, Songtao, Qin, Xiaoyu, Wu, Zhiyong
Speech-language multi-modal learning presents a significant challenge due to the fine nuanced information inherent in speech styles. Therefore, a large-scale dataset providing elaborate comprehension of speech style is urgently needed to facilitate i
Externí odkaz:
http://arxiv.org/abs/2408.13608
Autor:
Shen, Chen, Lian, Chunfeng, Zhang, Wanqing, Wang, Fan, Zhang, Jianhua, Fan, Shuanliang, Wei, Xin, Wang, Gongji, Li, Kehan, Mu, Hongshu, Wu, Hao, Liang, Xinggong, Ma, Jianhua, Wang, Zhenyuan
Forensic pathology is critical in determining the cause and manner of death through post-mortem examinations, both macroscopic and microscopic. The field, however, grapples with issues such as outcome variability, laborious processes, and a scarcity
Externí odkaz:
http://arxiv.org/abs/2407.14904
Autor:
Jin, Peng, Li, Hao, Cheng, Zesen, Li, Kehan, Yu, Runyi, Liu, Chang, Ji, Xiangyang, Yuan, Li, Chen, Jie
Text-to-motion generation requires not only grounding local actions in language but also seamlessly blending these individual actions to synthesize diverse and realistic global motions. However, existing motion generation methods primarily focus on t
Externí odkaz:
http://arxiv.org/abs/2407.10528
Autor:
Zhao, Yian, Li, Kehan, Cheng, Zesen, Qiao, Pengchong, Zheng, Xiawu, Ji, Rongrong, Liu, Chang, Yuan, Li, Chen, Jie
Interactive Segmentation (IS) segments specific objects or parts in the image according to user input. Current IS pipelines fall into two categories: single-granularity output and multi-granularity output. The latter aims to alleviate the spatial amb
Externí odkaz:
http://arxiv.org/abs/2405.00587
Image Retrieval aims to retrieve corresponding images based on a given query. In application scenarios, users intend to express their retrieval intent through various query styles. However, current retrieval tasks predominantly focus on text-query re
Externí odkaz:
http://arxiv.org/abs/2312.02428
Autor:
Shen, Chen, Zhang, Jun, Liang, Xinggong, Hao, Zeyi, Li, Kehan, Wang, Fan, Wang, Zhenyuan, Lian, Chunfeng
Forensic pathology is critical in analyzing death manner and time from the microscopic aspect to assist in the establishment of reliable factual bases for criminal investigation. In practice, even the manual differentiation between different postmort
Externí odkaz:
http://arxiv.org/abs/2308.14030
Autor:
Cheng, Zesen, Jin, Peng, Li, Hao, Li, Kehan, Li, Siheng, Ji, Xiangyang, Liu, Chang, Chen, Jie
The top-down and bottom-up methods are two mainstreams of referring segmentation, while both methods have their own intrinsic weaknesses. Top-down methods are chiefly disturbed by Polar Negative (PN) errors owing to the lack of fine-grained cross-mod
Externí odkaz:
http://arxiv.org/abs/2306.10750
Autor:
Li, Kehan, Zhao, Yian, Wang, Zhennan, Cheng, Zesen, Jin, Peng, Ji, Xiangyang, Yuan, Li, Liu, Chang, Chen, Jie
Interactive segmentation enables users to segment as needed by providing cues of objects, which introduces human-computer interaction for many fields, such as image editing and medical image analysis. Typically, massive and expansive pixel-level anno
Externí odkaz:
http://arxiv.org/abs/2303.13399