Zobrazeno 21 - 30
of 2 324
pro vyhledávání: '"Sun, Xing"'
Autor:
Yin, Shukang, Fu, Chaoyou, Zhao, Sirui, Xu, Tong, Wang, Hao, Sui, Dianbo, Shen, Yunhang, Li, Ke, Sun, Xing, Chen, Enhong
Hallucination is a big shadow hanging over the rapidly evolving Multimodal Large Language Models (MLLMs), referring to the phenomenon that the generated text is inconsistent with the image content. In order to mitigate hallucinations, existing studie
Externí odkaz:
http://arxiv.org/abs/2310.16045
Autor:
Qin, Yulei, Chen, Xingyu, Shen, Yunhang, Fu, Chaoyou, Gu, Yun, Li, Ke, Sun, Xing, Ji, Rongrong
Webly supervised learning has attracted increasing attention for its effectiveness in exploring publicly accessible data at scale without manual annotation. However, most existing methods of learning with web datasets are faced with challenges from l
Externí odkaz:
http://arxiv.org/abs/2310.09761
Autor:
Cao, Haoyu, Bao, Changcun, Liu, Chaohu, Chen, Huang, Yin, Kun, Liu, Hao, Liu, Yinsong, Jiang, Deqiang, Sun, Xing
We propose a novel end-to-end document understanding model called SeRum (SElective Region Understanding Model) for extracting meaningful information from document images, including document analysis, retrieval, and office automation. Unlike state-of-
Externí odkaz:
http://arxiv.org/abs/2309.01131
Autor:
Shu, Xiujun, Wen, Wei, Xu, Liangsheng, Qiao, Ruizhi, Guo, Taian, Li, Hanjun, Gan, Bei, Wang, Xiao, Sun, Xing
Video temporal character grouping locates appearing moments of major characters within a video according to their identities. To this end, recent works have evolved from unsupervised clustering to graph-based supervised clustering. However, graph met
Externí odkaz:
http://arxiv.org/abs/2308.14105
We exploit the potential of the large-scale Contrastive Language-Image Pretraining (CLIP) model to enhance scene text detection and spotting tasks, transforming it into a robust backbone, FastTCM-CR50. This backbone utilizes visual prompt learning an
Externí odkaz:
http://arxiv.org/abs/2308.10408
Autor:
Lu, Junru, An, Siyu, Lin, Mingbao, Pergola, Gabriele, He, Yulan, Yin, Di, Sun, Xing, Wu, Yunsheng
We propose MemoChat, a pipeline for refining instructions that enables large language models (LLMs) to effectively employ self-composed memos for maintaining consistent long-range open-domain conversations. We demonstrate a long-range open-domain con
Externí odkaz:
http://arxiv.org/abs/2308.08239
Temporal sentence grounding (TSG) aims to locate a specific moment from an untrimmed video with a given natural language query. Recently, weakly supervised methods still have a large performance gap compared to fully supervised ones, while the latter
Externí odkaz:
http://arxiv.org/abs/2308.04197
Image retrieval targets to find images from a database that are visually similar to the query image. Two-stage methods following retrieve-and-rerank paradigm have achieved excellent performance, but their separate local and global modules are ineffic
Externí odkaz:
http://arxiv.org/abs/2308.04008
Recently, Multimodal Large Language Model (MLLM) represented by GPT-4V has been a new rising research hotspot, which uses powerful Large Language Models (LLMs) as a brain to perform multimodal tasks. The surprising emergent capabilities of MLLM, such
Externí odkaz:
http://arxiv.org/abs/2306.13549
Autor:
Fu, Chaoyou, Chen, Peixian, Shen, Yunhang, Qin, Yulei, Zhang, Mengdan, Lin, Xu, Yang, Jinrui, Zheng, Xiawu, Li, Ke, Sun, Xing, Wu, Yunsheng, Ji, Rongrong
Multimodal Large Language Model (MLLM) relies on the powerful LLM to perform multimodal tasks, showing amazing emergent abilities in recent studies, such as writing poems based on an image. However, it is difficult for these case studies to fully ref
Externí odkaz:
http://arxiv.org/abs/2306.13394