Zobrazeno 1 - 10
of 480
pro vyhledávání: '"Luo, Gen"'
Autor:
Wu, Mingrui, Cai, Xinyue, Ji, Jiayi, Li, Jiale, Huang, Oucheng, Luo, Gen, Fei, Hao, Sun, Xiaoshuai, Ji, Rongrong
In this work, we propose a training-free method to inject visual referring into Multimodal Large Language Models (MLLMs) through learnable visual token optimization. We observe the relationship between text prompt tokens and visual tokens in MLLMs, w
Externí odkaz:
http://arxiv.org/abs/2407.21534
Autor:
Wu, Changli, Liu, Yihang, Ji, Jiayi, Ma, Yiwei, Wang, Haowei, Luo, Gen, Ding, Henghui, Sun, Xiaoshuai, Ji, Rongrong
3D Referring Expression Segmentation (3D-RES) is dedicated to segmenting a specific instance within a 3D space based on a natural language description. However, current approaches are limited to segmenting a single target, restricting the versatility
Externí odkaz:
http://arxiv.org/abs/2407.20664
Recently, mixture of experts (MoE) has become a popular paradigm for achieving the trade-off between modal capacity and efficiency of multi-modal large language models (MLLMs). Different from previous efforts, we are dedicated to exploring the dynami
Externí odkaz:
http://arxiv.org/abs/2407.14093
Recently, Segment Anything Model (SAM) has become a research hotspot in the fields of multimedia and computer vision, which exhibits powerful yet versatile capabilities on various (un) conditional image segmentation tasks. Although SAM can support di
Externí odkaz:
http://arxiv.org/abs/2404.00650
Autor:
Zhang, Jinlu, Zhou, Yiyi, Zheng, Qiancheng, Du, Xiaoxiong, Luo, Gen, Peng, Jun, Sun, Xiaoshuai, Ji, Rongrong
Text-to-3D-aware face (T3D Face) generation and manipulation is an emerging research hot spot in machine learning, which still suffers from low efficiency and poor quality. In this paper, we propose an End-to-End Efficient and Effective network for f
Externí odkaz:
http://arxiv.org/abs/2403.06702
Despite remarkable progress, existing multimodal large language models (MLLMs) are still inferior in granular visual recognition. Contrary to previous works, we study this problem from the perspective of image resolution, and reveal that a combinatio
Externí odkaz:
http://arxiv.org/abs/2403.03003
Referring Expression Segmentation (RES) is an emerging task in computer vision, which segments the target instances in images based on text descriptions. However, its development is plagued by the expensive segmentation labels. To address this issue,
Externí odkaz:
http://arxiv.org/abs/2311.00397
In 3D Referring Expression Segmentation (3D-RES), the earlier approach adopts a two-stage paradigm, extracting segmentation proposals and then matching them with referring expressions. However, this conventional paradigm encounters significant challe
Externí odkaz:
http://arxiv.org/abs/2308.16632
Recently, growing interest has been aroused in extending the multimodal capability of large language models (LLMs), e.g., vision-language (VL) learning, which is regarded as the next milestone of artificial general intelligence. However, existing sol
Externí odkaz:
http://arxiv.org/abs/2305.15023
Autor:
Mi, Peng, Lin, Jianghang, Zhou, Yiyi, Shen, Yunhang, Luo, Gen, Sun, Xiaoshuai, Cao, Liujuan, Fu, Rongrong, Xu, Qiang, Ji, Rongrong
In this paper, we study teacher-student learning from the perspective of data initialization and propose a novel algorithm called Active Teacher(Source code are available at: \url{https://github.com/HunterJ-Lin/ActiveTeacher}) for semi-supervised obj
Externí odkaz:
http://arxiv.org/abs/2303.08348