Zobrazeno 1 - 10
of 135
pro vyhledávání: '"Maaz, Muhammad"'
Building on the advances of language models, Large Multimodal Models (LMMs) have contributed significant improvements in video understanding. While the current video LMMs utilize advanced Large Language Models (LLMs), they rely on either image or vid
Externí odkaz:
http://arxiv.org/abs/2406.09418
Autor:
Maaz, Muhammad, Rasheed, Hanoona, Shaker, Abdelrahman, Khan, Salman, Cholakal, Hisham, Anwer, Rao M., Baldwin, Tim, Felsberg, Michael, Khan, Fahad S.
In pursuit of more inclusive Vision-Language Models (VLMs), this study introduces a Large Multilingual Multimodal Model called PALO. PALO offers visual reasoning capabilities in 10 major languages, including English, Chinese, Hindi, Spanish, French,
Externí odkaz:
http://arxiv.org/abs/2402.14818
Autor:
Munasinghe, Shehan, Thushara, Rusiru, Maaz, Muhammad, Rasheed, Hanoona Abdul, Khan, Salman, Shah, Mubarak, Khan, Fahad
Extending image-based Large Multimodal Models (LMMs) to videos is challenging due to the inherent complexity of video data. The recent approaches extending image-based LMMs to videos either lack the grounding capabilities (e.g., VideoChat, Video-Chat
Externí odkaz:
http://arxiv.org/abs/2311.13435
Autor:
Rasheed, Hanoona, Maaz, Muhammad, Mullappilly, Sahal Shaji, Shaker, Abdelrahman, Khan, Salman, Cholakkal, Hisham, Anwer, Rao M., Xing, Erix, Yang, Ming-Hsuan, Khan, Fahad S.
Large Multimodal Models (LMMs) extend Large Language Models to the vision domain. Initial LMMs used holistic images and text prompts to generate ungrounded textual responses. Recently, region-level LMMs have been used to generate visually grounded re
Externí odkaz:
http://arxiv.org/abs/2311.03356
Unsupervised performance estimation, or evaluating how well models perform on unlabeled data is a difficult task. Recently, a method was proposed by Garg et al. [2022] which performs much better than previous methods. Their method relies on having a
Externí odkaz:
http://arxiv.org/abs/2306.10160
Conversation agents fueled by Large Language Models (LLMs) are providing a new way to interact with visual data. While there have been initial attempts for image-based conversation models, this work addresses the under-explored field of \emph{video-b
Externí odkaz:
http://arxiv.org/abs/2306.05424
SwiftFormer: Efficient Additive Attention for Transformer-based Real-time Mobile Vision Applications
Autor:
Shaker, Abdelrahman, Maaz, Muhammad, Rasheed, Hanoona, Khan, Salman, Yang, Ming-Hsuan, Khan, Fahad Shahbaz
Self-attention has become a defacto choice for capturing global context in various vision applications. However, its quadratic computational complexity with respect to image resolution limits its use in real-time applications, especially for deployme
Externí odkaz:
http://arxiv.org/abs/2303.15446
Autor:
Shaker, Abdelrahman, Maaz, Muhammad, Rasheed, Hanoona, Khan, Salman, Yang, Ming-Hsuan, Khan, Fahad Shahbaz
Owing to the success of transformer models, recent works study their applicability in 3D medical segmentation tasks. Within the transformer models, the self-attention mechanism is one of the main building blocks that strives to capture long-range dep
Externí odkaz:
http://arxiv.org/abs/2212.04497
Large-scale multi-modal training with image-text pairs imparts strong generalization to CLIP model. Since training on a similar scale for videos is infeasible, recent approaches focus on the effective transfer of image-based CLIP to the video domain.
Externí odkaz:
http://arxiv.org/abs/2212.03640
Pre-trained vision-language (V-L) models such as CLIP have shown excellent generalization ability to downstream tasks. However, they are sensitive to the choice of input text prompts and require careful selection of prompt templates to perform well.
Externí odkaz:
http://arxiv.org/abs/2210.03117