AIConfPaper
← Search

Muhammad Maaz

10 accepted papers

2026

VideoMathQA: Benchmarking Mathematical Reasoning via Multimodal Understanding in Video

Hanoona Abdul Rasheed, Abdelrahman M Shaker, Anqi Tang, Muhammad Maaz, Ming-Hsuan Yang, Salman Khan +1
ICLR 2026poster

Mathematical reasoning in real-world video presents a fundamentally different challenge than static images or text. It requires interpreting fine-grained visual information, accurately reading handwritten or digital text, and integrating spoken cues, often dispersed non-linearly over time. In such m…

Cited by 0Source ↗code ↗Scholar ↗
2025

A Culturally-diverse Multilingual Multimodal Video Benchmark & Model

Bhuiyan Sanjid Shafique, Ashmal Vayani, Muhammad Maaz, Hanoona Abdul Rasheed, Dinura Dissanayake, Mohammed Irfan Kurpath +23
EMNLP 2025

Large multimodal models (LMMs) have recently gained attention due to their effectiveness to understand and generate descriptions of visual content. Most existing LMMs are in English language. While few recent works explore multilingual image LMMs, to the best of our knowledge, moving beyond the Engl

Cited by 0Source ↗PDF ↗Scholar ↗
2025

PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding

Jang Hyun Cho, Andrea Madotto, Effrosyni Mavroudi, Triantafyllos Afouras, Tushar Nagarajan, Muhammad Maaz +23
NeurIPS 2025spotlight

Vision-language models are integral to computer vision research, yet many high-performing models remain closed-source, obscuring their data, design and training recipe. The research community has responded by using distillation from black-box models to label training data, achieving strong benchmark…

Cited by 0Source ↗code ↗Scholar ↗
2024

GLaMM: Pixel Grounding Large Multimodal Model

Hanoona Rasheed, Muhammad Maaz, Sahal Shaji, Abdelrahman Shaker, Salman Khan, Hisham Cholakkal +4
CVPR 2024poster

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 responses. However they are limited to only referring…

Cited by 219Source ↗PDF ↗code ↗Scholar ↗
2024

Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models

Muhammad Maaz, Hanoona Rasheed, Salman Khan, Fahad Khan
ACL 2024long

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 video-based conversation by introducing Video-ChatGPT. It is a…

Cited by 766Source ↗PDF ↗code ↗Scholar ↗
2023

Fine-Tuned CLIP Models Are Efficient Video Learners

Hanoona Rasheed, Muhammad Uzair Khattak, Muhammad Maaz, Salman Khan, Fahad Shahbaz Khan
CVPR 2023poster

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. In this pursuit, new parametric modules are added…

Cited by 193Source ↗PDF ↗code ↗Scholar ↗
2023

MaPLe: Multi-Modal Prompt Learning

Muhammad Uzair Khattak, Hanoona Rasheed, Muhammad Maaz, Salman Khan, Fahad Shahbaz Khan
CVPR 2023poster

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. Inspired by the Natural Language Processing (NLP)…

Cited by 844Source ↗PDF ↗code ↗Scholar ↗
2023

SwiftFormer: Efficient Additive Attention for Transformer-based Real-time Mobile Vision Applications

Abdelrahman Shaker, Muhammad Maaz, Hanoona Rasheed, Salman Khan, Ming-Hsuan Yang, Fahad Shahbaz Khan
ICCV 2023poster

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 deployment on resource-constrained mobile devices. Althoug…

Cited by 143PDF ↗code ↗Scholar ↗
2022

Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detection

Hanoona Abdul Rasheed, Muhammad Maaz, Muhammd Uzair Khattak, Salman Khan, Fahad Khan
NeurIPS 2022accept

Existing open-vocabulary object detectors typically enlarge their vocabulary sizes by leveraging different forms of weak supervision. This helps generalize to novel objects at inference. Two popular forms of weak-supervision used in open-vocabulary detection (OVD) include pretrained CLIP model and i…

Cited by 179Source ↗PDF ↗code ↗Scholar ↗
2022

Class-Agnostic Object Detection with Multi-modal Transformer

Muhammad Maaz, Hanoona Rasheed, Salman Khan, Fahad Shahbaz Khan, Rao Muhammad Anwer, Ming-Hsuan Yang
ECCV 2022poster

"What constitutes an object? This has been a long-standing question in computer vision. Towards this goal, numerous learning-free and learning-based approaches have been developed to score objectness. However, they generally do not scale well across new domains and for unseen objects. In this paper,…

Cited by 116Source ↗PDF ↗code ↗Scholar ↗