67 citations · 79 across the 9 of their papers we have counts for
8 papers · 1 filter
Locate Anything in Videos: Rethinking Efficient Generative Spatio-Temporal Video Grounding
Hanoona Rasheed, Haania Siddiqui, Ming-Hsuan Yang +2
Spatio-temporal video grounding (STVG) requires models to identify when a referred event occurs and localize the target entity throughout that interval. Existing multimodal large l…
Video-CoM: Interactive Video Reasoning via Chain of Manipulations
Hanoona Rasheed, Mohammed Zumri, Muhammad Maaz +3
Recent multimodal large language models (MLLMs) have advanced video understanding, yet most still "think about videos" ie once a video is encoded, reasoning unfolds entirely in tex…
VideoMathQA: Benchmarking Mathematical Reasoning via Multimodal Understanding in Videos
Hanoona Rasheed, Abdelrahman Shaker, Anqi Tang +4
Mathematical reasoning in real-world video settings presents a fundamentally different challenge than in static images or text. It requires interpreting fine-grained visual informa…
Dynamic Pre-training: Towards Efficient and Scalable All-in-One Image Restoration
Akshay Dudhane, Omkar Thawakar, Syed Waqas Zamir +3
All-in-one image restoration tackles different types of degradations with a unified model instead of having task-specific, non-generic models for each degradation. The requirement…
Efficient Video Object Segmentation via Modulated Cross-Attention Memory
Abdelrahman Shaker, Syed Talal Wasim, Martin Danelljan +3
Recently, transformer-based approaches have shown promising results for semi-supervised video object segmentation. However, these approaches typically struggle on long videos due t…
Video-GroundingDINO: Towards Open-Vocabulary Spatio-Temporal Video Grounding
Syed Talal Wasim, Muzammal Naseer, Salman Khan +2
Video grounding aims to localize a spatio-temporal section in a video corresponding to an input text query. This paper addresses a critical limitation in current video grounding me…
GLaMM: Pixel Grounding Large Multimodal Model
Hanoona Rasheed, Muhammad Maaz, Sahal Shaji Mullappilly +7
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. Recen…
Learning Enriched Features for Real Image Restoration and Enhancement
Syed Waqas Zamir, Aditya Arora, Salman Khan +4
With the goal of recovering high-quality image content from its degraded version, image restoration enjoys numerous applications, such as in surveillance, computational photography…