5 papers · 1 filter
InfiniBench: A Benchmark for Large Multi-Modal Models in Long-Form Movies and TV Shows
Kirolos Ataallah, Eslam Abdelrahman, Mahmoud Ahmed +4
Understanding long-form videos, such as movies and TV episodes ranging from tens of minutes to two hours, remains a significant challenge for multi-modal models. Existing benchmark…
Kestrel: 3D Multimodal LLM for Part-Aware Grounded Description
Mahmoud Ahmed, Junjie Fei, Jian Ding +2
In this paper, we introduce Part-Aware Point Grounded Description (PaPGD), a challenging task aimed at advancing 3D multimodal learning for fine-grained, part-aware segmentation gr…
A Survey on Long-Video Storytelling Generation: Architectures, Consistency, and Cinematic Quality
Mohamed Elmoghany, Ryan Rossi, Seunghyun Yoon +26
Despite the significant progress that has been made in video generative models, existing state-of-the-art methods can only produce videos lasting 5-16 seconds, often labeled "long-…
ToddlerDiffusion: Interactive Structured Image Generation with Cascaded Schrödinger Bridge
Eslam Abdelrahman, Liangbing Zhao, Vincent Tao Hu +3
Diffusion models break down the challenging task of generating data from high-dimensional distributions into a series of easier denoising steps. Inspired by this paradigm, we propo…
CoT3DRef: Chain-of-Thoughts Data-Efficient 3D Visual Grounding
Eslam Abdelrahman, Mohamed Ayman, Mahmoud Ahmed +2
3D visual grounding is the ability to localize objects in 3D scenes conditioned by utterances. Most existing methods devote the referring head to localize the referred object direc…