11 papers
AHMAD: Adaptive Hybrid Multi-task Vision Learning with Assisted Distillation for Keypoint Detection
Mohammad Mahdi, Nedyalko Prisadnikov, Yuqian Fu +3
Generalist multitasking vision models aim to unify multiple vision tasks within a single framework, enabling more efficient and versatile learning. However, handling diverse vision…
Ego-Forge: Text and Geometric-Attention Free Exo-to-Egocentric Video Generation
Mohammad Mahdi, Luc Van Gool, Danda Pani Paudel
Exo-to-egocentric video generation aims to synthesize what a person sees from their own viewpoint given third-person footage and a target head trajectory. The task requires transfe…
Accelerated Decoding of Centroid Positional Encoding for Instance Segmentation
Carmelo Scribano, Filippo Muzzini, Nedyalko Prisadnikov +6
Beyond model inference, the decoding stage, which converts raw network outputs into task-level representations, constitutes a significant portion of the execution cost. Despite its…
More with Less: a Large Scale Remote Sensing VLM with a Simple Recipe
Stefan Maria Ailuro, Mario Markov, Mohammad Mahdi +2
Remote sensing vision-language models are increasingly expected to support open-ended reasoning over Earth Observation data and a variety of tasks. Most recent progress in this are…
B-GRTO: Bootstrapped Group Relative Tool Optimization for Referring Segmentation
Mario Markov, Stefan Maria Ailuro, Mohammad Mahdi +2
Segmentation is a fundamental task in computer vision, underpinning pixel-level scene understanding and serving as a cornerstone for applications ranging from autonomous perception…
Accelerating Vision Foundation Models with Drop-in Depthwise Convolution
Carmelo Scribano, Mohammad Mahdi, Nedyalko Prisadnikov +5
Pretrained vision foundation models deliver strong performance across tasks with limited fine-tuning. However, their Vision Transformer (ViT) backbones impose high inference costs,…
From Synchrony to Sequence: Exo-to-Ego Generation via Interpolation
Mohammad Mahdi, Nedko Savov, Danda Pani Paudel +1
Exo-to-Ego video generation aims to synthesize a first-person video from a synchronized third-person view and corresponding camera poses. While paired supervision is available, syn…
OSMDA: OpenStreetMap-based Domain Adaptation for Remote Sensing VLMs
Stefan Maria Ailuro, Mario Markov, Mohammad Mahdi +3
Vision-Language Models (VLMs) adapted to remote sensing rely heavily on domain-specific image-text supervision, yet high-quality annotations for satellite and aerial imagery remain…
Exo2EgoSyn: Unlocking Foundation Video Generation Models for Exocentric-to-Egocentric Video Synthesis
Mohammad Mahdi, Yuqian Fu, Nedko Savov +3
Foundation video generation models such as WAN 2.2 exhibit strong text- and image-conditioned synthesis abilities but remain constrained to the same-view generation setting. In thi…
V-SAM: Marrying SAM2 with Multi-Prompt Experts for Cross-View Object Correspondence
Jiancheng Pan, Runze Wang, Tianwen Qian +7
Cross-view object correspondence, exemplified by the representative task of ego-exo object correspondence, aims to establish consistent associations of the same object across diffe…
Exploration-Driven Generative Interactive Environments
Nedko Savov, Naser Kazemi, Mohammad Mahdi +3
Modern world models require costly and time-consuming collection of large video datasets with action demonstrations by people or by environment-specific agents. To simplify trainin…