6 papers · 1 filter
QueenVIS: Rethinking Image-Only Training for Video Instance Segmentation via Query Enrichment
Arian Kheirandish, Fardin Ayar, Ehsan Javanmardi +2
Video instance segmentation (VIS) requires models to detect, segment, and track object identities across frames, and most methods enforce temporal consistency through video-level s…
How Do Diffusion Classifiers Decide? A Bias-Centric Evaluation
Saba Fathi, Fardin Ayar, Maryam Abdolali +3
Diffusion models have recently been repurposed for zero-shot classification, giving rise to diffusion classifiers that identify the best-matching text prompt by minimizing the nois…
Evict3R: Training-Free Token Eviction for Memory-Bounded Streaming Visual Geometry Transformers
Soroush Mahdi, Fardin Ayar, Ehsan Javanmardi +2
Streaming visual transformers like StreamVGGT achieve strong 3D perception but suffer from unbounded growth of key value (KV) memory, which limits scalability. We propose a trainin…
Training-Free Diffusion Framework for Stylized Image Generation with Identity Preservation
Mohammad Ali Rezaei, Helia Hajikazem, Saeed Khanehgir +1
Although diffusion models have demonstrated remarkable generative capabilities, existing style transfer techniques often struggle to maintain identity while achieving high-quality…
Where Do You Go? Pedestrian Trajectory Prediction using Scene Features
Mohammad Ali Rezaei, Fardin Ayar, Ehsan Javanmardi +2
Accurate prediction of pedestrian trajectories is crucial for enhancing the safety of autonomous vehicles and reducing traffic fatalities involving pedestrians. While numerous stud…
LiDAR-Camera Fusion for Video Panoptic Segmentation without Video Training
Fardin Ayar, Ehsan Javanmardi, Manabu Tsukada +2
Panoptic segmentation, which combines instance and semantic segmentation, has gained a lot of attention in autonomous vehicles, due to its comprehensive representation of the scene…