arXiv:2603.11380v2 Announce Type: replace
Abstract: Fusing sensors with complementary modalities is crucial for maintaining a stable and comprehensive understanding of abnormal driving scenes. However, Multimodal Large Language Models (MLLMs) are unde…
arXiv:2603.23988v1 Announce Type: new
Abstract: Online Action Detection (OAD) systems face two primary challenges: high computational cost and insufficient modeling of discriminative temporal dynamics against background motion. Adding optical flow cou…
arXiv:2602.21917v2 Announce Type: replace
Abstract: Ultra-High-Definition (UHD) image restoration is trapped in a scalability crisis: existing models, bound to pixel-wise operations, demand unsustainable computation. While state space models (SSMs) li…
arXiv:2603.23976v1 Announce Type: new
Abstract: Gait silhouettes, which can be encoded into binary gait codes, are widely adopted to representing motion patterns of pedestrian. Recent approaches commonly leverage visual backbones to encode gait silhou…
arXiv:2602.18996v2 Announce Type: replace
Abstract: We study the task of establishing object-level visual correspondence across different viewpoints in videos, focusing on the challenging egocentric-to-exocentric and exocentric-to-egocentric scenarios…
arXiv:2603.23975v1 Announce Type: new
Abstract: In collaborative perception, an agent’s performance can be degraded by heterogeneity arising from differences in model architecture or training data distributions. To address this challenge, we propose H…
arXiv:2602.06037v3 Announce Type: replace
Abstract: Recent progress in spatial reasoning with Multimodal Large Language Models (MLLMs) increasingly leverages geometric priors from 3D encoders. However, most existing integration strategies remain passi…
arXiv:2603.23973v1 Announce Type: new
Abstract: Estimating the material property field of 3D assets is critical for physics-based simulation, robotics, and digital twin generation. Existing vision-based approaches are either too expensive and slow or …
arXiv:2603.23960v1 Announce Type: new
Abstract: The rapid progress of generative AI has enabled hyper-realistic audio-visual deepfakes, intensifying threats to personal security and social trust. Most existing deepfake detectors rely either on uni-mod…
arXiv:2512.16456v2 Announce Type: replace
Abstract: Human motion generation is a challenging task that aims to create realistic motion imitating natural human behaviour. We focus on the well-studied behaviour of priming an object/location for pick up …