Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2610.33627v1 Announce Type: new Abstract: Identity-document portraits are modified during document production by printing, engraving, and integration into the document template. These transform...
arXiv:2610.33639v1 Announce Type: new Abstract: Pedestrian Attribute Recognition (PAR) predicts semantic attributes of individuals, such as gender, age, clothing and accessories, and its descriptions...
arXiv:2610.33713v1 Announce Type: new Abstract: Driver emotion provides an important indication of how drivers perceive and evaluate ongoing traffic situations, making reliable emotion recognition an...
arXiv:2610.33965v1 Announce Type: new Abstract: Automated classification of gastrointestinal (GI) findings in endoscopic images could support early diagnosis, but architectures are often chosen on ac...
arXiv:2610.34033v1 Announce Type: new Abstract: Camera motion recognition requires separating viewpoint changes caused by camera translation, rotation, or zoom from object motion and scene dynamics....
arXiv:2610.34130v1 Announce Type: new Abstract: Indoor IoT cameras can support assisted living and activity-aware spaces, but exporting raw RGB frames raises privacy concerns by exposing facial, clot...
arXiv:2610.34271v1 Announce Type: new Abstract: We propose a novel method for robust point cloud registration with only one tunable parameter. Our method, dubbed TLP, uses truncated $L_p$ functions w...
arXiv:2610.34283v1 Announce Type: new Abstract: Training a spatial VLM to answer which side an object lies on does not require it to preserve the metric displacement that determines that answer, whil...
arXiv:2610.34403v1 Announce Type: new Abstract: Non-rigid structure from motion (NRSfM) aims to recover camera motion and time-varying 3D shape from tracked 2D image measurements. Recent high-perform...
arXiv:2610.34618v1 Announce Type: new Abstract: Recently, point-supervised temporal action localization has attracted increasing attention due to its low annotation cost (only one frame per action in...
arXiv:2610.34662v1 Announce Type: new Abstract: Vision-language models are shifting from offline passive understanding toward online proactive interaction. However, prevailing methods largely rely on...
arXiv:2610.34742v1 Announce Type: new Abstract: Reconstructing 1-m imagery from Sentinel-2 combines two difficulties. The input and the reference are observed by different satellites, which differ in...
arXiv:2610.34765v1 Announce Type: new Abstract: Multi-modal video fusion aims to generate temporally coherent videos with salient targets and rich structural details by integrating complementary info...
arXiv:2610.34819v1 Announce Type: new Abstract: Monocular observations of a tumbling object can support a precise fitted trajectory without establishing that the recovered physical axis is correct. W...
arXiv:2610.34854v1 Announce Type: new Abstract: When zooming between dual cameras on smartphones, prominent discontinuities in both geometric perspective and color rendition inevitably degrade the vi...
arXiv:2610.34879v1 Announce Type: new Abstract: Document layout analysis (DLA) faces a long-standing dilemma: existing methods either capture rich local details at prohibitive computational cost (e.g...
arXiv:2610.34925v1 Announce Type: new Abstract: In surgical instrument segmentation, the increasing variety of instruments over time poses a significant challenge for existing neural networks, as the...
arXiv:2610.35017v1 Announce Type: new Abstract: Text-steerable visual encoders condition a frozen Vision Transformer on a natural-language prompt and point at the matching image region, producing pro...
arXiv:2610.35018v1 Announce Type: new Abstract: Monocular depth estimation has advanced rapidly with the development of foundation models that demonstrate strong zero-shot generalisation across diver...
arXiv:2610.35038v1 Announce Type: new Abstract: Small uncrewed underwater vehicles are proliferating and threaten maritime security, yet evade sonar and magnetic sensors built for larger submarines....