← Back to all news
arXiv Computer Vision By Rangya Zhang, Jiaping Xiao, Yujing Shang, Yuhang Zhang, Mingsheng Li, Mir Feroskhan

OmniGlimpse: Asymmetric Identity Memory for Online Multi-View Tracking

Read the original on arXiv Computer Vision →

OmniGlimpse introduces an asymmetric propose‑verify framework for online multi‑view tracking, separating short‑term adaptive association from long‑term stable identity consolidation. It maps short‑term local and cross‑view evidence into target‑specific adaptive spaces for proposing associations, while maintaining long‑term identity distributions in a canonical space defined by a frozen encoder for verification. The method achieves significant gains over the best online baseline on M3Track and MvMHAT, outperforming offline‑trained references in IDF1 without any offline scene‑specific training.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Computer Vision
Oct 7

Toward Open-World Video Segmentation over Long Horizons

The paper introduces Savvy, a zero‑shot, semi‑online, class‑agnostic system that persistently discovers objects and maintains their identities in long videos, and OGA, an evaluation suite that rewards coherent part‑level predictions even when their granularity differs from reference annotations. Savvy combines modular mask discovery, deferred admission based on accumulated evidence, and track consolidation to keep an evolving object set, outperforming DEVA+SAM and EntitySAM on ScanNet and HM3D datasets in metrics such as VPQ_inf, STQ, and AQ. OGA further distinguishes coherent part‑level support from temporal identity failures, revealing that conventional one‑to‑one VPQ metrics are sensitive to annotation granularity and that temporal failures can be detected even when frame‑level masks remain unchanged.

By Qing Su, Kaiyang Li, Yuan Zhuang, Fei Miao, Shihao Ji
computer-vision
More like this →
arXiv AI
Jun 11

ARGUS: Stacked Multi-View Identity Mosaic Injection for Subject-Preserving Video Generation

arXiv:2606. 11670v1 Announce Type: cross Abstract: Subject-preserving video generation is not solved by frontal-face similarity alone: a generated person must remain recognizable across motion, large viewpoint changes, expression shifts, occlusion, scale variation, and conflicts among text, first-frame, and identity references.

By Zijie Meng, Jiwen Liu, Yufei Liu, Chengzhuo Tong, Xiaoqiang Liu, Yuanxing Zhang, Yulong Xu, Pengfei Wan
diffusionbenchmarks
More like this →