← Back to all news
arXiv Computer Vision By Abu Hanif Muhammad Syarubany, Jaehyun Jang, Siwoo Lim, Seungyeon Ryu, Chang D. Yoo

Event-Driven Refresh and Recurrence Memory to Reduce Stale Grounding in Referring Video Object Segmentation

Read the original on arXiv Computer Vision →

The paper introduces Event-Driven Refresh + Recurrence Memory (EDRRM) to improve Referring Video Object Segmentation (RVOS). EDRRM selectively re-invokes the Sa2VA model at stable change points, using an EMA‑smoothed event score from tracking cues and a recurrence memory that retrieves anchor frames via CLIP similarity. Experiments on Ref‑DAVIS17, MeViS, and ReVOS show that EDRRM maintains or surpasses J&F scores while reducing refresh calls and false‑positive failures, with modest overhead compared to Sa2VA inference.

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
Aug 25

Sa2VA: Marrying SAM2 with MLLM for Dense Grounded Understanding of Images and Videos

arXiv:2501.04001v4 Announce Type: replace Abstract: This work presents Sa2VA, the first comprehensive, unified model for dense grounded understanding of both images and videos. Unlike existing multi-...

By Haobo Yuan, Xiangtai Li, Tao Zhang, Yueyi Sun, Zilong Huang, Shilin Xu, Shunping Ji, Yunhai Tong, Lu Qi, Jiashi Feng, Ming-Hsuan Yang
llmscomputer-visionfine-tuningmultimodalbenchmarks
More like this →
arXiv Computer Vision
Sep 24

LiAM-SAM: Lifecycle-Aware Memory for Robust SAM2-Based MOT

LiAM‑SAM is a lifecycle‑aware memory framework designed to improve segmentation‑based multi‑object tracking (MOT) with the SAM2 foundation video model. It addresses three common failure modes—faulty track initiation, memory drift during close interactions, and unreliable re‑identification after occlusion—by introducing contrastive track initiation, motion‑ and geometry‑grounded memory correction, and adaptive context memory. The system achieves state‑of‑the‑art HOTA and IDF1 scores, with ablations showing significant gains in association metrics and a 96% reduction in identity switches.

By Gr\'egoire Francisco, Alessandro D'Amico, Samuele Costantini, Gianpiero Francesca, Lorenzo Garattoni
computer-visionefficiencybenchmarks
More like this →
Hugging Face Trending Papers
Aug 17

Unlocking Motion in Expressions: Temporal Calibration for Referring Video Object Segmentation

Referring Video Object Segmentation (RVOS) aims to segment referred objects at the pixel level in video sequences based on natural language descriptions. Existing methods typically introduce motion information within a unified cross-modal temporal modeling framework, where language cues are used for target localization and segmentation.

computer-visionmultimodalbenchmarks
More like this →