Key-Frame Reasoning with SAM3: Third Place Solution for the MeViS-Text Track of the 8th LSVOS Challenge

2026-08-17

AI Summary

本文提出了一种无需训练的两阶段方法，通过Gemini-3.1 Pro分解视频事件并选择关键帧，然后使用SAM3-agent生成并传播像素级掩模，解决了基于自然语言表达的对象定位与分割问题。

Abstract

This report presents a two-stage, training-free solution for the MeViS-Text track of the 8th LSVOS Challenge. The task requires a model to localize and segment the object specified by a natural-language expression throughout a video. Such expressions often depend on temporal cues, including actions, interactions, directions, and relative positions. Our first stage uses Gemini-3.1 Pro via API to decompose a video-level event into instance-level targets, select a key frame for each target, and generate a discriminative description aligned with that frame. In the second stage, SAM3-agent produces a pixel-level seed mask on the selected frame, and the SAM3 video tracker propagates the mask bidirectionally through the video. Valid instances are grounded and propagated independently before their frame-wise masks are merged. All local SAM3 processing runs on a single NVIDIA GeForce RTX 4090 without task-specific training or model ensembling. Our method ranked third on the challenge test set, obtaining J&F, J, F, N-acc., T-acc., and Final scores of 0.761, 0.7367, 0.7852, 0.8333, 0.9755, and 0.856593, respectively.

Problem

• natural-language expression
• video localization
• object segmentation
• temporal cues

Innovation

• two-stage
• training-free
• Gemini-3.1 Pro
• SAM3-agent
• bidirectional mask propagation