The MeViS-Audio track asks a system to segment the objects described by a spoken motion expression throughout a video and to return empty masks when the described target is absent. We present a simple staged solution. Qwen3-ASR first converts speech into text. Several video mask tracks are then produced with complementary grounding and segmentation models. Instead of trusting a single prediction, we select the track that has the highest average mask agreement with the other candidates. A small set of explicit direction, count, and plural rules corrects queries that require more than ordinary single-object tracking. Finally, a video-level classifier combines visual, audio-visual, and within-video query scores to decide whether any target is present. The submitted system obtains 0.5952 J&F, 0.7931 no-target accuracy, 0.9205 target accuracy, and a final score of 0.769589. The challenge organizers notified our team that this result ranked first in the track.
A training-free framework for audio-guided video object segmentation, which integrates Multimodal Large Language Models (MLLMs) with SAM-based segmentation models and employs SAM-based models for accurate object mask generation is presented.
Liang-Tao Shi, Jinxia Xie, Xian-Tao Hu et al.· 0 citations
This report presents a two-stage, training-free solution for the MeViS-Text track of the 8th LSVOS Challenge, which ranked third on the challenge test set, obtaining J&F, J, F, N-acc.
Ce Bian, X. He, Jin-Rong Zhang et al.· 0 citations
Speech-guided referring video object segmentation aims to recover the mask tracks of objects specified by a spoken motion description. Here, speech carries a linguistic instruction rather than acoustic evidence from a sounding object, so a solution must connect speech recognition, motion-centric temporal grounding, mas...
Jinxing Zhou, Suiyi Zhao, Yang-Hao Zhou et al.· 0 citations
Across the nine leading solutions, foundation segmentation models are combined with target-aware memory, multimodal reasoning, explicit target-existence verification, agentic interaction, and corrective tracking, illustrating a broader transition from single-model mask propagation toward modular pipelines that reason a...
Chang Liu, Heng-Hui Ding, Ling-Yi Hong et al.· 0 citations
This work proposes REcognition-based Zero-shot Extraction (REZE), a simple training-free method that splits the video into short clips, asks the model for a clip-level confidence score for the query, and uses a deterministic algorithm to convert the resulting score curve into the output required by the task.
Boyang Albert Li, Chen-Hui Gou, Jianfei Cai· 0 citations
SCoPE is introduced, a training-free framework in which all queried labels compete for shared evidence and each modality guides event selection in the other, and derives an exact condition for when this competition removes an FCA in a two-label fit.
J. Jeong, Junho Yoon, Hyunju Kim et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
