8 papers · 1 filter
Report of the 8th LSVOS Challenge: Complex and Multimodal Video Object Segmentation
Chang Liu, Henghui Ding, Lingyi Hong +36
This report summarizes the 8th Large-scale Video Object Segmentation (LSVOS) Challenge, held in conjunction with ECCV 2026. The challenge evaluates video segmentation in three comp…
Key-Frame Reasoning with SAM3: Third Place Solution for the MeViS-Text Track of the 8th LSVOS Challenge
Ce Bian, Xusheng He, Jinrong Zhang +3
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…
VOS-Agent: The 1st Place Solution for the 8th LSVOS Challenge (MOSEv2 Track)
Canyang Wu, Jinrong Zhang, Xusheng He +3
Complex video object segmentation requires robust target propagation under severe occlusion, disappearance and reappearance. Although SAM3 provides strong promptable mask propagati…
Report of the 5th PVUW Challenge: Towards More Diverse Modalities in Pixel-Level Understanding
Chang Liu, Henghui Ding, Nikhila Ravi +40
This report summarizes the objectives, datasets, and top-performing methodologies of the 2026 Pixel-level Video Understanding in the Wild (PVUW) Challenge, hosted at CVPR 2026, whi…
The 1st Winner for 5th PVUW MeViS-Text Challenge: Strong MLLMs Meet SAM3 for Referring Video Object Segmentation
Xusheng He, Canyang Wu, Jinrong Zhang +3
This report presents our winning solution to the 5th PVUW MeViS-Text Challenge. The track studies referring video object segmentation under motion-centric language expressions, whe…
Advancing Complex Video Object Segmentation via Tracking-Enhanced Prompt: The 1st Winner for 5th PVUW MOSE Challenge
Jinrong Zhang, Canyang Wu, Xusheng He +3
In the Complex Video Object Segmentation task, researchers are required to track and segment specific targets within cluttered environments, which rigorously tests a method's capab…
TAPNext: Tracking Any Point (TAP) as Next Token Prediction
Artem Zholus, Carl Doersch, Yi Yang +7
Tracking Any Point (TAP) in a video is a challenging computer vision problem with many demonstrated applications in robotics, video editing, and 3D reconstruction. Existing methods…
TRecViT: A Recurrent Video Transformer
Viorica Pătrăucean, Xu Owen He, Joseph Heyward +10
We propose a novel block for \emph{causal} video modelling. It relies on a time-space-channel factorisation with dedicated blocks for each dimension: gated linear recurrent units (…