14 papers
Competitive Memory Readout for Robust Video Object Segmentation: 2nd Place Technical Report for the MOSEv2 Track of the 8th LSVOS Challenge
Mingqi Gao, Sijie Li, Jungong Han
We present our solution for the MOSEv2 track of the 8th Large-scale Video Object Segmentation (LSVOS) Challenge at ECCV 2026. The challenge evaluates robust video object segmentati…
Hy-Embodied-VLM-1.0: Efficient Physical-World Agents
Ziyi Wang, Xumin Yu, Yongming Rao +19
Building capable embodied agents requires not only multimodal perception and understanding, but also agentic capabilities for reasoning about actions, adapting to evolving situatio…
Planning Takes More Than Token Prediction: Causal Plan for Benchmarking and Building Physically Grounded Embodied Reasoners
Zirong Song, Zheng Lu, Mingqi Gao +11
Current benchmarks for embodied vision-language planning inadvertently favor linguistic next-token prediction over physically grounded next-state reasoning. This rewards models tha…
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…
Reinforcing 3D Understanding in Point-VLMs via Geometric Reward Credit Assignment
Jingkun Chen, Ruoshi Xu, Mingqi Gao +2
Point-Vision-Language Models promise to empower embodied agents with executable spatial reasoning, yet they frequently succumb to geometric hallucination where predicted 3D structu…
UniSurgSAM: A Unified Promptable Model for Reliable Surgical Video Segmentation
Haofeng Liu, Ziyue Wang, Alex Y. W. Kong +6
Surgical video segmentation is fundamental to computer-assisted surgery. In practice, surgeons need to dynamically specify targets throughout extended procedures, using heterogeneo…
Re-Prompting SAM 3 via Object Retrieval: 3rd of the 5th PVUW MOSE Track
Mingqi Gao, Sijie Li, Jungong Han
This technical report explores the MOSEv2 track of the PVUW 2026 Challenge, which targets complex semi-supervised video object segmentation. Built on SAM~3, we develop an automatic…
Show Me When and Where: Towards Referring Video Object Segmentation in the Wild
Mingqi Gao, Jinyu Yang, Jingnan Luo +4
Referring video object segmentation (RVOS) has recently generated great popularity in computer vision due to its widespread applications. Existing RVOS setting contains elaborately…
SAM-Body4D: Training-Free 4D Human Body Mesh Recovery from Videos
Mingqi Gao, Yunqi Miao, Jungong Han
Human Mesh Recovery (HMR) aims to reconstruct 3D human pose and shape from 2D observations and is fundamental to human-centric understanding in real-world scenarios. While recent i…
LSVOS 2025 Challenge Report: Recent Advances in Complex Video Object Segmentation
Chang Liu, Henghui Ding, Kaining Ying +46
This report presents an overview of the 7th Large-scale Video Object Segmentation (LSVOS) Challenge held in conjunction with ICCV 2025. Besides the two traditional tracks of LSVOS…
The 1st Solution for MOSEv2 Challenge 2025: Long-term and Concept-aware Video Segmentation via SeC
Mingqi Gao, Jingkun Chen, Yunqi Miao +3
This technical report explores the MOSEv2 track of the LSVOS Challenge, which targets complex semi-supervised video object segmentation. By analysing and adapting SeC, an enhanced…
Point Linguist Model: Segment Any Object via Bridged Large 3D-Language Model
Zhuoxu Huang, Mingqi Gao, Jungong Han
3D object segmentation with Large Language Models (LLMs) has become a prevailing paradigm due to its broad semantics, task flexibility, and strong generalization. However, this par…
Unlocking the Potential of Diffusion Priors in Blind Face Restoration
Yunqi Miao, Zhiyu Qu, Mingqi Gao +4
Although diffusion prior is rising as a powerful solution for blind face restoration (BFR), the inherent gap between the vanilla diffusion model and BFR settings hinders its seamle…
THU-Warwick Submission for EPIC-KITCHEN Challenge 2025: Semi-Supervised Video Object Segmentation
Mingqi Gao, Haoran Duan, Tianlu Zhang +1
In this report, we describe our approach to egocentric video object segmentation. Our method combines large-scale visual pretraining from SAM2 with depth-based geometric cues to ha…