activity
20242026
collaborators

6 papers

cs.CV2026

Evidence-Grounded Trustworthy Multimodal Reasoning and Evaluation Benchmark in Complex Urban Scenes

Zhaoyang Wei, Bowen Jiang, Xumeng Han +6

While Multimodal Large Language Models (MLLMs) demonstrate impressive performance in benign scenarios, their cognitive reliability deteriorates significantly in complex scenes unde…

cs.CV2026

HeroGS: Hierarchical Guidance for Robust 3D Gaussian Splatting under Sparse Views

Jiashu Li, Xumeng Han, Zhaoyang Wei +5

3D Gaussian Splatting (3DGS) has recently emerged as a promising approach in novel view synthesis, combining photorealistic rendering with real-time efficiency. However, its succes…

cs.CV2026

SAPNet++: Evolving Point-Prompted Instance Segmentation with Semantic and Spatial Awareness

Zhaoyang Wei, Xumeng Han, Xuehui Yu +4

Single-point annotation is increasingly prominent in visual tasks for labeling cost reduction. However, it challenges tasks requiring high precision, such as the point-prompted ins…

cs.CV2025

VER-Bench: Evaluating MLLMs on Reasoning with Fine-Grained Visual Evidence

Chenhui Qiang, Zhaoyang Wei, Xumeng Han +5

With the rapid development of MLLMs, evaluating their visual capabilities has become increasingly crucial. Current benchmarks primarily fall into two main types: basic perception b…

cs.CV2025

P2Object: Single Point Supervised Object Detection and Instance Segmentation

Pengfei Chen, Xuehui Yu, Xumeng Han +5

Object recognition using single-point supervision has attracted increasing attention recently. However, the performance gap compared with fully-supervised algorithms remains large.…

cs.CV2024

ClickTrack: Towards Real-time Interactive Single Object Tracking

Kuiran Wang, Xuehui Yu, Wenwen Yu +5

Single object tracking(SOT) relies on precise object bounding box initialization. In this paper, we reconsidered the deficiencies in the current approaches to initializing single o…