3 citations · 4 across the 18 of their papers we have counts for
20 papers
Hi-OPD: Hierarchy-Aware Open-Prompt Detection for Remote Sensing Images
Jinlong Hu, Yi Zhang, Zhiqi Xia +2
Hi-OPD addresses a failure mode left uncontrolled by flat open-prompt training: descendant retrieval need not persist under ancestor queries when multi-source remote sensing annota…
Actor as Its Own Critic: Unifying Region Understanding and Localization via CycleGRPO
Xin Zhang, Haochen Wang, Yikang Zhou +3
This paper introduces Actor as Its Own Critic, a unified reinforcement learning framework, Cycle Group Relative Policy Optimization (CycleGRPO), that jointly optimizes region under…
PixelEyes: Decoupling Perception and Reasoning for Pinpoint Visual Evidence Seeking
Dengxian Gong, Yuanzheng Wu, Haobo Yuan +11
This paper explores multi-turn visual reasoning and observes that MLLMs repeatedly fail to localize the target, leading to long, redundant trajectories. We attribute this failure t…
MotionAtlas: Detailed Region Captioning for Motion-Centric Videos
Weisong Liu, Haochen Wang, Kuan Gao +8
We propose MotionAtlas, a system for detailed captioning of motion-centric videos, comprising (1) a dedicated human-annotated benchmark, (2) a scalable, high-quality pipeline to co…
World Action Models: The Next Frontier in Embodied AI
Siyin Wang, Junhao Shi, Zhaoyang Fu +11
Vision-Language-Action (VLA) models have achieved strong semantic generalization for embodied policy learning, yet they learn reactive observation-to-action mappings without explic…
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…
SaSaSaSa2VA: 2nd Place of the 5th PVUW MeViS-Text Track
Dengxian Gong, Quanzhu Niu, Shihao Chen +6
Referring video object segmentation (RVOS) commonly grounds targets in videos based on static textual cues. MeViS benchmark extends this by incorporating motion-centric expressions…
SAMTok: Representing Any Mask with Two Words
Yikang Zhou, Tao Zhang, Dengxian Gong +13
Pixel-wise capabilities are essential for building interactive intelligent systems. However, pixel-wise multi-modal LLMs (MLLMs) remain difficult to scale due to complex region-lev…
The 1st Solution for 7th LSVOS RVOS Track: SaSaSa2VA
Quanzhu Niu, Dengxian Gong, Shihao Chen +6
Referring video object segmentation (RVOS) requires segmenting and tracking objects in videos conditioned on natural-language expressions, demanding fine-grained understanding of b…
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…
Grasp Any Region: Towards Precise, Contextual Pixel Understanding for Multimodal LLMs
Haochen Wang, Yuhao Wang, Tao Zhang +13
While Multimodal Large Language Models (MLLMs) excel at holistic understanding, they struggle in capturing the dense world with complex scenes, requiring fine-grained analysis of i…
Beyond Appearance: Geometric Cues for Robust Video Instance Segmentation
Quanzhu Niu, Yikang Zhou, Shihao Chen +2
Video Instance Segmentation (VIS) fundamentally struggles with pervasive challenges including object occlusions, motion blur, and appearance variations during temporal association.…
DenseWorld-1M: Towards Detailed Dense Grounded Caption in the Real World
Xiangtai Li, Tao Zhang, Yanwei Li +13
Multimodal Large Language Models (MLLMs) demonstrate a complex understanding of scenes, benefiting from large-scale and high-quality datasets. Most existing caption datasets lack t…
Dense360: Dense Understanding from Omnidirectional Panoramas
Yikang Zhou, Tao Zhang, Dizhe Zhang +3
Multimodal Large Language Models (MLLMs) require comprehensive visual inputs to achieve dense understanding of the physical world. While existing MLLMs demonstrate impressive world…
An Empirical Study of GPT-4o Image Generation Capabilities
Sixiang Chen, Jinbin Bai, Zhuoran Zhao +16
The landscape of image generation has rapidly evolved, from early GAN-based approaches to diffusion models and, most recently, to unified generative architectures that seek to brid…
Are They the Same? Exploring Visual Correspondence Shortcomings of Multimodal LLMs
Yikang Zhou, Tao Zhang, Shilin Xu +7
Recent advancements in multimodal large language models (MLLM) have shown a strong ability in visual perception, reasoning abilities, and vision-language understanding. However, th…
P2PFormer: A Primitive-to-polygon Method for Regular Building Contour Extraction from Remote Sensing Images
Tao Zhang, Shiqing Wei, Yikang Zhou +3
Extracting building contours from remote sensing imagery is a significant challenge due to buildings' complex and diverse shapes, occlusions, and noise. Existing methods often stru…
DVIS-DAQ: Improving Video Segmentation via Dynamic Anchor Queries
Yikang Zhou, Tao Zhang, Shunping Ji +2
Modern video segmentation methods adopt object queries to perform inter-frame association and demonstrate satisfactory performance in tracking continuously appearing objects despit…
DVIS++: Improved Decoupled Framework for Universal Video Segmentation
Tao Zhang, Xingye Tian, Yikang Zhou +7
We present the \textbf{D}ecoupled \textbf{VI}deo \textbf{S}egmentation (DVIS) framework, a novel approach for the challenging task of universal video segmentation, including video…
1st Place Solution for the 5th LSVOS Challenge: Video Instance Segmentation
Tao Zhang, Xingye Tian, Yikang Zhou +7
Video instance segmentation is a challenging task that serves as the cornerstone of numerous downstream applications, including video editing and autonomous driving. In this report…