DM
Deshui Miao
cs.CVcs.AICLIP modelcs.CGcs.CLcs.HCcs.SDeess.IVFeature enhancementImage Processing, Computer-Assisted
On Valency
published · living versionsW_fbtadppd·v1 · currentpublished
Think Visually Across Space and Time: Grounded Reasoning for Video Segmentation
with Junwei Wen, Guangming Lu, Ming-Hsuan Yang, Xin Li +1
1 version
W_w8n2x5gs·v1published
Preprints & journals
18 papers in the corpus · 2021–2026DeOverlay: A Benchmark and Source-Anchored Flow for Video Overlay Removal2610.26081v1 · Deshui Miao, Yuhang Ma, Shaoyong Jia et al.2026 · 0 citationsarXivon Valency
Think Visually Across Space and Time: Grounded Reasoning for Video Segmentation2610.25090v1 · Junwei Wen, Deshui Miao, Guangming Lu et al.2026 · 0 citationsarXivon Valency
DeltaStreamer: Towards Human-Like Agentic Streaming Video Understanding2610.19849v1 · Boyuan Sun, Deshui Miao, Wenzhao Gao et al.2026 · 0 citationsarXiv
GeoWeaver: Grounding Visual Tokens with Geometric Evidence before Scene Reasoning2605.22558v1 · Deshui Miao, Xingsen Huang, Yameng Gu et al.2026 · 0 citationsarXiv
RCoT-Seg: Reinforced Chain-of-Thought for Video Reasoning and Segmentation2605.07334v1 · Junwei Wen, Deshui Miao, Guangming Lu et al.2026 · 0 citationsarXiv
Report of the 5th PVUW Challenge: Towards More Diverse Modalities in Pixel-Level Understanding2604.26031v1 · Chang Liu, Henghui Ding, Nikhila Ravi et al.2026 · 0 citationsarXiv
APRVOS: 1st Place Winner of 5th PVUW MeViS-Audio Track2604.18665v1 · Deshui Miao, Yameng Gu, Chao Yang et al.2026 · 0 citationsarXiv
AgentRVOS for MeViS-Text Track of 5th PVUW Challenge: 3rd Method2604.22836v1 · Deshui Miao, Chao Yang, Chao Tian et al.2026 · 0 citationsarXiv
OAMVOS:2nd Report for 5th PVUW MOSE Track2604.22837v1 · Deshui Miao, Xingsen Huang, Yameng Gu et al.2026 · 0 citationsarXiv
SGAFuse: Semantic-guided adaptive fusion for RGB-thermal images via dynamic gating.41797193 · Yang, Chao, Miao, Deshui, Tian, Chao et al.2026 · 0 citationsNeural networks : the official journal of the International Neural Network Society. 2026;200:108779
Fusing in 3D: Free-Viewpoint Fusion Rendering with a 3D Infrared-Visible Scene Representation2601.12697v1 · Chao Yang, Deshui Miao, Chao Tian et al.2026 · 0 citationsarXiv
LSVOS Challenge Report: Large-scale Complex and Long Video Object Segmentation2409.05847v1 · Henghui Ding, Lingyi Hong, Chang Liu et al.2024 · 2 citationsarXiv
Discriminative Spatial-Semantic VOS Solution: 1st Place Solution for 6th LSVOS2408.16431v1 · Deshui Miao, Yameng Gu, Xin Li et al.2024 · 0 citationsarXiv
Learning Spatial-Semantic Features for Robust Video Object Segmentation2407.07760v2 · Xin Li, Deshui Miao, Zhenyu He et al.2024 · 0 citationsProceedings of the 13th International Conference on Learning Representations (ICLR 2025)
PVUW 2024 Challenge on Complex Video Understanding: Methods and Results2406.17005v1 · Henghui Ding, Chang Liu, Yunchao Wei et al.2024 · 2 citationsarXiv
1st Place Solution for MOSE Track in CVPR 2024 PVUW Workshop: Complex Video Object Segmentation2406.04600v1 · Deshui Miao, Xin Li, Zhenyu He et al.2024 · 0 citationsarXiv
Spatial-Temporal Multi-level Association for Video Object Segmentation2404.06265v1 · Deshui Miao, Xin Li, Zhenyu He et al.2024 · 6 citationsarXiv
Simple Contrastive Representation Adversarial Learning for NLP Tasks2111.13301v2 · Deshui Miao, Jiaqi Zhang, Wenbo Xie et al.2021 · 8 citationsarXiv
Career total: 26 works. 18 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.