SJ

Shaoyong Jia

cs.CVcs.AIcs.HCcs.LGcs.SDeess.AS

On Valency

published · living versions

W_w8n2x5gs·v1 · currentpublished

DeOverlay: A Benchmark and Source-Anchored Flow for Video Overlay Removal

with Deshui Miao, Yuhang Ma, Wenzhao Gao, Yue Zhang +2

1 version

Preprints & journals

4 papers in the corpus · 2019–2026

DeOverlay: A Benchmark and Source-Anchored Flow for Video Overlay Removal2610.26081v1 · Deshui Miao, Yuhang Ma, Shaoyong Jia 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

Towards Universal Video MLLMs with Attribute-Structured and Quality-Verified Instructions2602.13013v1 · Yunheng Li, Hengrui Zhang, Meng-Hao Guo et al.2026 · 0 citationsarXiv

Cross-modal supervised learning for better acoustic representations1911.07917v2 · Shaoyong Jia, Xin Shu, Yang Yang et al.2019 · 2 citationsarXiv

Career total: 10 works. 4 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.