TS
Tanfeng Sun
cs.CVcs.MMcs.LGcs.AIcs.CRcs.SDeess.ASVideo Recording
On Valency
published · living versionsW_tes6s8ws·v1 · currentpublished
OmniGround: Strengthening Omni-Modal Temporal Grounding via Attention-Consistency Training
with Zixuan Chen, Depeng Wang, Hao Lin, Ke Xu +3
1 version
W_fed2dnk5·v1published
Preprints & journals
11 papers in the corpus · 2014–2026SAPO: Self-Supervised Attention Policy Optimization for Improving Temporal Video Grounding in Vision-Language Models2610.25923v1 · Zixuan Chen, Depeng Wang, Wei Chen et al.2026 · 0 citationsarXivon Valency
OmniGround: Strengthening Omni-Modal Temporal Grounding via Attention-Consistency Training2610.25929v1 · Zixuan Chen, Depeng Wang, Hao Lin et al.2026 · 0 citationsarXivon Valency
RED: Reconstruction Evolution Dynamics for Generalizable AI-Generated Image Detection2609.36822v1 · Wenpeng Mu, Junshan Jin, Tanfeng Sun et al.2026 · 0 citationsarXiv
IterInject: Indirect Prompt Injection Against LLM Agents via Feedback-Guided Iterative Optimization2605.24659v1 · Zixuan Chen, Jiaxiang Chen, Li Luo et al.2026 · 0 citationsarXiv
AVID: A Benchmark for Omni-Modal Audio-Visual Inconsistency Understanding via Agent-Driven Construction2604.13593v2 · Zixuan Chen, Depeng Wang, Hao Lin et al.2026 · 0 citationsarXiv
FGAS: Fixed Decoder Network-Based Audio Steganography with Adversarial Perturbation Generation2505.22266v3 · Jialin Yan, Yu Cheng, Zhaoxia Yin et al.2025 · 0 citationsarXiv
Dynamic Optimization and Safety Indicator Injection for Jailbreaking Text-to-Image Models with Multimodal Safety Filters2505.18979v2 · Zixuan Chen, Hao Lin, Ke Xu et al.2025 · 0 citationsarXiv
Joint Learning of Deep Texture and High-Frequency Features for Computer-Generated Image Detection2209.03322v1 · Qiang Xu, Shan Jia, Xinghao Jiang et al.2022 · 1 citationarXiv
Gait Identification under Surveillance Environment based on Human Skeleton2111.11720v2 · Xingkai Zheng, Xirui Li, Ke Xu et al.2021 · 1 citationarXiv
Coverless Video Steganography based on Maximum DC Coefficients2012.06809v1 · Laijin Meng, Xinghao Jiang, Zhenzhen Zhang et al.2020 · 6 citationsarXiv
A robust H.264/AVC video watermarking scheme with drift compensation.24672376 · Jiang, Xinghao, Sun, Tanfeng, Zhou, Yue et al.2015 · 7 citationsTheScientificWorldJournal. 2014;2014:802347
Career total: 184 works. 11 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.