AK
Alex C. Kot
cs.CVcs.AIcs.CReess.IV
On Valency
published · living versionsW_5qaersub·v1 · currentpublished
Taming Noise Initialization for Zero-shot Video Restoration with Image Diffusion Priors
with Chong Wang, Zixuan Fu, Hao Cheng, Siyuan Yang +1
1 version
Preprints & journals
13 papers in the corpus · 2024–2026Image Diffusion Models Are Good 3D Human Motion Generators2610.14254v1 · Siyuan Yang, Chong Wang, Hao Cheng et al.2026 · 0 citationsarXiv
TAME:Topology-Aware Text-Driven Motion Editing across Heterogeneous Humanoid Skeletons2610.04529v1 · Qichen Zheng, Siyuan Yang, Chong Wang et al.2026 · 0 citationsarXiv
Forensic-Aware Continual Adaptation for Image Forgery Localization2609.38251v1 · Chenqi Kong, Song Xia, Anwei Luo et al.2026 · 0 citationsarXiv
FVeinSyn: Synthetic Finger Vein Image Generator.42678849 · Wang, Yifan, Gui, Jie, Kong, Adams Wai Kin et al.2026 · 0 citationsIEEE transactions on pattern analysis and machine intelligence. 2026;PP
CertVLA: Certified Defense against Physical Visual Attacks for Vision-Language-Action Models2608.20791v1 · Hui Lu, Zhijie Peng, Yuqi Lin et al.2026 · 0 citationsarXiv
IdentiFace: Multi-Modal Iterative Diffusion Framework for Identifiable Suspect Face Generation in Crime Investigations2605.00526v1 · Weichen Liu, Yixin Yang, Changsheng Chen et al.2026 · 0 citationsarXiv
ActivityForensics: A Comprehensive Benchmark for Localizing Manipulated Activity in Videos2604.03819v1 · Peijun Bao, Anwei Luo, Gang Pan et al.2026 · 0 citationsarXiv
Skeleton-to-Image Encoding: Enabling Skeleton Representation Learning via Vision-Pretrained Models2603.05963v2 · Siyuan Yang, Jun Liu, Hao Cheng et al.2026 · 0 citationsarXiv
E.M.Ground: A Temporal Grounding Vid-LLM with Holistic Event Perception and Matching2602.05215v1 · Jiahao Nie, Wenbin An, Gongjie Zhang et al.2026 · 0 citationsarXiv
Cross-Domain Few-Shot Segmentation via Multi-view Progressive Adaptation2602.05217v2 · Jiahao Nie, Guanqiao Fu, Wenbin An et al.2026 · 0 citationsarXiv
Boosting SAM for Cross-Domain Few-Shot Segmentation via Conditional Point Sparsification2602.05218v1 · Jiahao Nie, Yun Xing, Wenbin An et al.2026 · 0 citationsarXiv
Universal Adversarial Attacks against Closed-Source MLLMs via Target-View Routed Meta Optimization2601.23179v2 · Hui Lu, Yi Yu, Yiming Yang et al.2026 · 0 citationsarXiv
From Chaos to Clarity: 3DGS in the Dark2406.08300v1 · Zhihao Li, Yufei Wang, Alex Kot et al.2024 · 4 citationsarXiv
Career total: 15 works. 13 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.