JX
Junyu Xie
cs.CVcs.AIcs.CL
On Valency
published · living versionsW_6xfxhmga·v1 · currentpublished
As the Story Unfolds: Watching a Film and Identifying Characters as a Human Does
with Zhongrui Gui, Tengda Han, Weidi Xie, Andrew Zisserman
1 version
Preprints & journals
10 papers in the corpus · 2022–2026GMOS: Grounding Moving Object Segmentation in 3D Space and Time2605.30352v1 · Junyu Xie, Tengda Han, Weidi Xie et al.2026 · 0 citationsarXiv
More than a Moment: Towards Coherent Sequences of Audio Descriptions2510.25440v1 · Eshika Khandelwal, Junyu Xie, Tengda Han et al.2025 · 0 citationsarXiv
Character-Centric Understanding of Animated Movies2509.12204v1 · Zhongrui Gui, Junyu Xie, Tengda Han et al.2025 · 0 citationsarXiv
Shot-by-Shot: Film-Grammar-Aware Training-Free Audio Description Generation2504.01020v2 · Junyu Xie, Tengda Han, Max Bain et al.2025 · 0 citationsarXiv
FacaDiffy: Inpainting Unseen Facade Parts Using Diffusion Models2502.14940v1 · Thomas Froech, Olaf Wysocki, Yan Xia et al.2025 · 2 citationsarXiv
AutoAD-Zero: A Training-Free Framework for Zero-Shot Audio Description2407.15850v2 · Junyu Xie, Tengda Han, Max Bain et al.2024 · 14 citationsarXiv
Moving Object Segmentation: All You Need Is SAM (and Flow)2404.12389v2 · Junyu Xie, Charig Yang, Weidi Xie et al.2024 · 17 citationsarXiv
Appearance-Based Refinement for Object-Centric Motion Segmentation2312.11463v2 · Junyu Xie, Weidi Xie, Andrew Zisserman2023 · 3 citationsarXiv
SHAP-EDITOR: Instruction-guided Latent 3D Editing in Seconds2312.09246v1 · Minghao Chen, Junyu Xie, Iro Laina et al.2023 · 18 citationsarXiv
Segmenting Moving Objects via an Object-Centric Layered Representation2207.02206v2 · Junyu Xie, Weidi Xie, Andrew Zisserman2022 · 23 citationsarXiv
Career total: 13 works. 10 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.