arXiv:2609.39157v1 Announce Type: new Abstract: Video object removal presents a uniquely difficult editing challenge. Because a removal prompt specifies only what to erase rather than what to generat...
arXiv:2608.24093v1 Announce Type: cross Abstract: Self-supervised representation learning for 4D point cloud videos is challenging because annotations are costly and reconstruction-based pretraining...
arXiv:2607. 24570v1 Announce Type: cross Abstract: Large-scale video platforms process millions of uploads hourly, requiring moderation systems that can localize when and where policy violations occur within each video.
arXiv:2610.30724v2 Announce Type: replace-cross Abstract: Video provides a natural source of supervision: what happens next serves as a learning signal for visual world modeling. Yet masked video pre...
arXiv:2609.40347v1 Announce Type: new Abstract: We introduce VideoMSN, a Masked Siamese Network framework for efficient self-supervised spatio-temporal representation learning in videos. Instead of r...
The paper introduces VANE, a self‑supervised visual pretraining framework that learns from next‑frame prediction in embedding space. It uses a causal encoder to summarize past observations, a state predictor to infer the representation of the entire next frame, and a lightweight generative decoder to reconstruct fine‑grained spatial detail. By applying the same objective to both videos and still images through a local‑to‑global crop sequence, VANE achieves state‑of‑the‑art performance on anticipation, recognition, and dense perception benchmarks, notably outperforming V‑JEPA on EPIC‑KITCHENS‑100 action anticipation.
arXiv:2607. 01962v1 Announce Type: cross Abstract: We study the challenging problem of novel view video synthesis from single images or monocular videos.
arXiv:2606. 25225v1 Announce Type: cross Abstract: Self-supervised learning from large-scale video data has emerged as a dominant paradigm for visual representation learning.
LayerRecall is a memory router for autoregressive video diffusion that selectively retrieves and injects historical key/value states into specific layers of the model, based on the current context. It addresses the problem that existing memory mechanisms expose nonlocal history but do not guarantee effective use, by recognizing that different layers prefer current, recent, or distant context. The method, combined with Cross‑Horizon Prediction Matching, achieves state‑of‑the‑art long‑range consistency on MemoBench and MovieBench while maintaining local continuity and incurring negligible inference overhead.
We study the challenging problem of novel view video synthesis from single images or monocular videos. Existing methods, which operate under the assumption that pre-trained video models lack native novel view synthesis capability and enforce view alignment via camera conditioning, task-specific fine-tuning, or stepwise hard denoising guidance, often suffer from artifacts and compromised global scene consistency.
arXiv:2607.14935v2 Announce Type: replace Abstract: Recent advances in video understanding have spanned motion, long video, and streaming interaction, driving this field toward real-world application...
arXiv:2610.35148v1 Announce Type: new Abstract: Recent advances in generative video models have improved visual realism, making detection increasingly dependent on subtle temporal inconsistencies. Ho...