CORTEXA
← Browse
arxivcs.CV2026-07-10

Adaptive Latent Trajectory Anchoring for Action Segmentation Dataset Condensation

Artheme Gauthier-Villar, Guodong Ding, Angela Yao

Dataset condensation for action segmentation synthesizes compact, informative representations of long, untrimmed video datasets. The existing approach relies on Variational Autoencoders and an iterative latent optimization; it is computationally expensive and suffers from over-smoothed reconstructions and rigid temporal constraints. This paper proposes to shift the condensation paradigm from optimization-based inversion to deterministic latent mapping. By leveraging Denoising Diffusion Implicit Models, we represent action segments as continuous trajectories anchored by sparse latent points in the noise manifold. To maximize representational efficiency, we introduce an adaptive allocation mechanism that dynamically redistributes the anchoring budget based on segment-wise reconstruction difficulty. Extensive experiments demonstrate that our framework significantly outperforms state-of-the-art methods in segmentation performance across common datasets. Notably, our approach achieves performance parity with real data training while maintaining a condensation ratio of 2.4\% on Breakfast dataset.

View free PDFSource page

Related papers

arxivcs.CVcs.RO2026-07-10

Causally Debiased Latent Action Model for Embodied Action Conditioned World Models

Yufan Wei, Kun Zhou, Lingjun Mao, Zijun Zhang, Ziming Xu, Ziqiao Xi, et al.

Action-conditioned world models (ACWMs) aim to simulate future observations conditioned on embodied actions, offering a promising foundation for robot planning, policy evaluation, and data augmentation. However, learning controllable ACWMs requires large-scale action-labeled data…

View free PDFSource page
arxivcs.CV2026-07-22

Domain Shift in Echocardiography: Interpretable Quantification and Prediction of Cross-Dataset Left Ventricular Segmentation

Soroush Elyasi, Nasim Dadashi Serej, Julie Wall, Massoud Zolgharni

Cross-dataset generalisation remains a major barrier to clinical deployment of echocardiographic left ventricular segmentation, yet the sources of this shift are rarely disentangled. We examined whether transfer degradation could be estimated before deployment using handcrafted u…

View free PDFSource page
arxivcs.CV2026-07-11

CVKD-UDA: Cross-View Knowledge Distillation for 3D Unsupervised Domain Adaptive Segmentation

Zhimin Yuan, Ming Cheng, Shangshu Yu, Wen Li, Dunqiang Liu, Xin Huang, et al.

3D unsupervised domain adaptive (UDA) segmentation mitigates the high cost of manual annotations of the new domain data. Self-training has emerged as the dominant approach in this area, where its success heavily depends on a well-initialized warm-up model to generate reliable pse…

View free PDFSource page
arxivcs.CV2026-06-29

Unveiling Transferability in Trajectory Prediction via Latent Scene Embeddings

Theodor Westny, David Axelsson, Björn Olofsson, Erik Frisk

The growing availability of trajectory datasets has fueled major advances in data-driven motion prediction. Yet, models trained on one dataset often fail to generalize beyond their training domain as a result of differences in scene layouts, agent behaviors, and sensing condition…

View free PDFSource page
arxivcs.CV2026-06-29

3D Scene-Adaptive Trajectory-Controllable Human Image Animation with Camera Movement

Deyin Liu, Jicheng Xu, Lin Yuanbo Wu, Xiaowei Zhao, Xiatian Zhu, Zhe Jin, et al.

Human image animation, which aims to generate a video of a reference subject following a provided action sequence, has received increasing research interest. With the development of diffusion-based/flow-based video foundation models, existing animation works have began to upgrade…

View free PDFSource page