arXiv Computer Vision
CoDy: Codec Dynamics as Complementary Priors for Unsupervised Temporal Action Localization
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv AI
Sep 7
What Moves? Localized Motion Representations for Compositional Scene Control
The paper introduces a promptable localized motion representation that generates persistent embeddings for user-specified regions in a video, without cropping or masking the input. By conditioning motion encoding directly on spatial masks while processing the full video, the method produces temporally consistent, region-addressable embeddings that capture local dynamics while preserving global context. These embeddings enable object-level motion transfer for dynamic scene composition and improve localized action classification in multi-actor videos, outperforming global representations that rely on cropping or post-hoc masking.
arXiv Computer Vision
Sep 1
MASQ: Mask-Aware Spatiotemporal Quantization for Unsupervised Skeleton Action Segmentation
arXiv:2608.29891v1 Announce Type: new Abstract: Unsupervised skeleton-based temporal action segmentation is a crucial task for understanding human behavior in long untrimmed sequences. Recent approac...
Hugging Face Trending Papers
Jul 14
FlowWAM: Optical Flow as a Unified Action Representation for World Action Models
World Action Models (WAMs) are able to leverage pretrained video generators for both world modeling and action prediction. However, directly leveraging such video generators for control raises a new challenge: how to represent actions in a suitable form that aligns with pretrained video generators while carrying enough motion cues for accurate control.
arXiv Computer Vision
3d ago
Learning High-Quality Pseudo-Labels for Point-Supervised Temporal Action Localization
arXiv:2610.35516v1 Announce Type: new Abstract: Point-supervised temporal action localization (PTAL) aims to recognize and localize action instances in untrimmed videos using only point-level annotat...
arXiv Computer Vision
Oct 21
CodecMotion-OAD: Efficient Online Action Detection with Compressed-Domain Motion
arXiv:2610.26915v1 Announce Type: new Abstract: Online action detection (OAD) identifies ongoing actions in streaming videos. Many existing OAD systems combine RGB appearance with optical flow, but d...
arXiv Computer Vision
Oct 5
Native Action-Prior Learning from Videos for World Action Models
The paper introduces NAVA-WAM, a method that learns action priors directly from observation-only videos to pretrain action policies for robots. It uses a two-stage training process: first, it pretrains on videos with future‑video flow‑matching supervision to learn action‑relevant priors, and second, it fine‑tunes with action‑labeled demonstrations for robot control. Experiments show that NAVA‑WAM outperforms previous methods in both in‑distribution and out‑of‑distribution scenarios, achieving strong action‑label efficiency and real‑robot generalization.