arXiv Computer Vision
Video-STLayout Pre-training
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Aug 25
Semantic Slots for Video Object-Centric Learning
Semantic Slots for Video Object-Centric Learning proposes a Transformer-based decoder that frees slots from spatial anchoring, enabling them to act as semantic queries invariant to object position. This design removes the need for complex temporal predictors, allowing a single-frame slot to decompose subsequent video frames. On YouTube-VIS, the method outperforms prior approaches, improving mBO by 31 points over VideoSAUR and achieving state-of-the-art results with 86.6% ARI and 62.8% mBO.
arXiv Computer Vision
Aug 27
Skeleton-based Zero-Shot Spatio-Temporal Action Localization via Weakly-Supervised Pretraining
The paper introduces Skeleton-Language feature Pooling Switching, a weakly‑supervised vision‑language pretraining strategy for skeleton‑based zero‑shot spatio‑temporal action localization. It replaces video‑level pooling with instance‑level feature computation during inference, enabling the model to estimate unseen actions without costly annotations. Additionally, Scene‑Mixed Discriminative Contrastive Learning is proposed to separate actions at the instance level within mixed scenes using a MIL framework, and experiments on four public datasets confirm the method’s effectiveness.
arXiv AI
Sep 1
PRISM: Predictive Recomposition via Semantic Latent Decomposition for View-invariant Video Representation Learning
arXiv:2608.30388v1 Announce Type: cross Abstract: Cross-view video representation learning aims to capture viewpoint-invariant action semantics despite substantial appearance changes across egocentri...
Hugging Face Trending Papers
Jun 11
OR-Action: Multi-Role Video Understanding with Fine-Grained Actions
Fine-grained understanding of operating room (OR) activity could enable workflow-aware assistance, yet remains difficult due to clutter, occlusions, and limited sensing. The prevailing approach to model this environment is scene graphs as an interpretable representation of OR interactions.
Hugging Face Trending Papers
Oct 8
SV-TAD: Native Sparse Convs for Efficient Temporal Action Detection
SV‑TAD introduces native sparse 2D convolutions to enable convolutional adapters to operate directly on dynamically pruned token sets, addressing the inefficiency of existing adapters that do not reduce inference‑time computation. By integrating this primitive, SV‑TAD cuts VideoMAEv2‑L computation by up to 64% and achieves 2.2× faster inference while preserving state‑of‑the‑art accuracy on THUMOS‑14 and ActivityNet‑1.3. When applied to InternVideoNext‑L, the approach surpasses prior state‑of‑the‑art performance at roughly half the computational cost and also supports auxiliary task tokens, improving fine‑grained assembly detection on ATTACH.
arXiv Machine Learning
Aug 4
DeepConvContext: A Multi-Scale Approach to Timeseries Classification in Human Activity Recognition
arXiv:2505. 20894v2 Announce Type: replace Abstract: Despite recognized limitations in modeling long-range temporal dependencies, Human Activity Recognition (HAR) has traditionally relied on a sliding window approach to segment labeled datasets.