CORTEXA
← Browse
arxivcs.CV2026-07-01

OnPoint: Offline-to-Online Multi-Level Distillation for Point-Supervised Online Temporal Action Localization

Sakib Reza, Gauri Jagatap, Mohsen Moghaddam, Octavia Camps, Andrea Fanelli

Temporal Action Localization (TAL) typically relies on segment annotations or offline access to full videos, limiting scalability and online use. We introduce Point-Supervised Online TAL (POTAL), which localizes actions in streaming videos using only one temporal point per instance. To solve POTAL, we propose OnPoint, an offline-to-online multi-level distillation framework that transfers knowledge from a point-supervised offline teacher to an online student via (i) pseudo-segment instance distillation, (ii) class-activation sequence distillation, and (iii) anticipatory window-level distillation. We further improve robustness by incorporating the original point labels into student training and by refining anchor decoding with actionness-guided attention calibration. Experiments on five datasets show OnPoint consistently outperforms strong baselines, establishing a solid foundation for POTAL.

View free PDFSource page

Related papers

arxivcs.CV2026-07-06

TubeLite: Lightweight Multi-Actor Spatio-Temporal Action Detection

Ali Soltaninezhad, Melissa Cote, Alejandro Rico Espinosa, Tunai Porto Marques, Alexandra Branzan Albu

Spatio-temporal action detection in videos requires jointly localizing actors in space and identifying action boundaries over time. A common challenge is constructing temporally stable action tubes, as frame-level detectors often suffer from jitter, fragmentation, and imprecise t…

View free PDFSource page
arxivcs.CV2026-07-02

SFKD: Spatial--Frequency Joint-Aware Heterogeneous Knowledge Distillation via Multi-Level Wavelet Spectral Interaction

Cuipeng Wang, Haipeng Wang

Most existing knowledge distillation methods focus on homogeneous models (e.g., CNN-to-CNN), thereby overlooking the flexibility and potential of knowledge transfer across heterogeneous models. Due to intrinsic inductive bias discrepancies between heterogeneous models that cause…

View free PDFSource page
arxivcs.CV2026-06-29

Clinical Risk-Aware Multi-Level Grading for Coronary Artery Stenosis through Curved Feature Reconstruction

Shishuang Zhao, Hongtai Li, Junjie Hou, Yuhang Liu

Developing a multi-level grading model for coronary artery stenosis holds great clinical significance for the diagnosis of coronary artery disease. However, designing an effective multi-level deep learning algorithm faces significant challenges. Specifically, utilizing CCTA or 3D…

View free PDFSource page
arxivcs.CV2026-07-08

Unraveling Machine Behavior by Multi-Level Bias Analysis and Detection: Methodology and Application to Computer Vision

Ignacio Serna, Aythami Morales, Julian Fierrez

This study investigates the presence and propagation of bias within Neural Networks through a comprehensive multi-level analysis spanning the learned latent space, layer activations, and the network's parameters. Based on this taxonomy, we propose three bias detection approaches:…

View free PDFSource page
arxivcs.CVcs.ROeess.IV2026-06-29

PS-MOT: Cultivating Instance Awareness from Point Seeds for Multi-Object Tracking

Kai Luo, Fei Teng, Mengfei Duan, Wanjun Jia, Xu Wang, Hao Shi, et al.

We introduce Point-supervised Multi-Object Tracking (PS-MOT) as a cost-effective alternative to traditional bounding box supervision, shifting the focus from spatial fitting to topological center-driven representation. However, PS-MOT faces challenges, e.g., spatial ambiguity and…

View free PDFSource page