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.CV2026-07-23

Webly Supervised Multi-Label Recognition: Evaluation Benchmark and Dual-Branch Multi-Label Contrastive Learning

Zhihua Xu, Zhijing Yang, Yufeng Yang, Tianshui Chen

Training deep learning models with freely available web images can reduce their dependence on costly manual annotations. Although webly supervised learning has been widely studied for single-label recognition, its multi-label counterpart remains underexplored, partly due to the l…

View free PDFSource page
arxivcs.CV2026-07-22

Robust Activation Map Rectification for Weakly Supervised Volumetric Segmentation: Temporal Coherence as a Free Lunch

Renshu Gu, Jialiang Chen, Fei Gao, Hang Su, Jun Qi, Jiamin Xu, et al.

Weakly supervised segmentation relies heavily on class activation maps (CAMs) to initially localize target regions. However, CAMs are often noisy and prone to catastrophic failures. Existing remedies typically introduce additional training stages or prototype learning, increasing…

View free PDFSource page
arxivcs.ROcs.CV2026-07-31

FibVLA: An Efficient Temporal Vision-Language-Action Model with Fibonacci Sampling

Li Lin, Wujun Xu, Weiwei Meng, Kaiwen Xia, Kang Hao Cheong, Shuai Wang

Vision-language-action models (VLAs), which leverage the cognition of multimodal information to infer physical-world actions, provide a generalized solution for embodied AI applications. Conventional VLAs usually concentrate on current digital cognition. While some efforts are ma…

View free PDFSource page
arxivcs.CV2026-07-31

Multi-Modal Object Re-Identification with Dual Semantic Guidance and Global-Local Mutual Modulation

Weixiang Zhou, Xingguo Xu, Yuhao Wang, Cong Wang, Yang Yang, Zhixun Su, et al.

Multi-modal object Re-Identification (ReID) aims to retrieve target instances by leveraging complementary information across modalities. However, existing methods suffer from two challenges. First, they often fail to exploit well-aligned and reliable semantic priors, making them…

View free PDFSource page
arxivcs.CVcs.AI2026-07-23

SCALE: Self-Supervised Constraint-Aware Layout GEneration for Local P&R DRV Fixing at Advanced Nodes

Chia-Tung Ho, Haoyu Yang, Guanglei Zhou, Yoshi Nishi, Yaguang Li, Walker Turner, et al.

As semiconductor manufacturing advances toward sub-2nm nodes, local place-and-route (P&R) design-rule violation (DRV) fixing is increasingly limited by complex rule interactions, dense multi-layer routing geometries, and foundry-specific constraints. While Large Language Models (…

View free PDFSource page