paper-with-me

Papers

Weakly-guided Self-supervised Pretraining for Temporal Activity Detection

2021-11-26 · Kumara Kahatapitiya, Zhou Ren, Haoxiang Li, Zhenyu Wu, Michael S. Ryoo, Gang Hua

Temporal Activity Detection aims to predict activity classes per frame, in contrast to video-level predictions in Activity Classification (i.e., Activity Recognition). Due to the expensive frame-level annotations required for detection, the scale of detection datasets is limited. Thus, commonly, previous work on temporal activity detection resorts to fine-tuning a classification model pretrained on large-scale classification datasets (e.g., Kinetics-400). However, such pretrained models are not ideal for downstream detection, due to the disparity between the pretraining and the downstream fine-tuning tasks. In this work, we propose a novel 'weakly-guided self-supervised' pretraining method for detection. We leverage weak labels (classification) to introduce a self-supervised pretext task (detection) by generating frame-level pseudo labels, multi-action frames, and action segments. Simply put, we design a detection task similar to downstream, on large-scale classification data, without extra annotations. We show that the models pretrained with the proposed weakly-guided self-supervised detection task outperform prior work on multiple challenging activity detection benchmarks, including Charades and MultiTHUMOS. Our extensive ablations further provide insights on when and how to use the proposed models for activity detection. Code is available at https://github.com/kkahatapitiya/SSDet.

📄 PDF Abstract BibTeX arXiv:2111.13675

Code (1)

kkahatapitiya/SSDet 공식 구현 pytorch

Tasks

Action DetectionActivity DetectionActivity RecognitionClassification

Similar Papers 제목 키워드 기반

Weakly Supervised Temporal Sentence Grounding With Uncertainty-Guided Self-Training

2023-01-01 · CVPR 2023 1 · Yifei HUANG, Lijin Yang, Yoichi Sato

The task of weakly supervised temporal sentence grounding aims at finding the corresponding temporal moments of a language description in the video, given video-language correspondence only at video-level. Most exist…

Data AugmentationSentenceTemporal Sentence GroundingWeakly-supervised Learning

Learning to diagnose cirrhosis from radiological and histological labels with joint self and weakly-supervised pretraining strategies

2023-02-16 · Emma Sarfati, Alexandre Bone, Marc-Michel Rohe, Pietro Gori 외

Identifying cirrhosis is key to correctly assess the health of the liver. However, the gold standard diagnosis of the cirrhosis needs a medical intervention to obtain the histological confirmation, e.g. the METAVIR score…

Transfer Learning

Skeleton-based Zero-Shot Spatio-Temporal Action Localization via Weakly-Supervised Pretraining

2026-08-26 · Koshiro Nagano, Fumiaki Sato, Ryo Hachiuma, Kazuki Tsutsukawa 외 arxiv

We propose a novel pretraining strategy for skeleton-based zero-shot spatio-temporal action localization to estimate unseen actions for person instances while overcoming high annotation costs for training via new target …

Spatio-Temporal Action LocalizationContrastive Learning

Multi-pretraining for Large-scale Text Classification

2020-11-01 · Findings of the Association for Computational Linguistics 2020 · Kang-Min Kim, Bumsu Hyeon, Yeachan Kim, Jun-Hyung Park 외

Deep neural network-based pretraining methods have achieved impressive results in many natural language processing tasks including text classification. However, their applicability to large-scale text classification with…

Classificationtext-classificationText Classification

`Attention-Guided Cross-Temporal Clustering for Self-Supervised Video Object Segmentation

2026-07-08 · Waqas Arshid, Mohammad Awrangjeb, Alan Wee-Chung Liew, Yongsheng Gao arxiv

Video object segmentation (VOS) is a fundamental task in video understanding, requiring accurate delineation and consistent tracking of objects across frames. While supervised methods achieve strong performance, they rel…

Video Object SegmentationSelf-Supervised Learning