paper-with-me

Papers

Uncertainty-Aware Weakly Supervised Action Detection from Untrimmed Videos

2020-07-21 · ECCV 2020 8 · Anurag Arnab, Chen Sun, Arsha Nagrani, Cordelia Schmid

Despite the recent advances in video classification, progress in spatio-temporal action recognition has lagged behind. A major contributing factor has been the prohibitive cost of annotating videos frame-by-frame. In this paper, we present a spatio-temporal action recognition model that is trained with only video-level labels, which are significantly easier to annotate. Our method leverages per-frame person detectors which have been trained on large image datasets within a Multiple Instance Learning framework. We show how we can apply our method in cases where the standard Multiple Instance Learning assumption, that each bag contains at least one instance with the specified label, is invalid using a novel probabilistic variant of MIL where we estimate the uncertainty of each prediction. Furthermore, we report the first weakly-supervised results on the AVA dataset and state-of-the-art results among weakly-supervised methods on UCF101-24.

📄 PDF Abstract BibTeX arXiv:2007.10703

Code (0)

등록된 구현이 없습니다.

Tasks

Action DetectionAction RecognitionMultiple Instance LearningSpatio-temporal Action RecognitionVideo Classification

Similar Papers 제목 키워드 기반

Uncertainty Guided Collaborative Training for Weakly Supervised Temporal Action Detection

2021-06-19 · CVPR 2021 1 · Wenfei Yang, Tianzhu Zhang, Xiaoyuan Yu, Tian Qi 외

Weakly supervised temporal action detection aims to localize temporal boundaries of actions and identify their categories simultaneously with only video-level category labels during training. Among existing methods, …

Action DetectionPseudo Label

Towards Open Set Video Anomaly Detection

2022-08-23 · Yuansheng Zhu, Wentao Bao, Qi Yu

Open Set Video Anomaly Detection (OpenVAD) aims to identify abnormal events from video data where both known anomalies and novel ones exist in testing. Unsupervised models learned solely from normal videos are applicable…

Anomaly DetectionMultiple Instance LearningTripletVideo Anomaly Detection

Weakly Supervised Monocular 3D Detection with a Single-View Image

2024-02-29 · CVPR 2024 1 · Xueying Jiang, Sheng Jin, Lewei Lu, Xiaoqin Zhang 외

Monocular 3D detection (M3D) aims for precise 3D object localization from a single-view image which usually involves labor-intensive annotation of 3D detection boxes. Weakly supervised M3D has recently been studied to ob…

Knowledge DistillationObject LocalizationSelf-Knowledge DistillationTransfer Learning

Uncertainty-Aware Extreme Point Tracing for Weakly Supervised Ultrasound Image Segmentation

2025-10-17 · Lei Shi, Gang Li, Junxing Zhang arxiv

Automatic medical image segmentation is a fundamental step in computer-aided diagnosis, yet fully supervised approaches demand extensive pixel-level annotations that are costly and time-consuming. To alleviate this burde…

Medical Image Segmentation

An Uncertainty-Aware Encoder for Aspect Detection

2021-11-01 · Findings (EMNLP) 2021 11 · Thi-Nhung Nguyen, Kiem-Hieu Nguyen, Young-In Song, Tuan-Dung Cao

Aspect detection is a fundamental task in opinion mining. Previous works use seed words either as priors of topic models, as anchors to guide the learning of aspects, or as features of aspect classifiers. This paper pres…

Opinion MiningTopic Models