Related papers: Spatio-Temporal Action Localization in a Weakly Su…

In this paper, we show that recent advances in video representation learning and pre-trained vision-language models allow for substantial improvements in self-supervised video object localization. We propose a method that first localizes…

Temporal action localization aims to identify the boundaries and categories of actions in videos, such as scoring a goal in a football match. Single-frame supervision has emerged as a labor-efficient way to train action localizers as it…

This paper addresses the problem of automatically localizing dominant objects as spatio-temporal tubes in a noisy collection of videos with minimal or even no supervision. We formulate the problem as a combination of two complementary…

We propose a novel model for temporal detection and localization which allows the training of deep neural networks using only counts of event occurrences as training labels. This powerful weakly-supervised framework alleviates the burden of…

Spatio-temporal action detection in videos requires localizing the action both spatially and temporally in the form of an "action tube". Nowadays, most spatio-temporal action detection datasets (e.g. UCF101-24, AVA, DALY) are annotated with…

Weakly supervised temporal action localization (WTAL) aims to detect action instances in untrimmed videos using only video-level annotations. Since many existing works optimize WTAL models based on action classification labels, they…

Cell detection is the task of detecting the approximate positions of cell centroids from microscopy images. Recently, convolutional neural network-based approaches have achieved promising performance. However, these methods require a…

Labeled data is a critical resource for training and evaluating machine learning models. However, many real-life datasets are only partially labeled. We propose a semi-supervised machine learning training strategy to improve event detection…

We introduce the task of weakly supervised learning for detecting human and object interactions in videos. Our task poses unique challenges as a system does not know what types of human-object interactions are present in a video or the…

We address the problem of video representation learning without human-annotated labels. While previous efforts address the problem by designing novel self-supervised tasks using video data, the learned features are merely on a…

Sequential video understanding, as an emerging video understanding task, has driven lots of researchers' attention because of its goal-oriented nature. This paper studies weakly supervised sequential video understanding where the accurate…

Recently, Weakly-supervised Temporal Action Localization (WTAL) has been densely studied but there is still a large gap between weakly-supervised models and fully-supervised models. It is practical and intuitive to annotate temporal…

Deep neural networks are efficient learning machines which leverage upon a large amount of manually labeled data for learning discriminative features. However, acquiring substantial amount of supervised data, especially for videos can be a…

For robotic surgical videos, instrument presence annotations are typically recorded with video streams, which offering the potential to reduce the manually annotated costs for segmentation. However, weakly supervised surgical instrument…

In industrial settings, weakly supervised (WS) methods are usually preferred over their fully supervised (FS) counterparts as they do not require costly manual annotations. Unfortunately, the segmentation masks obtained in the WS regime are…

Unsupervised domain adaptation (UDA) has been a potent technique to handle the lack of annotations in the target domain, particularly in semantic segmentation task. This study introduces a different UDA scenarios where the target domain…

The recent success in human action recognition with deep learning methods mostly adopt the supervised learning paradigm, which requires significant amount of manually labeled data to achieve good performance. However, label collection is an…

In semantic segmentation, the creation of pixel-level labels for training data incurs significant costs. To address this problem, semi-supervised learning, which utilizes a small number of labeled images alongside unlabeled images to…

Audio-Visual Video Parsing is a task to predict the events that occur in video segments for each modality. It often performs in a weakly supervised manner, where only video event labels are provided, i.e., the modalities and the timestamps…

Existing temporal action localization (TAL) works rely on a large number of training videos with exhaustive segment-level annotation, preventing them from scaling to new classes. As a solution to this problem, few-shot TAL (FS-TAL) aims to…