Related papers: Leveraging Action Affinity and Continuity for Semi…

In this paper, we present a novel cross-consistency based semi-supervised approach for semantic segmentation. Consistency training has proven to be a powerful semi-supervised learning framework for leveraging unlabeled data under the…

In this paper we address the problem of automatically discovering atomic actions in unsupervised manner from instructional videos. Instructional videos contain complex activities and are a rich source of information for intelligent agents,…

Recognizing actions from a limited set of labeled videos remains a challenge as annotating visual data is not only tedious but also can be expensive due to classified nature. Moreover, handling spatio-temporal data using deep $3$D…

This paper addresses a new problem of weakly-supervised online action segmentation in instructional videos. We present a framework to segment streaming videos online at test time using Dynamic Programming and show its advantages over greedy…

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…

With video-level labels, weakly supervised temporal action localization (WTAL) applies a localization-by-classification paradigm to detect and classify the action in untrimmed videos. Due to the characteristic of classification,…

In this paper, we investigate the usage of autoencoders in modeling textual data. Traditional autoencoders suffer from at least two aspects: scalability with the high dimensionality of vocabulary size and dealing with task-irrelevant words.…

Semantic segmentation is a challenging task in the absence of densely labelled data. Only relying on class activation maps (CAM) with image-level labels provides deficient segmentation supervision. Prior works thus consider pre-trained…

Human action understanding is crucial for the advancement of multimodal systems. While recent developments, driven by powerful large language models (LLMs), aim to be general enough to cover a wide range of categories, they often overlook…

We propose a novel semi-supervised image segmentation method that simultaneously optimizes a supervised segmentation and an unsupervised reconstruction objectives. The reconstruction objective uses an attention mechanism that separates the…

In video surveillance, person re-identification is the task of searching person images in non-overlapping cameras. Though supervised methods for person re-identification have attained impressive performance, obtaining large scale cross-view…

Semi-supervised learning addresses the issue of limited annotations in medical images effectively, but its performance is often inadequate for complex backgrounds and challenging tasks. Multi-modal fusion methods can significantly improve…

The goal of this paper is to self-train a 3D convolutional neural network on an unlabeled video collection for deployment on small-scale video collections. As smaller video datasets benefit more from motion than appearance, we strive to…

Most activity localization methods in the literature suffer from the burden of frame-wise annotation requirement. Learning from weak labels may be a potential solution towards reducing such manual labeling effort. Recent years have…

We apply a generative segmental model of task structure, guided by narration, to action segmentation in video. We focus on unsupervised and weakly-supervised settings where no action labels are known during training. Despite its simplicity,…

Recognising actions in videos relies on labelled supervision during training, typically the start and end times of each action instance. This supervision is not only subjective, but also expensive to acquire. Weak video-level supervision…

Weakly supervised temporal action localization is a challenging task as only the video-level annotation is available during the training process. To address this problem, we propose a two-stage approach to fully exploit multi-resolution…

Temporal segmentation of long videos is an important problem, that has largely been tackled through supervised learning, often requiring large amounts of annotated training data. In this paper, we tackle the problem of self-supervised…

Medical data often exhibits long-tail distributions with heavy class imbalance, which naturally leads to difficulty in classifying the minority classes (i.e., boundary regions or rare objects). Recent work has significantly improved…

Weakly supervised temporal action localization aims at learning the instance-level action pattern from the video-level labels, where a significant challenge is action-context confusion. To overcome this challenge, one recent work builds an…