Related papers: Open Set Action Recognition via Multi-Label Eviden…
This paper presents the first-rank solution for the Multi-Modal Action Recognition Challenge, part of the Multi-Modal Visual Pattern Recognition Workshop at the \acl{ICPR} 2024. The competition aimed to recognize human actions using a…
Recognizing human activities in videos is challenging due to the spatio-temporal complexity and context-dependence of human interactions. Prior studies often rely on single input modalities, such as RGB or skeletal data, limiting their…
In classic video action recognition, labels may not contain enough information about the diverse video appearance and dynamics, thus, existing models that are trained under the standard supervised learning paradigm may extract less…
Active learning has emerged as a promising approach to reduce the substantial annotation burden in 3D object detection tasks, spurring several initiatives in outdoor environments. However, its application in indoor environments remains…
Temporal action localization (TAL), which involves recognizing and locating action instances, is a challenging task in video understanding. Most existing approaches directly predict action classes and regress offsets to boundaries, while…
Despite the success of deep neural networks on facial action unit (AU) detection, better performance depends on a large number of training images with accurate AU annotations. However, labeling AU is time-consuming, expensive, and…
The construction of models for video action classification progresses rapidly. However, the performance of those models can still be easily improved by ensembling with the same models trained on different modalities (e.g. Optical flow).…
Owing to its rapid progress and broad application prospects, few-shot action recognition has attracted considerable interest. However, current methods are predominantly based on limited single-modal data, which does not fully exploit the…
Most dense recognition approaches bring a separate decision in each particular pixel. These approaches deliver competitive performance in usual closed-set setups. However, important applications in the wild typically require strong…
The demands on visual recognition systems do not end with the complexity offered by current large-scale image datasets, such as ImageNet. In consequence, we need curious and continuously learning algorithms that actively acquire knowledge…
Open-set action recognition is to reject unknown human action cases which are out of the distribution of the training set. Existing methods mainly focus on learning better uncertainty scores but dismiss the importance of feature…
The efficacy of deep learning depends on large-scale data sets that have been carefully curated with reliable data acquisition and annotation processes. However, acquiring such large-scale data sets with precise annotations is very…
This paper focuses on the weakly-supervised audio-visual video parsing task, which aims to recognize all events belonging to each modality and localize their temporal boundaries. This task is challenging because only overall labels…
This paper studies the joint learning of action recognition and temporal localization in long, untrimmed videos. We employ a multi-task learning framework that performs the three highly related steps of action proposal, action recognition,…
Human action recognition plays a critical role in healthcare and medicine, supporting applications such as patient behavior monitoring, fall detection, surgical robot supervision, and procedural skill assessment. While traditional models…
Deep networks have produced significant gains for various visual recognition problems, leading to high impact academic and commercial applications. Recent work in deep networks highlighted that it is easy to generate images that humans…
Graph anomaly detection faces significant challenges due to the scarcity of reliable anomaly-labeled datasets, driving the development of unsupervised methods. Graph autoencoders (GAEs) have emerged as a dominant approach by reconstructing…
Vision-language models (VLMs) are capable of recognizing unseen actions. However, existing VLMs lack intrinsic understanding of procedural action concepts. Hence, they overfit to fixed labels and are not invariant to unseen action synonyms.…
We propose ViewAL, a novel active learning strategy for semantic segmentation that exploits viewpoint consistency in multi-view datasets. Our core idea is that inconsistencies in model predictions across viewpoints provide a very reliable…
Open-vocabulary video visual relationship detection aims to detect objects and their relationships in videos without being restricted by predefined object or relationship categories. Existing methods leverage the rich semantic knowledge of…