Related papers: FinePseudo: Improving Pseudo-Labelling through Tem…

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…

In this work, we focus on semi-supervised learning for video action detection. Video action detection requires spatiotemporal localization in addition to classification, and a limited amount of labels makes the model prone to unreliable…

Action recognition from videos, i.e., classifying a video into one of the pre-defined action types, has been a popular topic in the communities of artificial intelligence, multimedia, and signal processing. However, existing methods usually…

We address the problem of fine-grained action localization from temporally untrimmed web videos. We assume that only weak video-level annotations are available for training. The goal is to use these weak labels to identify temporal segments…

Our objective in this work is fine-grained classification of actions in untrimmed videos, where the actions may be temporally extended or may span only a few frames of the video. We cast this into a query-response mechanism, where each…

Self-driving vehicles must perceive and predict the future positions of nearby actors in order to avoid collisions and drive safely. A learned deep learning module is often responsible for this task, requiring large-scale, high-quality…

Alleviating noisy pseudo labels remains a key challenge in Semi-Supervised Temporal Action Localization (SS-TAL). Existing methods often filter pseudo labels based on strict conditions, but they typically assess classification and…

Contrastively pretrained audio-language models (e.g., CLAP) excel at clip-level understanding but struggle with frame-level tasks. Existing extensions fail to exploit the varying granularity of real-world audio-text data, where massive…

Temporal action localization is an important step towards video understanding. Most current action localization methods depend on untrimmed videos with full temporal annotations of action instances. However, it is expensive and…

While the widely available embedded sensors in smartphones and other wearable devices make it easier to obtain data of human activities, recognizing different types of human activities from sensor-based data remains a difficult research…

Despite great progress in supervised semantic segmentation,a large performance drop is usually observed when deploying the model in the wild. Domain adaptation methods tackle the issue by aligning the source domain and the target domain.…

Training deep learning models on in-home IoT sensory data is commonly used to recognise human activities. Recently, federated learning systems that use edge devices as clients to support local human activity recognition have emerged as a…

Multi-Modal Self-Supervised Learning from videos has been shown to improve model's performance on various downstream tasks. However, such Self-Supervised pre-training requires large batch sizes and a large amount of computation resources…

Temporal Action Localization (TAL) aims to predict both action category and temporal boundary of action instances in untrimmed videos, i.e., start and end time. Fully-supervised solutions are usually adopted in most existing works, and…

Extracting discriminative features plays a crucial role in the fine-grained visual classification task. Most of the existing methods focus on developing attention or augmentation mechanisms to achieve this goal. However, addressing the…

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…

Pseudo-label learning methods have been widely applied in weakly-supervised temporal action localization. Existing works directly utilize weakly-supervised base model to generate instance-level pseudo-labels for training the…

Action segmentation of behavioral videos is the process of labeling each frame as belonging to one or more discrete classes, and is a crucial component of many studies that investigate animal behavior. A wide range of algorithms exist to…

Semi-supervised semantic segmentation aims to utilize limited labeled images and abundant unlabeled images to achieve label-efficient learning, wherein the weak-to-strong consistency regularization framework, popularized by FixMatch, is…

Federated Semi-Supervised Learning (FSSL) aims to leverage unlabeled data across clients with limited labeled data to train a global model with strong generalization ability. Most FSSL methods rely on consistency regularization with…