Related papers: ActionHub: A Large-scale Action Video Description …

Due to the lack of properly annotated medical data, exploring the generalization capability of the deep model is becoming a public concern. Zero-shot learning (ZSL) has emerged in recent years to equip the deep model with the ability to…

Zero-shot learning (ZSL) tackles the novel class recognition problem by transferring semantic knowledge from seen classes to unseen ones. Existing attention-based models have struggled to learn inferior region features in a single image by…

This paper introduces a video dataset of spatio-temporally localized Atomic Visual Actions (AVA). The AVA dataset densely annotates 80 atomic visual actions in 430 15-minute video clips, where actions are localized in space and time,…

Human Action Recognition (HAR) stands as a pivotal research domain in both computer vision and artificial intelligence, with RGB cameras dominating as the preferred tool for investigation and innovation in this field. However, in real-world…

Advancements in deep neural networks have contributed to near perfect results for many computer vision problems such as object recognition, face recognition and pose estimation. However, human action recognition is still far from…

Deep learning-based human activity recognition (HAR) methods have shown great promise in the applications of smart healthcare systems and wireless body sensor network (BSN). Despite their demonstrated performance in laboratory settings, the…

In this paper, we propose a study on multi-modal (audio and video) action spotting and classification in soccer videos. Action spotting and classification are the tasks that consist in finding the temporal anchors of events in a video and…

Trained on large datasets, deep learning (DL) can accurately classify videos into hundreds of diverse classes. However, video data is expensive to annotate. Zero-shot learning (ZSL) proposes one solution to this problem. ZSL trains a model…

Understanding crowd behavior in video is challenging for computer vision. There have been increasing attempts on modeling crowded scenes by introducing ever larger property ontologies (attributes) and annotating ever larger training…

We propose a novel approach for aerial video action recognition. Our method is designed for videos captured using UAVs and can run on edge or mobile devices. We present a learning-based approach that uses customized auto zoom to…

There are substantial instructional videos on the Internet, which enables us to acquire knowledge for completing various tasks. However, most existing datasets for instructional video analysis have the limitations in diversity and…

Zero-Shot Video Anomaly Detection (ZS-VAD) requires temporally localizing anomalies without target domain training data, which is a crucial task due to various practical concerns, e.g., data privacy or new surveillance deployments.…

Zero-shot temporal action localization (ZS-TAL) consists of classifying and localizing actions in untrimmed videos, where action classes are unseen at training time. Existing work uses Vision and Language Models (VLMs), taking advantage of…

Human Action Recognition (HAR), one of the most important tasks in computer vision, has developed rapidly in the past decade and has a wide range of applications in health monitoring, intelligent surveillance, virtual reality, human…

Realistic videos of human actions exhibit rich spatiotemporal structures at multiple levels of granularity: an action can always be decomposed into multiple finer-grained elements in both space and time. To capture this intuition, we…

Zero-shot Hashing (ZSH) is to learn hashing models for novel/target classes without training data, which is an important and challenging problem. Most existing ZSH approaches exploit transfer learning via an intermediate shared semantic…

This work presents an approach to category-based action recognition in video using sparse coding techniques. The proposed approach includes two main contributions: i) A new method to handle intra-class variations by decomposing each video…

Zero-shot skeleton-based action recognition (ZSSAR) is typically treated as a skeleton-text alignment problem: encode joint-coordinate sequences, align them with language, and classify unseen actions. We argue that this alignment is often…

Detecting actions in videos, particularly within cluttered scenes, poses significant challenges due to the limitations of 2D frame analysis from a camera perspective. Unlike human vision, which benefits from 3D understanding, recognizing…

Zero-shot learning (ZSL) aims to transfer knowledge from seen classes to semantically related unseen classes, which are absent during training. The promising strategies for ZSL are to synthesize visual features of unseen classes conditioned…