-
AViD Dataset: Anonymized Videos from Diverse Countries
AViD is a new public video dataset for action recognition, containing action videos from diverse countries. -
Generative Action-description Prompts for Skeleton-based Action Recognition
Skeleton-based action recognition has recently received considerable attention. Current approaches to skeleton-based action recognition are typically formulated as one-hot... -
FaMoS dataset
The FaMoS dataset records 95 subjects, each performing 28 predefined actions (e.g. anger, disgust, fear, surprise). -
N-EPIC Kitchens
Recognizing and comprehending human actions and gestures is a crucial perception requirement for robots to interact with humans and carry out tasks in diverse domains, including... -
THUMOS'13 Dataset
The THUMOS'13 dataset contains 24 classes and 3,207 videos. -
JHMDB Dataset
The JHMDB dataset contains a varying number of actions (21 in JHMDB) across different domains (sports and daily activities). -
UCF Sports Dataset
The UCF Sports dataset contains a varying number of actions (10 in UCF Sports, 21 in JHMDB, and 24 in THUMOS’13) across different domains (sports and daily activities). -
Kinetics Skeleton 400
Kinetics Skeleton 400 is a dataset adapted from the Kinetics 400 video dataset using the OpenPose toolbox in 2D keypoint modality. -
THUMOS'14, ActivityNet v1.3
Temporal action detection in untrimmed videos via multi-stage cnns, Cdc: convolutional-de-convolutional networks for precise temporal action localization, Temporal action... -
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
The dataset used in the paper is a collection of videos and corresponding referring expressions. -
MPII Human Pose Dataset
Human pose estimation refers to the task of recognizing postures by localizing body keypoints (head, shoulders, elbows, wrists, knees, ankles, etc.) from images. -
EPIC-KITCHENS
EPIC-KITCHENS is a large-scale egocentric video benchmark recorded by 32 participants in their native kitchen environments. Our videos depict non-scripted daily activities: we... -
UCF Sports
UCF Sports dataset consists of 150 videos from sport broadcasts covering 10 action categories. -
SCUBA and SCUFO
The dataset used in the paper to evaluate static bias in action representations. -
Action Recognition with Kernel-based Graph Convolutional Networks
Learning graph convolutional networks (GCNs) is an emerging field which aims at generalizing deep learning to arbitrary non-regular domains.
