-
PURE dataset
The dataset used in this paper is a collection of 28 industrial requirements documents covering diverse application domains. -
UBFC dataset
The dataset used for testing the proposed model for video-based cardiac measurement. -
AFRL dataset
The dataset used for training and testing the proposed model for video-based cardiac measurement. -
Unstructured Social Activity Attribute (USAA)
A video dataset of 69 instance-level attributes for 8 classes of complex social group activity videos. -
MoSeg: A Dataset for Object Segmentation in Videos
MoSeg is a dataset for object segmentation in videos. -
Causal-VidQA
This dataset is used in the paper to evaluate the performance of the TranSTR architecture. -
UCSD Pedestrian
The dataset used for local anomaly detection in videos using object-centric adversarial learning. -
ActivityNet-QA
Video question answering (VideoQA) is an essential task in vision-language understanding, which has attracted numerous research attention recently. Nevertheless, existing works... -
Kinetics: A Large-Scale Video Benchmark for Human Action Recognition
A large-scale video benchmark for human action recognition. -
Video-Specific Query-Key Attention Modeling for Weakly-Supervised Temporal Ac...
Weakly-supervised temporal action localization aims to identify and localize the action instances in the untrimmed videos with only video-level action labels. -
Star: A Benchmark for Situated Reasoning in Real-World Videos
The STAR dataset provides 60K situated reasoning questions based on 22K trimmed situation video clips. -
Agqa: A Benchmark for Compositional Spatio-Temporal Reasoning
The AGQA benchmark is a visual dataset comprising 192M hand-crafted questions about 9.6K videos from the Charades dataset. -
Learning to Predict Situation Hyper-Graphs for Video Question Answering
The SHG-VQA model predicts a situation hyper-graph structure composed of existing actions and relations in the input video. -
KnowIT VQA
A video story question answering dataset containing 24,282 questions about 207 episodes of The Big Bang Theory. -
YouTube Clickbait Detection Dataset
The dataset is a collection of online videos from YouTube, with comments and metadata. It is used to evaluate the performance of the Online Video Clickbait Protector (OVCP) scheme. -
Pulse Labs AI Dataset
The dataset used for this investigation comes from a set of usability studies conducted by Pulse Labs AI. The dataset contains 209, 183, and 214 instances of names, phone... -
Action Search: Spotting Actions in Videos
This paper proposes a method for action search in videos, which is used for spotting actions in videos. -
Olympic Sports dataset
The Olympic Sports dataset consists of video sequences of athletes practicing 16 different sports. The dataset contains an overall number of 113,516 frames, covering a rich set... -
Subway Exit
The Subway Exit dataset contains video clips of people leaving a train station. -
Subway Entrance
The Subway Entrance dataset contains video clips of people waiting to board a train.
