Video Analysis - Groups

DFDC Preview

A dataset for deepfake detection challenge.

Dataset
JSON

Mesonet

A compact facial video forgery detection network for detecting manipulated faces in videos.

Dataset
JSON

Day-to-Day Video Dataset

A dataset of 30 videos of length 3 minutes to 20 minutes from five classes of daily activities: socializing, home repair, biking around urban areas, cooking, and home tours.

Dataset
JSON

ShareChat Video Posts Dataset

Dataset of video posts created in the Hindi language over a period of one week on the ShareChat application, capturing both implicit signals (such as video play, and skip) and...

Dataset
JSON

ActivityNet1.2

The ActivityNet1.2 dataset is a large-scale benchmark for action recognition and localization in videos.

Dataset
JSON

SoundNet

The dataset is used for learning general and effective models for both audio and video analysis from self-supervised temporal synchronization.

Dataset
JSON

Sherlock

The Sherlock dataset contains 103K images collected from the Visual Genome and Visual Common Sense Reasoning datasets. These images are split into 90K training, 6.6K validation,...

Dataset
JSON

Temporal Sentence Grounding in Videos

Temporal sentence grounding in videos (TSGV) is a task to retrieve a video segment that semantically corresponds to a query in natural language.

Dataset
JSON

Skip-Clip: Self-Supervised Spatiotemporal Representation Learning by Future C...

A self-supervised spatiotemporal representation learning approach for videos, combining temporal coherence and future clip order ranking.

Dataset
JSON

SCUBA and SCUFO

The dataset used in the paper to evaluate static bias in action representations.

Dataset
JSON

Assembly101: a large-scale multi-view video dataset for understanding procedu...

Assembly101: a large-scale multi-view video dataset for understanding procedural activities

Dataset
JSON

Miradata

The dataset used in the paper for Miradata

Dataset
JSON

YouTube-VIS Dataset

The YouTube-VIS dataset is a large-scale dataset for instance segmentation, containing 2,883 videos and 131K instance masks.

Dataset
JSON

MSRVTT-QA

Video question answering (VideoQA) requires systems to understand the visual information and infer an answer for a natural language question from it.

Dataset
JSON

InternVid: A Large-Scale Video-Text Dataset for Multimodal Understanding and ...

InternVid: A large-scale video-text dataset for multimodal understanding and generation.

Dataset
JSON

THUMOS Challenge: Action Recognition with a Large Number of Classes

THUMOS Challenge: Action Recognition with a Large Number of Classes.

Dataset
JSON

ActivityNet-1.3

Generating human action proposals in untrimmed videos is an important yet challenging task with wide applications. Current methods often suffer from the noisy boundary locations...

Dataset
JSON

SDU Fall Dataset

The dataset contains videos of people performing normal activities and falls.

Dataset
JSON

UR Dataset

The dataset contains videos of people performing normal activities and falls.

Dataset
JSON

Spatio-Temporal Adversarial Learning for Detecting Unseen Falls

The proposed spatio-temporal adversarial learning framework for detecting unseen falls from videos.

Dataset
JSON

132 datasets found