Charades

Dataset Information
Modalities
Videos
Introduced
2016
License
Custom (non-commercial)
Homepage
Official Website
Contents

Overview

The Charades dataset is composed of 9,848 videos of daily indoors activities with an average length of 30 seconds, involving interactions with 46 objects classes in 15 types of indoor scenes and containing a vocabulary of 30 verbs leading to 157 action classes. Each video in this dataset is annotated by multiple free-text descriptions, action labels, action intervals and classes of interacting objects. 267 different users were presented with a sentence, which includes objects and actions from a fixed vocabulary, and they recorded a video acting out the sentence. In total, the dataset contains 66,500 temporal annotations for 157 action classes, 41,104 labels for 46 object classes, and 27,847 textual descriptions of the videos. In the standard split there are7,986 training video and 1,863 validation video.

Source: Temporal Reasoning Graph for Activity Recognition

Variants: Charades

Associated Benchmarks

This dataset is used in 4 benchmarks:

Recent Benchmark Submissions

Task Model Paper Date
Action Detection UniMD+Sync. (RGB+Flow) UniMD: Towards Unifying Moment Retrieval … 2024-04-07
Action Detection PAT PAT: Position-Aware Transformer for Dense … 2023-08-09
Zero-Shot Action Recognition MSQNet Actor-agnostic Multi-label Action Recognition with … 2023-07-20
Action Recognition MSQNet Actor-agnostic Multi-label Action Recognition with … 2023-07-20
Zero-Shot Action Recognition MAXI MAtch, eXpand and Improve: Unsupervised … 2023-03-15
Zero-Shot Action Recognition VideoCoCa VideoCoCa: Video-Text Modeling with Zero-Shot … 2022-12-09
Action Detection TTM Token Turing Machines 2022-11-16
Zero-Shot Action Recognition CLIP-Hitchhiker (ViT-B/16, 32 frames) A CLIP-Hitchhiker's Guide to Long … 2022-05-17
Action Detection MS-TCT (RGB only) MS-TCT: Multi-Scale Temporal ConvTransformer for … 2021-12-07
Action Detection Coarse-Fine Networks (w/ self-supervised detection pretraining) Weakly-guided Self-supervised Pretraining for Temporal … 2021-11-26
Action Detection CTRN CTRN: Class-Temporal Relational Network for … 2021-10-26
Action Detection MLAD (RGB + Flow) Modeling Multi-Label Action Dependencies for … 2021-03-04
Action Detection Coarse-Fine Networks Coarse-Fine Networks for Temporal Activity … 2021-03-01
Action Detection 3D ResNet-50 + super-events pretrained on AViD AViD Dataset: Anonymized Videos from … 2020-07-10
Action Detection 3D ResNet-50 pretrained on AViD AViD Dataset: Anonymized Videos from … 2020-07-10
Video Classification Multigrid A Multigrid Method for Efficiently … 2019-12-02
Action Detection I3D + biGRU + VS-ST-MPNN Representation Learning on Visual-Symbolic Graphs … 2019-05-17
Action Detection TGM (RGB+Flow) Temporal Gaussian Mixture Layer for … 2018-03-16
Action Detection Super-events (RGB+Flow) Learning Latent Super-Events to Detect … 2017-12-05
Action Detection R-C3D R-C3D: Region Convolutional 3D Network … 2017-03-22

Research Papers

Recent papers with results on this dataset:

External Links: