CoChat

ActivityNet: A large-scale video benchmark for human activity understanding

Heilbron, Fabian Caba, Escorcia, Victor, Ghanem, Bernard, Niebles, Juan Carlos · 2015 · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

The DOI matches its Crossref record; 40 of the 43 references it cites were found in a registry or an index.

Abstract

In spite of many dataset efforts for human action recognition, current computer vision algorithms are still severely limited in terms of the variability and complexity of the actions that they can recognize. This is in part due to the simplicity of current benchmarks, which mostly focus on simple actions and movements occurring on manually trimmed videos. In this paper we introduce ActivityNet, a new large-scale video benchmark for human activity understanding. Our benchmark aims at covering a wide range of complex human activities that are of interest to people in their daily living. In its current version, ActivityNet provides samples from 203 activity classes with an average of 137 untrimmed videos per class and 1.41 activity instances per video, for a total of 849 video hours. We illustrate three scenarios in which ActivityNet can be used to compare algorithms for human activity understanding: untrimmed video classification, trimmed activity classification and activity detection.

Overview

Integrity signals

Registry

Crossref · 10.1109/cvpr.2015.7298698

Cites

40 of 40 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

Show all 40 references

Research works printed but not linked: 1

  1. wang, 2013, Lear-inria submission for the thu-mos workshop, THUMOS ICCV Workshop on Action Recognition with A Large Number of Classes

Cited by

Items 501–600 of 1,010

Metadata

Authors
Heilbron, F. C., Escorcia, V., Ghanem, B., & Niebles, J. C.
Affiliations
  • Universidad del Norte (CO)
  • King Abdullah University of Science and Technology (SA)
Venue
2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2015-06
Pages
961-970
ISSN
1063-6919 (ISSN-L)
OpenAlex
W1927052826
Cited by
2,578
References
43
Citations by year
2026: 161 · 2025: 273 · 2024: 349 · 2023: 333 · 2022: 305 · 2021: 374 · 2020: 258 · 2019: 215 · 2018: 162 · 2017: 99 · 2016: 42 · 2015: 7
FWCI
42.38
Type
conference paper
Language
en
Open access
closed
Locations
  • IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
  • King Abdullah University of Science and Technology Repository (King Abdullah University of Science and Technology) (submittedVersion)
Funders
  • Microsoft Research
  • King Abdullah University of Science and Technology
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Human Pose and Action Recognition
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
  • Physical Sciences › Computer Science › Human-Computer Interaction › Hand Gesture Recognition Systems
Keywords
ActivityNet, human activity understanding, human action recognition, video benchmark, activity detection, activity classification, activities of daily living, large-scale video datasets

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.