FIVR-200K

Dataset Information
Modalities
Videos
Introduced
2019
License
Unknown
Homepage
Official Website
Contents

Overview

The FIVR-200K dataset has been collected to simulate the problem of Fine-grained Incident Video Retrieval (FIVR). The dataset comprises 225,960 videos associated with 4,687 Wikipedia events and 100 selected video queries.

Variants: FIVR-200K

Associated Benchmarks

This dataset is used in 1 benchmark:

Recent Benchmark Submissions

Task Model Paper Date
Video Retrieval S2VS Self-Supervised Video Similarity Learning 2023-04-06
Video Retrieval S2VS Self-Supervised Video Similarity Learning 2023-04-06
Video Retrieval VVS VVS: Video-to-Video Retrieval with Irrelevant … 2023-03-15
Video Retrieval VRAG (video) VRAG: Region Attention Graphs for … 2022-05-18
Video Retrieval VRAG (CS) VRAG: Region Attention Graphs for … 2022-05-18
Video Retrieval DnS (S^f_B) DnS: Distill-and-Select for Efficient and … 2021-06-24
Video Retrieval DnS (S^c) DnS: Distill-and-Select for Efficient and … 2021-06-24
Video Retrieval DnS (S^f_A) DnS: Distill-and-Select for Efficient and … 2021-06-24
Video Retrieval TCAf Temporal Context Aggregation for Video … 2020-08-04
Video Retrieval TCAsym Temporal Context Aggregation for Video … 2020-08-04
Video Retrieval TCAc Temporal Context Aggregation for Video … 2020-08-04
Video Retrieval ViSiLf ViSiL: Fine-grained Spatio-Temporal Video Similarity … 2019-08-20
Video Retrieval ViSiLv (tf) ViSiL: Fine-grained Spatio-Temporal Video Similarity … 2019-08-20
Video Retrieval ViSiLv (pt) ViSiL: Fine-grained Spatio-Temporal Video Similarity … 2019-08-20
Video Retrieval ViSiLsym ViSiL: Fine-grained Spatio-Temporal Video Similarity … 2019-08-20

Research Papers

Recent papers with results on this dataset:

External Links: