computer-vision-1
Ad-hoc video search
3260 papers • 126 benchmarks • 313 datasets
The Ad-hoc search task ended a 3 year cycle from 2016-2018 with a goal to model the end user search use-case, who is searching (using textual sentence queries) for segments of video containing persons, objects, activities, locations, etc. and combinations of the former. While the Internet Archive (IACC.3) dataset was adopted between 2016 to 2018, starting in 2019 a new data collection based on Vimeo Creative Commons (V3C) will be adopted to support the task for at least 3 more years. Given the test collection (V3C1 or IACC.3), master shot boundary reference, and set of Ad-hoc queries (approx. 30 queries) released by NIST, return for each query a list of at most 1000 shot IDs from the test collection ranked according to their likelihood of containing the target query.
(Image credit: Papersgraph)
Benchmarks
These leaderboards are used to track progress in ad-hoc-video-search-1
Trend
Dataset
Best Model
Actions
TRECVID-AVS16 (IACC.3)
TRECVID-AVS16 (IACC.3)
TRECVID-AVS17 (IACC.3)
TRECVID-AVS17 (IACC.3)
Libraries
iUse these libraries to find ad-hoc-video-search-1 models and implementations
Datasets
Subtasks
No subtasks available.
Most implemented papers
Dual Encoding for Zero-Example Video Retrieval
Xirong Li, Chaoxi Xu, Gang Yang, S. Ji, Jianfeng Dong, Yuan He, Xun Wang•Sun Sep 16 2018
This paper takes a concept-free approach, proposing a dual deep encoding network that encodes videos and queries into powerful dense representations of their own and establishes a new state-of-the-art for zero-example video retrieval.
289
