仅显示平台推荐
VIOLIN
${starItems[0]}

VIOLIN(视频和语言推理),由来自15887个视频片段的95322个视频假设对组成,跨越582个小时的视频(YouTube和电视节目)。

2020-11-18 2 0
TAO
${starItems[1]}

TAO是一个用于跟踪任何对象的联邦数据集,包含2907个高分辨率视频,在不同的环境中捕获,这些视频的平均长度为半分钟。

2020-11-18 0 1
RISE_Video_Dataset
${starItems[2]}

介绍了RISE,第一个用于识别工业烟雾排放的大规模视频数据集。我们的数据集包含12,567个剪辑,其中19个不同的视角来自三个监控三个不同工业设施的站点。

2020-11-19 0 0
Condensed_Movies
${starItems[3]}

一个大规模的视频数据集,包含有详细字幕的电影片段。超过3000部不同类型、不同国家和不同年代的电影。

2020-11-18 0 1
AVID
${starItems[4]}

AViD数据集:来自不同国家的匿名视频,AViD是一个大型视频数据集,包含467k个视频和887个动作类。所收集的视频具有知识共享许可证。 https://github.com/piergiaj/AViD

2020-10-27 1 4
FlyingChairs
${starItems[5]}

由相对固定的背景以及人工制造的椅子,有利于提升flownet2.0版本的训练精度

2022-07-26 144 3
PPR10K
${starItems[6]}

训练集和三个专家的gt结果

2022-08-14 0 0
Visual-Tracker-Benchmark
${starItems[7]}

The full benchmark contains 100 sequences from recent literatures. The sequence names are in CamelCase without any blanks or underscores (_). When there exist multiple targets each target is identified as dot+id_number (e.g. Jogging.1 and Jogging.2). Each row in the ground-truth files represents the bounding box of the target in that frame, (x, y, box-width, box-height). In most sequences the first row corresponds to the first frame and the last row to the last frame, except the following sequences: David(300:770), Football1(1:74), Freeman3(1:460), Freeman4(1:283).

2022-08-05 1 0
VSR_dataset
${starItems[8]}

视频超分辨率经典训练数据集

2022-05-26 4 0
kinetics400
${starItems[9]}

kinetics400

2022-04-25 26 0
PP8K_Dataset
${starItems[10]}

This folder provides our produced "Peking University and Peng Cheng Laboratory 8K (PP8K)" video dataset, including "8K Common Raw Format Video (PP8K-CRFV) sequences" and "8K Video Salient Object Detection (PP8K-VSOD) sequences".

2022-05-30 0 0
DAVIS
${starItems[11]}

DAVIS2016&DAVIS2017

2022-05-25 2 0
VGG-Sound
${starItems[12]}

vggi - sound是一个视听对应的数据集,由从上传到YouTube的视频中提取的音频片段组成

2020-11-18 0 0
OpenIVA Model Zoo
${starItems[13]}

2021-12-20 0 8
CVD2014
${starItems[14]}

CVD2014 nr video quality assessment

2021-02-02 0 3