The video label detection feature of Intelligent Media Management (IMM) allows you to perform intelligent analysis on a video and obtain labels of the video. IMM provides a comprehensive set of video labels. Video label detection provides high accuracy, effectiveness, and value. You can classify and retrieve videos based on these labels. This way, you can manage videos in a more accurate and efficient manner.
Scenarios
Scenario | Description |
Video classification | IMM provides suggestions on the classification of videos. The categories include news, entertainment, game, technology, food, sports, travel, animation, dance, music, film and television, and automobile. |
Video retrieval | You can retrieve videos based on labels. |
Video recommendation | IMM helps you extract comprehensive and high-value content labels from videos. Based on the intelligent recommendation technology, IMM can accurately match the content labels with user labels to achieve personalized recommendation. |
Limits
The following table describes the limits on video label detection.
Item | Description |
Video formats | Video label detection supports the following formats: AVI, MPEG, MPG, DAT, DIVX, XVID, RM, RMVB, MOV, QT, ASF, WMV, VOB, 3GP, MP4, FLV, AVS, MKV, TS, OGM, NSV, and SWF. |
Prerequisites
An AccessKey pair is created and obtained. For more information, see Create an AccessKey pair.
OSS is activated, a bucket is created, and objects are uploaded to the bucket. For more information, see Upload objects.
IMM is activated. For more information, see Activate IMM.
A project is created in the IMM console. For more information, see Create a project.
NoteYou can call the CreateProject operation to create a project. For more information, see CreateProject.
You can call the ListProjects operation to query the existing projects in a specific region. For more information, see ListProjects.
Procedure
Upload a video to the OSS bucket, create a video label detection task to label the video, and use returned labels in your application scenarios.
Usage
Call the CreateVideoLabelClassificationTask operation to create an asynchronous task to detect video labels. Then, call the GetVideoLabelClassificationResult operation to obtain the result of the video label detection task.
The task information is retained for seven days after the task starts. Task information cannot be obtained after the seven-day window ends. You can use one of the following methods to query task information:
In the region in which the IMM project is located, configure a Simple Message Queue (SMQ) subscription to receive task information notifications.. For more information, see Asynchronous message examples. For information about the MNS SDK, see Step 4: Receive and delete the message.
In the region in which the IMM project is located, create an ApsaraMQ for RocketMQ 4.0 instance, a topic, and a group to receive task notifications. For more information, see Asynchronous message examples. For information about how to use ApsaraMQ for RocketMQ, see Use HTTP client SDKs to send and subscribe to normal messages.
In the region in which the IMM project is located, use EventBridge to receive task information notifications. For more information, see IMM events.
Sample response
{
"ProjectName": "test-project",
"DatasetName": "",
"RequestId": "D65E8038-C584-0809-9BF0-****",
"StartTime": "2022-08-22T05:01:17.572Z",
"EndTime": "2022-08-22T05:01:20.49Z",
"UserData": "",
"TaskType": "VideoLabelClassification",
"TaskId": "VideoLabelClassification-1b77de73-ff9f-4c39-b254-****",
"Status": "Succeeded",
"Code": "",
"Message": "",
"Labels": [
{
"Language": "zh-Hans",
"LabelName": "Color",
"LabelConfidence": 0.999,
"CentricScore": 0.77,
"LabelLevel": 2,
"ParentLabelName": "Others"
},
{
"Language": "zh-Hans",
"LabelName": "Others",
"LabelConfidence": 0.999,
"CentricScore": 0.77,
"LabelLevel": 1,
"ParentLabelName": ""
},
{
"Language": "zh-Hans",
"LabelName": "Mobile phone screenshot",
"LabelConfidence": 0.966,
"CentricScore": 0.707,
"LabelLevel": 2,
"ParentLabelName": "Other scenes"
},
{
"Language": "zh-Hans",
"LabelName": "Other scenes",
"LabelConfidence": 0.983,
"CentricScore": 0.711,
"LabelLevel": 1,
"ParentLabelName": ""
},
{
"Language": "zh-Hans",
"LabelName": "Blue",
"LabelConfidence": 1,
"CentricScore": 0.716,
"LabelLevel": 3,
"ParentLabelName": "Color"
},
{
"Language": "zh-Hans",
"LabelName": "Text",
"LabelConfidence": 0.995,
"CentricScore": 0.72,
"LabelLevel": 2,
"ParentLabelName": "Daily necessities"
},
{
"Language": "zh-Hans",
"LabelName": "Daily necessities",
"LabelConfidence": 0.995,
"CentricScore": 0.793,
"LabelLevel": 1,
"ParentLabelName": ""
},
{
"Language": "zh-Hans",
"LabelName": "Letter",
"LabelConfidence": 0.85,
"CentricScore": 0.795,
"LabelLevel": 2,
"ParentLabelName": "Daily necessities"
},
{
"Language": "zh-Hans",
"LabelName": "Sky blue",
"LabelConfidence": 0.658,
"CentricScore": 0.666,
"LabelLevel": 3,
"ParentLabelName": "Color"
},
{
"Language": "zh-Hans",
"LabelName": "Web page",
"LabelConfidence": 0.798,
"CentricScore": 0.721,
"LabelLevel": 2,
"ParentLabelName": "Virtual scene"
},
{
"Language": "zh-Hans",
"LabelName": "Virtual scene",
"LabelConfidence": 0.798,
"CentricScore": 0.721,
"LabelLevel": 1,
"ParentLabelName": ""
},
{
"Language": "zh-Hans",
"LabelName": "White",
"LabelConfidence": 0.899,
"CentricScore": 0.805,
"LabelLevel": 3,
"ParentLabelName": "Color"
},
{
"Language": "zh-Hans",
"LabelName": "Website",
"LabelConfidence": 0.667,
"CentricScore": 0.715,
"LabelLevel": 2,
"ParentLabelName": "Virtual scene"
},
{
"Language": "zh-Hans",
"LabelName": "Artwork",
"LabelConfidence": 0.809,
"CentricScore": 0.818,
"LabelLevel": 1,
"ParentLabelName": ""
},
{
"Language": "zh-Hans",
"LabelName": "Green",
"LabelConfidence": 0.824,
"CentricScore": 0.768,
"LabelLevel": 3,
"ParentLabelName": "Color"
},
{
"Language": "zh-Hans",
"LabelName": "Black",
"LabelConfidence": 0.937,
"CentricScore": 0.83,
"LabelLevel": 3,
"ParentLabelName": "Color"
},
{
"Language": "zh-Hans",
"LabelName": "Illustration",
"LabelConfidence": 0.768,
"CentricScore": 0.775,
"LabelLevel": 2,
"ParentLabelName": "Artwork"
},
{
"Language": "zh-Hans",
"LabelName": "Moon",
"LabelConfidence": 0.859,
"CentricScore": 0.756,
"LabelLevel": 3,
"ParentLabelName": "Natural landscape"
},
{
"Language": "zh-Hans",
"LabelName": "Sky",
"LabelConfidence": 0.733,
"CentricScore": 0.768,
"LabelLevel": 3,
"ParentLabelName": "Natural landscape"
},
{
"Language": "zh-Hans",
"LabelName": "Astronomical object",
"LabelConfidence": 0.832,
"CentricScore": 0.756,
"LabelLevel": 2,
"ParentLabelName": "Others"
},
{
"Language": "zh-Hans",
"LabelName": "Natural landscape",
"LabelConfidence": 0.897,
"CentricScore": 0.801,
"LabelLevel": 2,
"ParentLabelName": "Tourism & geography"
}
]
}FAQ
Can I specify video labels?
No, you cannot specify video labels.
What are the categories of video labels?
Video labels in IMM are classified into three categories:
Scenes: natural landscapes (for example, forests, beaches, and snow-capped mountains), living scenes (for example, homes and restaurants), disaster scenes, and more.
Events: talent shows, office activities, performances, and production processes, and more.
Objects: tableware, electronic products (for example, mobile phones and computers), furniture, vehicles, and more.