Video Scene Search

Find specific scenes within videos using natural language descriptions. The pipeline detects scene boundaries, generates embeddings for each scene, and enables precise timestamp-level search across an entire video library. Query for visual content, actions, or spoken dialogue.

video

image

text

Multi-Tier

3.2K runs

Run in Builder

from mixpeek import Mixpeek

client = Mixpeek(api_key="YOUR_API_KEY")

# Create video collection with scene decomposition
collection = client.collections.create(
    namespace_id="ns_your_namespace",
    name="video_scenes",
    extractors=["multimodal-extractor", "text-extractor"],
    params={"video_chunking": "scene-based"}
)

# Upload videos
client.buckets.upload(bucket_id="bkt_videos", url="s3://your-bucket/videos/")

# Search for a specific scene
results = client.retrievers.execute(
    retriever_id="ret_scene_search",
    query={"text": "person presenting a chart on a whiteboard"}
)

for doc in results["documents"]:
    print(f"Video: {doc['root_object_id']}")
    print(f"  Scene: {doc['start_time']:.1f}s - {doc['end_time']:.1f}s")
    print(f"  Score: {doc['score']:.3f}")
    if doc.get("text"):
        print(f"  Transcript: {doc['text'][:80]}...")

Feature Extractors

Retriever Stages

rerank

Rerank documents using cross-encoder models for accurate relevance

sort

Related Recipes & Resources

Explore these related resources to deepen your understanding and discover more powerful features

Recipe

Hierarchical Classification

Assign content to multi-level category hierarchies using embedding-based classification. Define your taxonomy once, then classify new content automatically with confidence scores.

Learn more

Recipe

Brand Safety & Ad Verification Pipeline

GARM-compliant brand safety pipeline for ad networks. Analyze video and image creatives for brand safety violations before serving.

Learn more

Recipe

Automated Video Tagging

Automatically generate descriptive tags for video content using scene analysis, object detection, and taxonomy classification. Each video receives structured labels for scenes, objects, actions, and custom business categories without manual annotation.

Learn more

Recipe

Searchable Video Library

Turn an unstructured video archive into a fully searchable library. Each video is decomposed into scenes with transcriptions, visual embeddings, and metadata. Users search by natural language and jump directly to the relevant moment in any video.

Learn more

Recipe

Semantic Multimodal Search

Unified semantic search across all content types. Query by natural language and retrieve relevant video clips, images, audio segments, and documents based on meaning-not keywords or manual tags.

Learn more

Recipe

Feature Extraction

Multi-tier feature extraction that decomposes content into searchable components: embeddings, transcripts, detected objects, OCR text, scene boundaries, and more. The foundation for all downstream retrieval and analysis.

Learn more