[Models](/models)/Alibaba-VELLDEPTH/CTVG-4B

Unresolved: academic-use notice from TimeLens2, no commercial license granted

# CTVG-4B

by Alibaba-VELLDEPTH

A 4B model that returns the exact start and end time of a described moment in a video, with a confidence score for each interval

3likes

4.8Bparams

[HuggingFace](https://huggingface.co/Alibaba-VELLDEPTH/CTVG-4B)[Run it on your own data, free](https://studio.mixpeek.com/namespaces/create?mode=managed&utm_source=homepage&utm_medium=model_page&utm_campaign=mvs_onramp)

Identifiers

Model ID

`Alibaba-VELLDEPTH/CTVG-4B`

## Deploy CTVG-4B

Single-tenant

Mixpeek has no managed extractor for this model. On a single-tenant deployment you upload the weights and a custom plugin serves them next to the rest of your pipeline.

[Read the customer-hosted guide](https://mixpeek.com/docs/customer-hosted/overview) [Talk to us about single-tenant](/demo)

## Overview

CTVG-4B is a video temporal grounding model from Alibaba, released in October 2026 with the paper Grounding with Confidence: Controllable Generative Video Temporal Grounding. Given a video and a text query such as "a person opens a door", it generates candidate time intervals and scores each one with a small confidence head, so you can rank the intervals, keep the best, or reject all of them when the event is not in the video.

It is a fine-tune of MCG-NJU/TimeLens2-4B, which uses the Qwen3-VL architecture. The card reports 67.39 tF1@0.5 and 63.24 temporal IoU on the 320 queries of OMTG-Bench, and says most of that gain comes from non-maximum suppression rather than from the confidence head. Its license is unresolved: the card carries an academic-use notice from TimeLens2 and grants no commercial license.

## Architecture

Qwen3-VL-architecture generator (about 4.8B parameters, merged BF16), fine-tuned from TimeLens2-4B with supervised training and then set-level reinforcement learning. A separate confidence head (LayerNorm, Linear 2560 to 256, GELU, Linear 256 to 1, sigmoid) scores each generated interval from the mean of its decoder states. Candidates pass temporal NMS at IoU 0.3 before the confidence threshold. Released inference settings: 2 fps, a 16,384-token context and at most 512 output tokens.

## Mixpeek SDK Integration

IngestRetrieve

\# Index the videos first so search can find the right scenes. This uses
# Mixpeek's multimodal extractor with scene splitting, as in the video
# scene search recipe; CTVG-4B then runs on your side on the scenes it returns.
import requests

requests.post(
    "https://api.mixpeek.com/v1/buckets/bkt\_your\_bucket/objects",
    headers={"Authorization": "Bearer API\_KEY", "X-Namespace": "ns\_your\_namespace"},
    json={"blobs": \[{"property": "video", "type": "video",
                     "data": "s3://your-bucket/recordings/dock-cam-2.mp4"}\]},
)

## Capabilities

*   Returns start and end times for a text-described event in a video
*   Several candidate intervals per query, for events that repeat
*   A confidence score per interval, for ranking or rejecting
*   Thresholds can change without decoding the video again
*   Runs through the authors' Grounding-with-Confidence inference code

## Use Cases on Mixpeek

Trimming a retrieved scene to the exact seconds a query describes

Finding every time an action repeats in a recording

Rejecting a search hit when the described event is not in the clip

## Benchmarks

Dataset

Metric

Score

Source

OMTG-Bench (320 queries)

tF1@0.5

67.39%

Model card: Alibaba-VELLDEPTH/CTVG-4B (self-reported; threshold selected on the test set)

OMTG-Bench (320 queries)

Temporal IoU

63.24%

Model card (self-reported)

OMTG-Bench (320 queries)

EtF1

42.64%

Model card (self-reported)

## Performance

Input SizeA video file and a text query, read at 2 fps in the released configuration

Embedding Dimn/a (outputs time intervals with confidence scores)

GPU LatencyInput dependent

GPU ThroughputBatch dependent

GPU MemoryModel dependent

The card says the operating threshold was chosen on the test set, so it is not a calibrated default, and that the confidence head's gain after NMS (+0.32 points) is not statistically established. It needs a CUDA GPU and the companion inference code. We have not measured it.

## Common Pipeline Companions

[

MCG-NJU/OneStreamer-4B

Streaming video model for live feeds, where CTVG-4B works on recorded clips

](/model/MCG-NJU/OneStreamer-4B)[

Qwen/Qwen3-VL-4B-Instruct

A general video-language model to answer questions about the interval CTVG-4B returns

](/model/Qwen/Qwen3-VL-4B-Instruct)

## Frequently Asked Questions

### What is CTVG-4B?

A video temporal grounding model. You give it a video and a description of an event, and it returns the time intervals where that event happens, each with a confidence score.

### What is video temporal grounding?

Finding when something happens in a video from a text description, as start and end times. Search tells you which video or scene matches; grounding tells you which seconds.

### Can I use CTVG-4B commercially?

The card does not grant that. It preserves an academic-use notice from TimeLens2, its base model, and says public availability does not imply permission for commercial use. Check the upstream terms before using it in a product.

### How do I use it with Mixpeek?

Index your videos with scene splitting so a retriever returns the matching scenes with their start and end times, then run CTVG-4B on those scenes with the same query to get the exact interval, as in the example on this page.

## Explore on Mixpeek

[

Browse all models

Search the full model catalog

](/models)[

Feature Extractors

See how Mixpeek runs models as extractors

](/extractors)[

Mixpeek Vector Store

Store & search embeddings at scale

](/mvs)[

Pricing

Usage-based pricing for pipelines

](/pricing)[

All Curated Lists

Compare models, APIs & infrastructure

](/curated-lists)

### Specification

OrganizationAlibaba-VELLDEPTH

Retriever\-

Parameters4.8B

LicenseUnresolved: academic-use notice from TimeLens2, no commercial license granted

Downloads/moN/A

Likes3

[

### Research Paper

Grounding with Confidence: Controllable Generative Video Temporal Grounding

arxiv.org](https://arxiv.org/abs/2609.39883)

### Build a pipeline with CTVG-4B

Add this model to a processing pipeline alongside other extractors. Combine with retrieval stages for end-to-end search.

[Run it on your own data, free](https://studio.mixpeek.com/namespaces/create?mode=managed&utm_source=homepage&utm_medium=model_page&utm_campaign=mvs_onramp)