10 actions in 10 pieces of software · ranked by words, meaning and measured trust · 691 ms

1. 1SpotSound Temporal Groundingverified and signedpassport

   MCP serverrecord

   • spotsound_temporal_grounding_spot

     Localise a sound event described in natural language inside an audio recording. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool. Returns: A wa

2. 2Temporal Context Routingverified and signedpassport

   MCP serverrecord

   • temporal_context_routing_generate

     Generate a multi-shot video with synchronised audio from a timed script JSON. Returns: A tuple of (path to the generated mp4 with audio, a markdown run summary).

3. 3candysunplus/grounding-dino-swinbverified and signedpassport

   modelrecord

   • candysunplus/grounding-dino-swinb

     grounding-dino-swinb

4. 4tao-train-mask-grounding-dinoverified and signedpassport

   skillnvidia/skillsrecord

   • tao-train-mask-grounding-dino

     Mask Grounding DINO for grounded instance segmentation. Extends Grounding DINO with a mask-prediction head for open-set segmentation guided by text prompts. Use when training, evaluating, exporting, quantizing, or running inference for a TAO Mask-Grounding-DINO model. Trigger phrases include "train

5. 5adirik/grounding-dinoverified and signedpassport

   modelrecord

   • adirik/grounding-dino

     Detect everything with language!

6. 6hautechai/grounding-dinoverified and signedpassport

   modelrecord

   • hautechai/grounding-dino

     Grounding DINO: zero-shot text-prompted object detection (SwinT-OGC). H100 build.

7. 7PinpointQA Spatial Groundingverified and signedpassport

   MCP serverrecord

   • pinpoint_qa_spatial_grounding_run_inference

     Answer a spatial understanding question about an indoor video. Upload a video (or select an example) and ask a question about where a small object is located. The model will describe the object's spatial position relative to nearby reference objects. If a user passes a file as an input, use the uplo

8. 8tao-generate-image-groundingverified and signedpassport

   skillnvidia/skillsrecord

   • tao-generate-image-grounding

     Two-step image grounding pipeline: extracts referring expressions from (image, caption) pairs and grounds them to pixel-space bounding boxes via a VLM. Use when the user wants to ground captions to bboxes, generate phrase-grounded annotations, auto-label images for grounding, or run the image_ground

9. 9dbs-theory-groundingverified and signedpassport

   skilldontbesilent2025/dbskillrecord

   • dbs-theory-grounding

     理论溯源与案例重释。审查 PPT、课程、文案或方法论中的经验判断，先判断命题是否成立，再匹配并核实可信理论，用该理论重释案例并标明边界。适用于给自创理论找依据、给 PPT 补理论来源、判断一句话能否上升为理论、检查是否硬套名人；聚焦单次理论锚定，不默认展开历史同构研究。

10. 10Claim Groundingverified and signedpassport

    agentrecord

    • Check answer