Results for “robotic-vision”

COCO: Microsoft COCO: Common Objects in Context

Generate image captions, answer visual questions, and perform image-text retrieval using BLIP-2's Q-Former architecture with frozen vision encoders and LLMs.

Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or multimodal chat with state-of-the-art zero-shot performance.

Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or multimodal chat with state-of-the-art zero-shot performance.

This skill provides guidance for video analysis and processing tasks using computer vision techniques. It should be used when analyzing video frames, detecting motion or events, tracking objects, extracting temporal data (e.g., identifying specific frames like takeoff/landing moments), or performing frame-by-frame processing with OpenCV or similar libraries.

Develop, migrate, and debug ROS 1 and ROS 2 robotics projects with support for build systems, navigation, control, simulation, and embedded integration.

Diagnose and fix Vue 3 runtime errors, warnings, async failures, and SSR/hydration issues with targeted debugging guides.

Transform text plans into interactive visual documents with diagrams, code snippets, and review surfaces for coding agents.

NLVR2: A Visual Reasoning Benchmark for Natural Language

Render long lists (1k+ rows) efficiently in Salesforce LWC using lightning-datatable infinite loading or an IntersectionObserver sentinel, with keyset pagination and accessibility guidance.

Nocaps: Novel Object Captioning at Scale

Open-Vocabulary Object Detection Using Captions

Multimodal Few-Shot Learning with Frozen Language Models

Scaling Vision Transformers to 22 Billion Parameters

Generate aerial drone-perspective footage with sweeping bird's-eye views, orbit shots, and flyover sequences for landscapes, architecture, and events.

Mosaic Augmentation for Detection and Segmentation

See, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand- extract frames, build visual/semantic/temporal indexes, and search moments with timestamps and auto-clips. Act- transcode and normalize (codec, fps, resolution, aspect ratio), perform timeline edits (subtitles, text/image overlays, branding, audio overlays, dubbing, translation), generate media assets (image, audio, video), and create real time alerts for events from live streams or desktop capture.

LongVA: Long Context Transfer from Language to Vision

Watch and understand video files by converting them to viewable image storyboards for enjoyment, analysis, species identification, behavior tracking, and comprehension

Enables visual instruction tuning and image-based conversations using open-source vision-language models. Supports multi-turn image chat, visual question answering, and image understanding tasks.

Scaling Vision with Sparse Mixture of Experts

Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis.

Runs the open-source LLaVA vision-language model for image understanding, captioning, visual question answering, and multi-turn image conversations, including setup, inference, and training guidance.

Visual Instruction Tuning

Expert in drone systems, computer vision, and autonomous navigation. Specializes in flight control, SLAM, object detection, sensor fusion, and path planning. Activate on "drone", "UAV", "SLAM", "visual odometry", "PID control", "MAVLink", "Pixhawk", "path planning", "A*", "RRT", "EKF", "sensor fusion", "optical flow", "ByteTrack". NOT for domain-specific inspection tasks like fire detection, roof damage assessment, or thermal analysis (use drone-inspection-specialist), GPU shader optimization (use metal-shader-expert), or general image classification without drone context (use clip-aware-embeddings).

Towards Open-World Segmentation of Parts

Three.js interaction - raycasting, controls, mouse/touch input, object selection. Use when handling user input, implementing click detection, adding camera controls, or creating interactive 3D experiences.

Manim CE animations: 3Blue1Brown math/algo videos.

Control the Unreal Editor level viewport — camera type/position, view mode, FOV, exposure, layout, and rendering settings (ViewportService). Use when the user asks to move the editor camera, change the view mode (Lit/Unlit/Wireframe), set FOV/exposure, switch viewport layout, or frame the level for a screenshot.

Vision-language chat: VQA, captioning, image dialogue.

GLIP: Grounded Language-Image Pre-training

See, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand- extract frames, build visual/semantic/temporal indexes, and search moments with timestamps and auto-clips. Act- transcode and normalize (codec, fps, resolution, aspect ratio), perform timeline edits (subtitles, text/image overlays, branding, audio overlays, dubbing, translation), generate media assets (image, audio, video), and create real time alerts for events from live streams or desktop capture.

Build a visual sequence that proves, explains, and supports decisions.

Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. (gstack)