#python #action_recognition #ava #benchmark #deep_learning #i3d #non_local #openmmlab #posec3d #pytorch #slowfast #spatial_temporal_action_detection #temporal_action_localization #tsm #tsn #video_understanding #x3d
https://github.com/open-mmlab/mmaction2
https://github.com/open-mmlab/mmaction2
GitHub
GitHub - open-mmlab/mmaction2: OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark
OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark - open-mmlab/mmaction2
#python #mllm #point_clouds #scene_understanding #spatial_intelligence
SpatialLM is a powerful 3D language model that turns complex 3D point cloud data from videos, RGBD images, or LiDAR into clear, structured 3D scene layouts showing walls, doors, windows, and objects with labels. It works without needing special equipment and can detect user-specified object categories. This helps you understand and analyze indoor spaces better, useful for robotics, navigation, and 3D design. You can run it on your data, visualize results, and even customize detection tasks easily, making 3D scene understanding more accessible and flexible for many applications.
https://github.com/manycore-research/SpatialLM
SpatialLM is a powerful 3D language model that turns complex 3D point cloud data from videos, RGBD images, or LiDAR into clear, structured 3D scene layouts showing walls, doors, windows, and objects with labels. It works without needing special equipment and can detect user-specified object categories. This helps you understand and analyze indoor spaces better, useful for robotics, navigation, and 3D design. You can run it on your data, visualize results, and even customize detection tasks easily, making 3D scene understanding more accessible and flexible for many applications.
https://github.com/manycore-research/SpatialLM
GitHub
GitHub - manycore-research/SpatialLM: [NeurIPS 2025] SpatialLM: Training Large Language Models for Structured Indoor Modeling
[NeurIPS 2025] SpatialLM: Training Large Language Models for Structured Indoor Modeling - manycore-research/SpatialLM
#javascript #3d_globe #cesium #flight_tracking #geospatial #geospatial_intelligence #gis #osint #photogrammetry #satellite_tracking #spatial_intelligence #webgl #worldview
God’s Eye View is a browser app that shows a real-time 3D Earth with live flights, ships, satellites, earthquakes, traffic, public cameras, and voice control. It helps you explore the world fast, see what is happening in one place, and track public signals without signing up.
https://github.com/bilawalsidhu/gods-eye-view
God’s Eye View is a browser app that shows a real-time 3D Earth with live flights, ships, satellites, earthquakes, traffic, public cameras, and voice control. It helps you explore the world fast, see what is happening in one place, and track public signals without signing up.
https://github.com/bilawalsidhu/gods-eye-view
GitHub
GitHub - bilawalsidhu/gods-eye-view: A spy satellite simulator in your browser, except the data is real. Live open source spatial…
A spy satellite simulator in your browser, except the data is real. Live open source spatial intelligence on a photorealistic 3D globe. - bilawalsidhu/gods-eye-view