graph.json

{"meta": {"papers": 4068, "keywords": 89, "links": 381, "venue": "CVPR 2026", "communities": 6}, "nodes": [{"id": "Generation", "count": 629, "community": 1}, {"id": "Video", "count": 500, "community": 1}, {"id": "3D", "count": 461, "community": 2}, {"id": "Diffusion", "count": 337, "community": 4}, {"id": "Multimodal", "count": 332, "community": 3}, {"id": "Vision-Language", "count": 284, "community": 3}, {"id": "Efficient", "count": 248, "community": 4}, {"id": "Detection", "count": 230, "community": 0}, {"id": "Reasoning", "count": 226, "community": 3}, {"id": "Segmentation", "count": 201, "community": 0}, {"id": "Motion", "count": 154, "community": 1}, {"id": "Benchmark", "count": 143, "community": 3}, {"id": "Geometry", "count": 142, "community": 2}, {"id": "Human", "count": 134, "community": 1}, {"id": "Transformer", "count": 127, "community": 4}, {"id": "Gaussian Splatting", "count": 126, "community": 2}, {"id": "Robustness", "count": 125, "community": 0}, {"id": "LLM", "count": 113, "community": 3}, {"id": "Generalization", "count": 104, "community": 0}, {"id": "Sparse", "count": 103, "community": 2}, {"id": "Editing", "count": 101, "community": 1}, {"id": "Prompt", "count": 100, "community": 0}, {"id": "Dataset", "count": 96, "community": 3}, {"id": "Optimization", "count": 94, "community": 1}, {"id": "Matching", "count": 90, "community": 5}, {"id": "Medical", "count": 90, "community": 0}, {"id": "Agent", "count": 82, "community": 3}, {"id": "Distillation", "count": 80, "community": 4}, {"id": "Multi-View", "count": 80, "community": 2}, {"id": "Reinforcement Learning", "count": 79, "community": 3}, {"id": "Restoration", "count": 79, "community": 4}, {"id": "Open-Vocabulary", "count": 74, "community": 0}, {"id": "Pose Estimation", "count": 74, "community": 2}, {"id": "Image Generation", "count": 73, "community": 1}, {"id": "Grounding", "count": 73, "community": 3}, {"id": "Attention", "count": 72, "community": 4}, {"id": "Retrieval", "count": 68, "community": 1}, {"id": "Continual Learning", "count": 66, "community": 0}, {"id": "Test-Time", "count": 66, "community": 0}, {"id": "Zero-Shot", "count": 65, "community": 0}, {"id": "Autonomous Driving", "count": 61, "community": 3}, {"id": "Tracking", "count": 60, "community": 4}, {"id": "Autoregressive", "count": 59, "community": 1}, {"id": "Camera", "count": 54, "community": 1}, {"id": "Remote Sensing", "count": 53, "community": 0}, {"id": "Compression", "count": 52, "community": 1}, {"id": "Text-to-Image", "count": 51, "community": 1}, {"id": "Foundation Model", "count": 51, "community": 2}, {"id": "Anomaly", "count": 50, "community": 0}, {"id": "Depth", "count": 45, "community": 0}, {"id": "Super-Resolution", "count": 45, "community": 4}, {"id": "Few-Shot", "count": 44, "community": 0}, {"id": "Adversarial", "count": 43, "community": 0}, {"id": "Material/Lighting", "count": 42, "community": 1}, {"id": "Federated", "count": 41, "community": 0}, {"id": "Self-Supervised", "count": 40, "community": 2}, {"id": "Point Cloud", "count": 40, "community": 2}, {"id": "Contrastive", "count": 39, "community": 0}, {"id": "Forgery/Deepfake", "count": 39, "community": 0}, {"id": "Uncertainty", "count": 38, "community": 2}, {"id": "Navigation", "count": 37, "community": 3}, {"id": "Flow Matching", "count": 36, "community": 5}, {"id": "Event Camera", "count": 35, "community": 1}, {"id": "Face", "count": 35, "community": 4}, {"id": "Classification", "count": 35, "community": 0}, {"id": "World Model", "count": 34, "community": 1}, {"id": "Unsupervised", "count": 33, "community": 0}, {"id": "Avatar", "count": 30, "community": 2}, {"id": "Trajectory", "count": 30, "community": 1}, {"id": "Rendering", "count": 28, "community": 1}, {"id": "Hand", "count": 28, "community": 1}, {"id": "Embodied", "count": 27, "community": 3}, {"id": "Implicit/Neural Field", "count": 27, "community": 2}, {"id": "Mamba/SSM", "count": 27, "community": 0}, {"id": "CLIP", "count": 26, "community": 0}, {"id": "Stereo", "count": 25, "community": 5}, {"id": "Re-ID", "count": 24, "community": 0}, {"id": "Document/OCR", "count": 23, "community": 0}, {"id": "Quantization", "count": 22, "community": 3}, {"id": "Mesh", "count": 22, "community": 1}, {"id": "VQA", "count": 20, "community": 3}, {"id": "Registration", "count": 19, "community": 2}, {"id": "Captioning", "count": 17, "community": 1}, {"id": "Weakly-Supervised", "count": 17, "community": 0}, {"id": "In-Context", "count": 17, "community": 1}, {"id": "Texture", "count": 16, "community": 1}, {"id": "Scene Understanding", "count": 15, "community": 2}, {"id": "Action Recognition", "count": 14, "community": 0}, {"id": "Domain Adaptation", "count": 14, "community": 0}], "links": [{"source": "3D", "target": "Generalization", "weight": 11}, {"source": "3D", "target": "Matching", "weight": 11}, {"source": "3D", "target": "Tracking", "weight": 5}, {"source": "Gaussian Splatting", "target": "Optimization", "weight": 5}, {"source": "Benchmark", "target": "Editing", "weight": 7}, {"source": "Camera", "target": "Video", "weight": 10}, {"source": "Continual Learning", "target": "Distillation", "weight": 5}, {"source": "Efficient", "target": "Generation", "weight": 28}, {"source": "Efficient", "target": "Transformer", "weight": 19}, {"source": "Efficient", "target": "Video", "weight": 42}, {"source": "Generation", "target": "Transformer", "weight": 13}, {"source": "Generation", "target": "Video", "weight": 132}, {"source": "Self-Supervised", "target": "Video", "weight": 7}, {"source": "Transformer", "target": "Video", "weight": 11}, {"source": "Autonomous Driving", "target": "Reasoning", "weight": 7}, {"source": "Autonomous Driving", "target": "Vision-Language", "weight": 9}, {"source": "Reasoning", "target": "Vision-Language", "weight": 35}, {"source": "Diffusion", "target": "Efficient", "weight": 28}, {"source": "3D", "target": "Editing", "weight": 16}, {"source": "Generation", "target": "Reinforcement Learning", "weight": 13}, {"source": "Continual Learning", "target": "Few-Shot", "weight": 5}, {"source": "Continual Learning", "target": "Prompt", "weight": 6}, {"source": "Continual Learning", "target": "Vision-Language", "weight": 8}, {"source": "Few-Shot", "target": "Prompt", "weight": 6}, {"source": "Prompt", "target": "Vision-Language", "weight": 14}, {"source": "Quantization", "target": "Vision-Language", "weight": 5}, {"source": "3D", "target": "Efficient", "weight": 16}, {"source": "3D", "target": "Gaussian Splatting", "weight": 63}, {"source": "3D", "target": "Multi-View", "weight": 23}, {"source": "Efficient", "target": "Multi-View", "weight": 7}, {"source": "Gaussian Splatting", "target": "Multi-View", "weight": 5}, {"source": "Compression", "target": "Video", "weight": 15}, {"source": "Medical", "target": "Segmentation", "weight": 26}, {"source": "Diffusion", "target": "Text-to-Image", "weight": 12}, {"source": "Reasoning", "target": "Reinforcement Learning", "weight": 9}, {"source": "Reinforcement Learning", "target": "Vision-Language", "weight": 7}, {"source": "Gaussian Splatting", "target": "Geometry", "weight": 10}, {"source": "3D", "target": "Camera", "weight": 11}, {"source": "3D", "target": "Depth", "weight": 5}, {"source": "3D", "target": "Geometry", "weight": 43}, {"source": "3D", "target": "Pose Estimation", "weight": 22}, {"source": "3D", "target": "Uncertainty", "weight": 7}, {"source": "Gaussian Splatting", "target": "Pose Estimation", "weight": 7}, {"source": "Geometry", "target": "Pose Estimation", "weight": 5}, {"source": "Anomaly", "target": "Detection", "weight": 44}, {"source": "Diffusion", "target": "Super-Resolution", "weight": 19}, {"source": "Diffusion", "target": "Transformer", "weight": 47}, {"source": "Multimodal", "target": "Reasoning", "weight": 47}, {"source": "Multimodal", "target": "Test-Time", "weight": 5}, {"source": "Diffusion", "target": "Human", "weight": 9}, {"source": "Diffusion", "target": "Motion", "weight": 17}, {"source": "Diffusion", "target": "Sparse", "weight": 10}, {"source": "Human", "target": "Motion", "weight": 33}, {"source": "Human", "target": "Sparse", "weight": 5}, {"source": "Motion", "target": "Sparse", "weight": 5}, {"source": "Motion", "target": "Tracking", "weight": 7}, {"source": "Diffusion", "target": "Distillation", "weight": 11}, {"source": "Sparse", "target": "Transformer", "weight": 6}, {"source": "LLM", "target": "Multimodal", "weight": 68}, {"source": "Attention", "target": "Video", "weight": 11}, {"source": "Optimization", "target": "Video", "weight": 10}, {"source": "Reasoning", "target": "Video", "weight": 40}, {"source": "Compression", "target": "Efficient", "weight": 7}, {"source": "Efficient", "target": "Tracking", "weight": 8}, {"source": "Benchmark", "target": "Multimodal", "weight": 26}, {"source": "Benchmark", "target": "Vision-Language", "weight": 12}, {"source": "Multimodal", "target": "Vision-Language", "weight": 9}, {"source": "Generation", "target": "Motion", "weight": 49}, {"source": "Benchmark", "target": "Video", "weight": 26}, {"source": "Multimodal", "target": "Video", "weight": 24}, {"source": "3D", "target": "LLM", "weight": 7}, {"source": "3D", "target": "Reasoning", "weight": 14}, {"source": "LLM", "target": "Reasoning", "weight": 13}, {"source": "Diffusion", "target": "Generation", "weight": 62}, {"source": "Multimodal", "target": "Navigation", "weight": 5}, {"source": "Anomaly", "target": "Video", "weight": 8}, {"source": "Detection", "target": "Video", "weight": 22}, {"source": "3D", "target": "Generation", "weight": 83}, {"source": "3D", "target": "Human", "weight": 24}, {"source": "Generation", "target": "Human", "weight": 30}, {"source": "Editing", "target": "Generation", "weight": 17}, {"source": "Generation", "target": "Image Generation", "weight": 73}, {"source": "3D", "target": "Vision-Language", "weight": 19}, {"source": "Distillation", "target": "Segmentation", "weight": 5}, {"source": "Multimodal", "target": "Robustness", "weight": 11}, {"source": "Multimodal", "target": "Segmentation", "weight": 11}, {"source": "Robustness", "target": "Segmentation", "weight": 8}, {"source": "Continual Learning", "target": "Medical", "weight": 5}, {"source": "Continual Learning", "target": "Test-Time", "weight": 7}, {"source": "Medical", "target": "Prompt", "weight": 8}, {"source": "Prompt", "target": "Segmentation", "weight": 20}, {"source": "Prompt", "target": "Test-Time", "weight": 8}, {"source": "Segmentation", "target": "Test-Time", "weight": 6}, {"source": "3D", "target": "Open-Vocabulary", "weight": 13}, {"source": "Diffusion", "target": "Reinforcement Learning", "weight": 5}, {"source": "Efficient", "target": "Sparse", "weight": 15}, {"source": "Motion", "target": "Video", "weight": 32}, {"source": "Detection", "target": "Reasoning", "weight": 13}, {"source": "Diffusion", "target": "Geometry", "weight": 7}, {"source": "Generation", "target": "World Model", "weight": 5}, {"source": "Generation", "target": "Text-to-Image", "weight": 27}, {"source": "Image Generation", "target": "Text-to-Image", "weight": 25}, {"source": "Adversarial", "target": "Robustness", "weight": 11}, {"source": "3D", "target": "Robustness", "weight": 12}, {"source": "3D", "target": "Sparse", "weight": 21}, {"source": "Gaussian Splatting", "target": "Robustness", "weight": 7}, {"source": "Gaussian Splatting", "target": "Sparse", "weight": 14}, {"source": "Optimization", "target": "Vision-Language", "weight": 11}, {"source": "Detection", "target": "Distillation", "weight": 5}, {"source": "3D", "target": "Detection", "weight": 36}, {"source": "Autoregressive", "target": "Diffusion", "weight": 8}, {"source": "Autoregressive", "target": "Generation", "weight": 35}, {"source": "Autoregressive", "target": "Motion", "weight": 5}, {"source": "Human", "target": "Mesh", "weight": 6}, {"source": "3D", "target": "Scene Understanding", "weight": 10}, {"source": "Generation", "target": "Retrieval", "weight": 11}, {"source": "Generation", "target": "Tracking", "weight": 5}, {"source": "Adversarial", "target": "Vision-Language", "weight": 5}, {"source": "Diffusion", "target": "Video", "weight": 42}, {"source": "Benchmark", "target": "LLM", "weight": 7}, {"source": "Multimodal", "target": "Reinforcement Learning", "weight": 7}, {"source": "Benchmark", "target": "Dataset", "weight": 17}, {"source": "Dataset", "target": "Multimodal", "weight": 14}, {"source": "Prompt", "target": "Remote Sensing", "weight": 5}, {"source": "Segmentation", "target": "Video", "weight": 22}, {"source": "Diffusion", "target": "Vision-Language", "weight": 7}, {"source": "Generalization", "target": "Optimization", "weight": 5}, {"source": "Point Cloud", "target": "Registration", "weight": 5}, {"source": "Agent", "target": "Vision-Language", "weight": 6}, {"source": "Attention", "target": "Segmentation", "weight": 6}, {"source": "Open-Vocabulary", "target": "Remote Sensing", "weight": 6}, {"source": "Open-Vocabulary", "target": "Segmentation", "weight": 21}, {"source": "Remote Sensing", "target": "Segmentation", "weight": 10}, {"source": "3D", "target": "Multimodal", "weight": 18}, {"source": "Generation", "target": "Multimodal", "weight": 47}, {"source": "Generation", "target": "Reasoning", "weight": 21}, {"source": "3D", "target": "Video", "weight": 25}, {"source": "Generation", "target": "Pose Estimation", "weight": 10}, {"source": "Pose Estimation", "target": "Video", "weight": 7}, {"source": "3D", "target": "Test-Time", "weight": 6}, {"source": "Video", "target": "Zero-Shot", "weight": 5}, {"source": "Efficient", "target": "Restoration", "weight": 8}, {"source": "Generation", "target": "Texture", "weight": 5}, {"source": "Test-Time", "target": "Vision-Language", "weight": 12}, {"source": "Retrieval", "target": "Robustness", "weight": 6}, {"source": "Detection", "target": "Remote Sensing", "weight": 6}, {"source": "LLM", "target": "Video", "weight": 18}, {"source": "Benchmark", "target": "Detection", "weight": 8}, {"source": "Detection", "target": "Multimodal", "weight": 20}, {"source": "3D", "target": "Segmentation", "weight": 29}, {"source": "3D", "target": "Unsupervised", "weight": 6}, {"source": "Autonomous Driving", "target": "Multimodal", "weight": 5}, {"source": "Domain Adaptation", "target": "Unsupervised", "weight": 7}, {"source": "Segmentation", "target": "Unsupervised", "weight": 6}, {"source": "Diffusion", "target": "Multimodal", "weight": 13}, {"source": "Diffusion", "target": "Robustness", "weight": 7}, {"source": "Multimodal", "target": "Transformer", "weight": 8}, {"source": "Autoregressive", "target": "Video", "weight": 7}, {"source": "Detection", "target": "Sparse", "weight": 5}, {"source": "Generation", "target": "Geometry", "weight": 22}, {"source": "Event Camera", "target": "Motion", "weight": 6}, {"source": "3D", "target": "Agent", "weight": 6}, {"source": "Detection", "target": "Test-Time", "weight": 6}, {"source": "Compression", "target": "Generation", "weight": 9}, {"source": "Human", "target": "Multi-View", "weight": 5}, {"source": "Human", "target": "Video", "weight": 18}, {"source": "Multi-View", "target": "Video", "weight": 7}, {"source": "Geometry", "target": "Sparse", "weight": 5}, {"source": "Geometry", "target": "Reasoning", "weight": 17}, {"source": "Geometry", "target": "Vision-Language", "weight": 9}, {"source": "Detection", "target": "Forgery/Deepfake", "weight": 18}, {"source": "Distillation", "target": "Generation", "weight": 11}, {"source": "Autoregressive", "target": "Efficient", "weight": 5}, {"source": "Generation", "target": "LLM", "weight": 7}, {"source": "LLM", "target": "Motion", "weight": 5}, {"source": "3D", "target": "Hand", "weight": 11}, {"source": "Hand", "target": "Video", "weight": 6}, {"source": "3D", "target": "Medical", "weight": 8}, {"source": "Generalization", "target": "Medical", "weight": 5}, {"source": "Gaussian Splatting", "target": "Segmentation", "weight": 7}, {"source": "Grounding", "target": "Segmentation", "weight": 13}, {"source": "Human", "target": "Multimodal", "weight": 9}, {"source": "Navigation", "target": "Remote Sensing", "weight": 6}, {"source": "Camera", "target": "Event Camera", "weight": 7}, {"source": "3D", "target": "Motion", "weight": 20}, {"source": "Generation", "target": "Robustness", "weight": 8}, {"source": "3D", "target": "Grounding", "weight": 14}, {"source": "Geometry", "target": "Grounding", "weight": 5}, {"source": "3D", "target": "Point Cloud", "weight": 15}, {"source": "Geometry", "target": "Multi-View", "weight": 7}, {"source": "Segmentation", "target": "Vision-Language", "weight": 5}, {"source": "Video", "target": "Vision-Language", "weight": 10}, {"source": "Generation", "target": "Restoration", "weight": 5}, {"source": "Generation", "target": "Zero-Shot", "weight": 7}, {"source": "Efficient", "target": "Multimodal", "weight": 13}, {"source": "Agent", "target": "Reinforcement Learning", "weight": 8}, {"source": "Agent", "target": "Video", "weight": 17}, {"source": "Efficient", "target": "Reinforcement Learning", "weight": 6}, {"source": "Reinforcement Learning", "target": "Video", "weight": 14}, {"source": "Generation", "target": "Mesh", "weight": 9}, {"source": "Motion", "target": "Multimodal", "weight": 6}, {"source": "3D", "target": "Implicit/Neural Field", "weight": 8}, {"source": "Generation", "target": "Implicit/Neural Field", "weight": 5}, {"source": "Anomaly", "target": "Zero-Shot", "weight": 10}, {"source": "Detection", "target": "Zero-Shot", "weight": 13}, {"source": "Camera", "target": "Generation", "weight": 8}, {"source": "Diffusion", "target": "Multi-View", "weight": 7}, {"source": "Detection", "target": "Transformer", "weight": 7}, {"source": "Multimodal", "target": "Retrieval", "weight": 8}, {"source": "Anomaly", "target": "Multimodal", "weight": 8}, {"source": "Dataset", "target": "Detection", "weight": 6}, {"source": "Detection", "target": "Efficient", "weight": 7}, {"source": "Detection", "target": "Open-Vocabulary", "weight": 15}, {"source": "Efficient", "target": "Vision-Language", "weight": 20}, {"source": "Diffusion", "target": "Image Generation", "weight": 9}, {"source": "Benchmark", "target": "Reasoning", "weight": 17}, {"source": "3D", "target": "Self-Supervised", "weight": 7}, {"source": "3D", "target": "Zero-Shot", "weight": 10}, {"source": "Matching", "target": "Multi-View", "weight": 5}, {"source": "Matching", "target": "Zero-Shot", "weight": 6}, {"source": "Detection", "target": "Diffusion", "weight": 7}, {"source": "Attention", "target": "Efficient", "weight": 14}, {"source": "Attention", "target": "Diffusion", "weight": 9}, {"source": "Attention", "target": "Sparse", "weight": 9}, {"source": "Attention", "target": "Transformer", "weight": 10}, {"source": "Trajectory", "target": "Video", "weight": 10}, {"source": "Diffusion", "target": "Face", "weight": 7}, {"source": "Robustness", "target": "Vision-Language", "weight": 10}, {"source": "Agent", "target": "Generation", "weight": 8}, {"source": "Flow Matching", "target": "Matching", "weight": 29}, {"source": "Diffusion", "target": "Restoration", "weight": 10}, {"source": "Segmentation", "target": "Weakly-Supervised", "weight": 7}, {"source": "Grounding", "target": "Multimodal", "weight": 11}, {"source": "Geometry", "target": "Multimodal", "weight": 7}, {"source": "Geometry", "target": "Motion", "weight": 6}, {"source": "Grounding", "target": "Reasoning", "weight": 7}, {"source": "Medical", "target": "Reasoning", "weight": 10}, {"source": "Reasoning", "target": "Segmentation", "weight": 12}, {"source": "Attention", "target": "Generation", "weight": 7}, {"source": "Benchmark", "target": "Generation", "weight": 18}, {"source": "Generation", "target": "Prompt", "weight": 11}, {"source": "Distillation", "target": "Vision-Language", "weight": 6}, {"source": "Editing", "target": "Video", "weight": 22}, {"source": "Editing", "target": "Motion", "weight": 7}, {"source": "Generation", "target": "Optimization", "weight": 21}, {"source": "Mamba/SSM", "target": "Video", "weight": 6}, {"source": "Generalization", "target": "Generation", "weight": 7}, {"source": "Autonomous Driving", "target": "Trajectory", "weight": 5}, {"source": "Autoregressive", "target": "Image Generation", "weight": 5}, {"source": "Gaussian Splatting", "target": "Motion", "weight": 7}, {"source": "Motion", "target": "Restoration", "weight": 6}, {"source": "Detection", "target": "Vision-Language", "weight": 13}, {"source": "Retrieval", "target": "Video", "weight": 8}, {"source": "3D", "target": "Transformer", "weight": 8}, {"source": "Geometry", "target": "Transformer", "weight": 12}, {"source": "Geometry", "target": "Segmentation", "weight": 10}, {"source": "Point Cloud", "target": "Segmentation", "weight": 6}, {"source": "Embodied", "target": "Navigation", "weight": 5}, {"source": "Generation", "target": "Material/Lighting", "weight": 7}, {"source": "Diffusion", "target": "Optimization", "weight": 8}, {"source": "Reasoning", "target": "VQA", "weight": 5}, {"source": "Generalization", "target": "Reasoning", "weight": 5}, {"source": "Few-Shot", "target": "Generation", "weight": 5}, {"source": "Editing", "target": "Vision-Language", "weight": 5}, {"source": "Dataset", "target": "Diffusion", "weight": 6}, {"source": "Dataset", "target": "Distillation", "weight": 14}, {"source": "Depth", "target": "Efficient", "weight": 5}, {"source": "Agent", "target": "Reasoning", "weight": 14}, {"source": "Flow Matching", "target": "Generation", "weight": 13}, {"source": "Generation", "target": "Matching", "weight": 14}, {"source": "Matching", "target": "Multimodal", "weight": 5}, {"source": "3D", "target": "Foundation Model", "weight": 9}, {"source": "Generation", "target": "Vision-Language", "weight": 11}, {"source": "Benchmark", "target": "Human", "weight": 6}, {"source": "Efficient", "target": "LLM", "weight": 6}, {"source": "3D", "target": "Anomaly", "weight": 7}, {"source": "Detection", "target": "Geometry", "weight": 7}, {"source": "Geometry", "target": "Video", "weight": 9}, {"source": "Video", "target": "World Model", "weight": 7}, {"source": "Grounding", "target": "Vision-Language", "weight": 7}, {"source": "Detection", "target": "Generation", "weight": 7}, {"source": "Detection", "target": "Prompt", "weight": 12}, {"source": "Generation", "target": "Open-Vocabulary", "weight": 7}, {"source": "Open-Vocabulary", "target": "Prompt", "weight": 8}, {"source": "Grounding", "target": "Video", "weight": 18}, {"source": "Human", "target": "Pose Estimation", "weight": 10}, {"source": "Grounding", "target": "LLM", "weight": 7}, {"source": "Detection", "target": "Robustness", "weight": 11}, {"source": "Stereo", "target": "Video", "weight": 5}, {"source": "Multi-View", "target": "Sparse", "weight": 5}, {"source": "Multi-View", "target": "Transformer", "weight": 6}, {"source": "Prompt", "target": "Zero-Shot", "weight": 5}, {"source": "Captioning", "target": "Video", "weight": 6}, {"source": "Compression", "target": "Diffusion", "weight": 6}, {"source": "Agent", "target": "Benchmark", "weight": 5}, {"source": "Agent", "target": "Multimodal", "weight": 10}, {"source": "Detection", "target": "Unsupervised", "weight": 5}, {"source": "Efficient", "target": "Reasoning", "weight": 15}, {"source": "Sparse", "target": "Vision-Language", "weight": 11}, {"source": "Dataset", "target": "Video", "weight": 14}, {"source": "VQA", "target": "Video", "weight": 5}, {"source": "Classification", "target": "Few-Shot", "weight": 7}, {"source": "Agent", "target": "Embodied", "weight": 7}, {"source": "Attention", "target": "Vision-Language", "weight": 5}, {"source": "Distillation", "target": "Video", "weight": 10}, {"source": "Few-Shot", "target": "Segmentation", "weight": 5}, {"source": "Detection", "target": "Generalization", "weight": 10}, {"source": "Generalization", "target": "Multimodal", "weight": 5}, {"source": "Generation", "target": "Segmentation", "weight": 10}, {"source": "3D", "target": "Avatar", "weight": 7}, {"source": "3D", "target": "Distillation", "weight": 5}, {"source": "Pose Estimation", "target": "Sparse", "weight": 5}, {"source": "Distillation", "target": "Matching", "weight": 7}, {"source": "Efficient", "target": "Segmentation", "weight": 8}, {"source": "Forgery/Deepfake", "target": "Robustness", "weight": 13}, {"source": "Continual Learning", "target": "Multimodal", "weight": 8}, {"source": "Mamba/SSM", "target": "Segmentation", "weight": 5}, {"source": "Editing", "target": "Generalization", "weight": 6}, {"source": "Generalization", "target": "Segmentation", "weight": 8}, {"source": "3D", "target": "Diffusion", "weight": 19}, {"source": "Generation", "target": "Rendering", "weight": 5}, {"source": "Adversarial", "target": "Generation", "weight": 5}, {"source": "Restoration", "target": "Video", "weight": 9}, {"source": "Embodied", "target": "Reasoning", "weight": 5}, {"source": "Medical", "target": "Multimodal", "weight": 10}, {"source": "Diffusion", "target": "Matching", "weight": 5}, {"source": "Efficient", "target": "Geometry", "weight": 9}, {"source": "Sparse", "target": "Video", "weight": 7}, {"source": "Medical", "target": "Vision-Language", "weight": 11}, {"source": "Editing", "target": "Optimization", "weight": 5}, {"source": "Generation", "target": "Medical", "weight": 12}, {"source": "Efficient", "target": "Matching", "weight": 6}, {"source": "Generation", "target": "Hand", "weight": 9}, {"source": "Super-Resolution", "target": "Video", "weight": 10}, {"source": "Gaussian Splatting", "target": "Generation", "weight": 8}, {"source": "Unsupervised", "target": "Video", "weight": 5}, {"source": "Matching", "target": "Stereo", "weight": 6}, {"source": "Autonomous Driving", "target": "Generation", "weight": 6}, {"source": "Autonomous Driving", "target": "World Model", "weight": 6}, {"source": "Benchmark", "target": "Remote Sensing", "weight": 5}, {"source": "Flow Matching", "target": "Motion", "weight": 5}, {"source": "Matching", "target": "Motion", "weight": 6}, {"source": "Efficient", "target": "Medical", "weight": 5}, {"source": "Detection", "target": "Human", "weight": 8}, {"source": "Dataset", "target": "Human", "weight": 6}, {"source": "Classification", "target": "Generation", "weight": 5}, {"source": "Generation", "target": "Trajectory", "weight": 13}, {"source": "Anomaly", "target": "Weakly-Supervised", "weight": 5}, {"source": "Detection", "target": "Weakly-Supervised", "weight": 7}, {"source": "Video", "target": "Weakly-Supervised", "weight": 6}, {"source": "Prompt", "target": "Video", "weight": 6}, {"source": "3D", "target": "Embodied", "weight": 6}, {"source": "Agent", "target": "Optimization", "weight": 5}, {"source": "Distillation", "target": "Efficient", "weight": 8}, {"source": "Face", "target": "Generation", "weight": 9}, {"source": "Navigation", "target": "Vision-Language", "weight": 10}, {"source": "Generation", "target": "In-Context", "weight": 5}, {"source": "Dataset", "target": "Generation", "weight": 11}, {"source": "Restoration", "target": "Self-Supervised", "weight": 6}, {"source": "Detection", "target": "Segmentation", "weight": 5}, {"source": "Navigation", "target": "Reasoning", "weight": 9}, {"source": "Diffusion", "target": "Retrieval", "weight": 5}, {"source": "Pose Estimation", "target": "Robustness", "weight": 5}, {"source": "Motion", "target": "Reasoning", "weight": 5}, {"source": "CLIP", "target": "Detection", "weight": 5}, {"source": "Generation", "target": "Test-Time", "weight": 5}, {"source": "Tracking", "target": "Transformer", "weight": 5}, {"source": "Generation", "target": "Sparse", "weight": 5}, {"source": "Diffusion", "target": "Generalization", "weight": 8}, {"source": "Diffusion", "target": "Medical", "weight": 7}, {"source": "Diffusion", "target": "Segmentation", "weight": 5}, {"source": "3D", "target": "Material/Lighting", "weight": 5}, {"source": "Depth", "target": "Segmentation", "weight": 5}, {"source": "Detection", "target": "Few-Shot", "weight": 8}, {"source": "Diffusion", "target": "Editing", "weight": 8}, {"source": "Efficient", "target": "Optimization", "weight": 5}, {"source": "Generalization", "target": "Prompt", "weight": 5}, {"source": "Generalization", "target": "Vision-Language", "weight": 5}, {"source": "Agent", "target": "LLM", "weight": 5}, {"source": "LLM", "target": "Optimization", "weight": 5}, {"source": "Optimization", "target": "Text-to-Image", "weight": 5}], "legend": [{"community": 0, "top": ["Detection", "Segmentation", "Robustness", "Generalization"], "size": 27}, {"community": 1, "top": ["Generation", "Video", "Motion", "Human"], "size": 22}, {"community": 2, "top": ["3D", "Geometry", "Gaussian Splatting", "Sparse"], "size": 14}, {"community": 3, "top": ["Multimodal", "Vision-Language", "Reasoning", "Benchmark"], "size": 14}, {"community": 4, "top": ["Diffusion", "Efficient", "Transformer", "Distillation"], "size": 9}, {"community": 5, "top": ["Matching", "Flow Matching", "Stereo"], "size": 3}]}