Scene Understanding

Place Recognition with ConvNet Landmarks: Viewpoint-Robust, Condition-Robust, Training-Free RSS 2015 Predicting Good Features for Image Geo-Localization Using Per-Bundle VLAD ICCV 2015 Recognize Complex Events From Static Images by Fusing Deep Channels CVPR 2015 Revisiting Kernelized Locality-Sensitive Hashing for Improved Large-Scale Image Retrieval CVPR 2015 Robust Manhattan Frame Estimation From a Single RGB-D Image CVPR 2015 SALICON: Saliency in Context CVPR 2015 Saliency Propagation From Simple to Difficult CVPR 2015 Saliency, Scale and Information: Towards a Unifying Theory NeurIPS 2015 Salient Object Subitizing CVPR 2015 Scene Classification With Semantic Fisher Vectors CVPR 2015 Scene Labeling With LSTM Recurrent Neural Networks CVPR 2015 Semantic Segmentation of RGBD Images With Mutex Constraints ICCV 2015 Separating Objects and Clutter in Indoor Scenes CVPR 2015 Single Image 3D Without a Single 3D Image ICCV 2015 Social Saliency Prediction CVPR 2015 Structured Indoor Modeling ICCV 2015 SUN RGB-D: A RGB-D Scene Understanding Benchmark Suite CVPR 2015 Synthesizing Illumination Mosaics From Internet Photo-Collections ICCV 2015 Temporally Coherent Interpretations for Long Videos Using Pattern Theory CVPR 2015 Time-to-Contact From Image Intensity CVPR 2015 Traditional Saliency Reloaded: A Good Old Model in New Shape CVPR 2015 Understanding Image Structure via Hierarchical Shape Parsing CVPR 2015 Understanding Image Virality CVPR 2015 Understanding Pedestrian Behaviors From Stationary Crowd Groups CVPR 2015 Unifying Local Consistency and MAX SAT Relaxations for Scalable Inference with Rounding Guarantees AISTATS 2015