Computer Vision

The Lovász-Softmax Loss: A Tractable Surrogate for the Optimization of the Intersection-Over-Union Measure in Neural Networks CVPR 2018 Theoretical Analysis of Image-to-Image Translation with Adversarial Learning ICML 2018 The Perception-Distortion Tradeoff CVPR 2018 The Power of Ensembles for Active Learning in Image Classification CVPR 2018 The Unreasonable Effectiveness of Deep Features as a Perceptual Metric CVPR 2018 Think Visually: Question Answering through Virtual Imagery ACL 2018 Thoracic Disease Identification and Localization With Limited Supervision CVPR 2018 Through-Wall Human Pose Estimation Using Radio Signals CVPR 2018 TieNet: Text-Image Embedding Network for Common Thorax Disease Classification and Reporting in Chest X-Rays CVPR 2018 Time-Resolved Light Transport Decomposition for Thermal Photometric Stereo CVPR 2018 Toddler-Inspired Visual Object Learning NeurIPS 2018 TOM-Net: Learning Transparent Object Matting From a Single Image CVPR 2018 Tongue Segmentation with Geometrically Constrained Snake Model Interspeech 2018 Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodies CVPR 2018 Toward Designing Convergent Deep Operator Splitting Methods for Task-specific Nonconvex Optimization IJCAI 2018 Toward Driving Scene Understanding: A Dataset for Learning Driver Behavior and Causal Reasoning CVPR 2018 Towards Automatic Speech Identification from Vocal Tract Shape Dynamics in Real-time MRI Interspeech 2018 Towards Battery-Free HD Video Streaming NSDI 2018 Towards Dense Object Tracking in a 2D Honeybee Hive CVPR 2018 Towards Effective Low-Bitwidth Convolutional Neural Networks CVPR 2018 Towards Faster Training of Global Covariance Pooling Networks by Iterative Matrix Square Root Normalization CVPR 2018 Towards Generalized and Efficient Metric Learning on Riemannian Manifold IJCAI 2018 Towards High Performance Video Object Detection CVPR 2018 Towards Human-Machine Cooperation: Self-Supervised Sample Mining for Object Detection CVPR 2018 Towards Open-Set Identity Preserving Face Synthesis CVPR 2018