Monday, September 9, 2018 | 10:00 AM | 1A
From Face Recognition to Models of Identity: A Bayesian Approach to Learning about Unknown Identities from Unsupervised Data (opens in new tab)
Daniel Castro, Sebastian Nowozin
DeepPhys: Video-Based Physiological Measurement Using Convolutional Attention Networks (opens in new tab)
Weixuan Chen, Daniel McDuff
Semantic Match Consistency for Long-Term Visual Localization (opens in new tab)
Carl Toft, Erik Stenborg, Lars Hammarstrand, Lucas Brynte, Marc Pollefeys, Torsten Sattler, Fredrik Kahl
Monday, September 9, 2018 | 4:00 PM | 1B
Stacked Cross Attention for Image-Text Matching
Kuang-Huei Lee, Xi Chen, Gang Hua, Houdong Hu, Xiaodong He
Affinity Derivation and Graph Merge for Instance Segmentation (opens in new tab)
Yiding Liu, Siyu Yang, Bin Li, Wengang Zhou, Ji-Zheng Xu, Houqiang Li, Yan Lu
Online Dictionary Learning for Approximate Archetypal Analysis
Jieru Mei, Chunyu Wang, Wenjun Zeng
VSO: Visual Semantic Odometry (opens in new tab)
Konstantinos-Nektarios Lianos, Johannes Schönberger, Marc Pollefeys, Torsten Sattler
Improved Structure from Motion Using Fiducial Marker Matching (opens in new tab)
Joseph DeGol, Timothy Bretl, Derek Hoiem
Tuesday, September 10, 2018 | 10:00 AM | 2A
Semi-supervised FusedGAN for Conditional Image Generation (opens in new tab)
Navaneeth Bodla, Gang Hua, Rama Chellappa
Integral Human Pose Regression (opens in new tab)
Xiao Sun, Bin Xiao, Fangyin Wei, Shuang Liang, Yichen Wei
Recurrent Tubelet Proposal and Recognition Networks for Action Detection (opens in new tab)
Dong Li, Zhaofan Qiu, Qi Dai, Ting Yao, Tao Mei
Reinforced Temporal Attention and Split-Rate Transfer for Depth-Based Person Re-identification (opens in new tab)
Nikolaos Karianakis, Zicheng Liu, Yinpeng Chen, Stefano Soatto
Simple Baselines for Human Pose Estimation and Tracking (opens in new tab)
Bin Xiao, Haiping Wu, Yichen Wei
Tuesday, September 10, 2018 | 4:00 PM | 2B
Optimized Quantization for Highly Accurate and Compact DNNs (opens in new tab)
Dongqing Zhang, Jiaolong Yang, Dongqiangzi Ye, Gang Hua
Improving Embedding Generalization via Scalable Neighborhood Component Analysis (opens in new tab)
Zhirong Wu, Alexei Efros, Stella Yu
Wednesday, September 11, 2018 | 10:00 AM | 3A
“Factual” or “Emotional”: Stylized Image Captioning with Adaptive Learning and Attention (opens in new tab)
Tianlang Chen, Zhongping Zhang, Quanzeng You, Chen Fang, Zhaowen Wang, Hailin Jin, Jiebo Luo
Adding Attentiveness to the Neurons in Recurrent Neural Networks
Pengfei Zhang, Jianru Xue, Cuiling Lan, Wenjun Zeng, Zhanning Gao, Nanning Zheng
Deep Directional Statistics: Pose Estimation with Uncertainty Quantification (opens in new tab)
Sergey Prokudin, Sebastian Nowozin, Peter Gehler
Faces as Lighting Probes via Unsupervised Deep Highlight Extraction (opens in new tab)
Renjiao Yi, Chenyang Zhu, Ping Tan, Stephen Lin
A Dataset of Flash and Ambient Illumination Pairs from the Crowd (opens in new tab)
Yagiz Aksoy, Changil Kim, Petr Kellnhofer, Sylvain Paris, Mohamed A. Elghareb, Marc Pollefeys, Wojciech Matusik
Wednesday, September 11, 2018 | 2:30 PM | 3B
Deep Attention Neural Tensor Network for Visual Question Answering (opens in new tab)
Yalong Bai, Jianlong Fu, Tao Mei
Learning Region Features for Object Detection (opens in new tab)
Jiayuan Gu, Han Hu, Liwei Wang, Yichen Wei, Jifeng Dai
Video Object Segmentation by Learning Location-Sensitive Embeddings (opens in new tab)
Hai Ci, Chunyu Wang, Yizhou Wang
Learning Priors for Semantic 3D Reconstruction (opens in new tab)
Ian Cherabier, Johannes Schönberger, Martin R. Oswald, Marc Pollefeys, Andreas Geiger
Thursday, September 12, 2018 | 10:00 AM | 4A
Exploring Visual Relationship for Image Captioning (opens in new tab)
Ting Yao, Yingwei Pan, Yehao Li, Tao Mei
Learning to Learn Parameterized Image Operators (opens in new tab)
Qingnan Fan, Dongdong Chen, Lu Yuan, Gang Hua, Nenghai Yu, Baoquan Chen
Learning to Fuse Proposals from Multiple Scanline Optimizations in Semi-Global Matching
Johannes Schoenberger, Sudipta Sinha, Marc Pollefeys
Part-Aligned Bilinear Representations for Person Re-Identification (opens in new tab)
Yumin Suh, Jingdong Wang, Kyoung Mu Lee
Thursday, September 12, 2018 | 4:00PM | 4B
Hierarchical Metric Learning and Matching for 2D and 3D Geometric Correspondences (opens in new tab)
Mohammed Fathy, Quoc-Huy Tran, Zeeshan Zia, Paul Vernaza, Manmohan Chandraker
Learn-to-Score: Efficient 3D Scene Exploration by Predicting View Utility
Benjamin Hepp, Debadeepta Dey, Sudipta Sinha, Ashish Kapoor, Neel Joshi, Otmar Hilliges
AutoLoc: Weakly-supervised Temporal Action Localization in Untrimmed Videos (opens in new tab)
Zheng Shou, Hang Gao, Lei Zhang, Kazuyuki Miyazawa, Shih-Fu Chang