CVPR 2016 Summary
/
Last week I attended 2016's Computer Vision and Pattern Recognition conference in Las Vegas with my Ditto Labs colleague Arel Cordero. The core threads this year's were visual question & answering, semantic segmentation, and fine-grained classifications and embeddings. The page total of all the papers was over 6k, so I wanted to quickly highlight what we thought were the hottest papers:
Fine-grained Categorization and Dataset Bootstrapping using Deep Metric Learning with Humans in the Loop
Yin Cui, Feng Zhou, Yuanqing Lin, Serge Belongie
http://conferences.computer.org/cvpr/2016/content/papers/8851b153.pdfBilinear CNN Models for Fine-grained Visual Recognition
Tsung-Yu Lin, Aruni RoyChowdhury, Subhransu Maji
http://arxiv.org/pdf/1504.07889v3Fine-Grained Recognition without Part Annotations
Jonathan Krause, Hailin Jin, Jianchao Yang, Li Fei-Fei
http://vision.stanford.edu/pdf/joncvpr15.pdfDeep Metric Learning via Lifted Structured Feature Embedding
Hyun Oh Song, Yu Xiang, Stefanie Jegelka, Silvio Savarese
http://conferences.computer.org/cvpr/2016/content/papers/8851e004.pdfDeep Residual Learning for Image Recognition (ResNet)
Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun
http://conferences.computer.org/cvpr/2016/content/papers/8851a770.pdfInception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
Christian Szegedy, Sergey Ioffe, Vincent Vanhoucke
http://arxiv.org/pdf/1602.07261v1.pdfThe Multiverse Loss for Robust Transfer Learning
Etai Littwin, Lior Wolf
http://conferences.computer.org/cvpr/2016/content/papers/8851d957.pdfTraining Region-Based Object Detectors with Online Hard Example Mining
Abhinav Shrivastava, Abhinav Gupta, Ross Girshick
http://conferences.computer.org/cvpr/2016/content/papers/8851a761.pdfWe Don’t Need No Bounding-Boxes: Training Object Class Detectors Using Only Human Verification
Dim P. Papadopoulos, Jasper R. R. Uijlings, Frank Keller, Vittorio Ferrari
http://conferences.computer.org/cvpr/2016/content/papers/8851a854.pdfEye Tracking for Everyone (GazeCapture)
Kyle Krafka, Aditya Khosla, Petr Kellnhofer, Harini Kannan, Suchendra Bhandarkar, Wojciech Matusik, Antonio Torralba
http://conferences.computer.org/cvpr/2016/content/papers/8851c176.pdfDeepFashion: Powering Robust Clothes Recognition and Retrieval with Rich Annotations
Ziwei Liu, Ping Luo, Shi Qiu, Xiaogang Wang, Xiaoou Tang
http://conferences.computer.org/cvpr/2016/content/papers/8851b096.pdfAnticipating Visual Representations from Unlabeled Video (Learning from unlabeled video)
Carl Vondrick, Hamed Pirsiavash, Antonio Torralba
http://conferences.computer.org/cvpr/2016/content/papers/8851a098.pdfHierarchically Gated Deep Networks for Semantic Segmentation
Guo-Jun Qi
http://conferences.computer.org/cvpr/2016/content/papers/8851c267.pdfXNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks
Mohammad Rastegari, Vicente Ordonez, Joseph Redmon, Ali Farhadi
http://arxiv.org/pdf/1603.05279v3.pdfSynthetic Data for Text Localisation in Natural Images
Ankush Gupta, Andrea Vedaldi, Andrew Zisserman
http://conferences.computer.org/cvpr/2016/content/papers/8851c315.pdfStructural-RNN: Deep Learning on Spatio-Temporal Graphs
Ashesh Jain, Amir R. Zamir, Silvio Savarese, Ashutosh Saxena
http://conferences.computer.org/cvpr/2016/content/papers/8851f308.pdfEmotioNet: An Accurate, Real-Time Algorithm for the Automatic Annotation of a Million Facial Expressions in the Wild
C. Fabian Benitez-Quiroz, Ramprakash Srinivasan, Aleix M. Martinez
http://conferences.computer.org/cvpr/2016/content/papers/8851f562.pdfYou Only Look Once: Unified, Real-Time Object Detection (YOLO)
Joseph Redmon, Santosh Divvala, Ross Girshick, Ali Farhadi
http://arxiv.org/pdf/1506.02640v5ReSeg: A Recurrent Neural Network-based Model for Semantic Segmentation
Francesco Visin, Marco Ciccone, Adriana Romero, Kyle Kastner, Kyunghyun Cho, Yoshua Bengio, Matteo Matteucci, Aaron Courville
http://arxiv.org/pdf/1511.07053v3.pdfLearning with Side Information through Modality Hallucination
Judy Hoffman, Saurabh Gupta, Trevor Darrell
http://conferences.computer.org/cvpr/2016/content/papers/8851a826.pdf