Helping Watson see – so you can see more

IBM Research is a leading player in the quest to give AI systems sight. We’re enabling Watson, IBM's AI platform, to interpret visual content as easily as it does text. With over 1 billion people on track to interact with Watson by the end of 2017, it’s essential that IBM, its partners and the community enable it to see as much as possible. The goal is to give us all even more insight to augment our innate abilities.

Featured Papers at CVPR 2017

S3Pool: Pooling With Stochastic Spatial Sampling
Shuangfei Zhai, Hui Wu, Abhishek Kumar, Yu Cheng, Yongxi Lu, Zhongfei Zhang, Rogerio Feris

Read paper

A Low Power, Fully Event-Based Gesture Recognition System
Arnon Amir, Brian Taba, David Berg, Timothy Melano, Jeffrey McKinstry, Carmelo Di Nolfo, Tapan Nayak, Alexander Andreopoulos, Guillaume Garreau, Marcela Mendoza, Jeff Kusnitz, Michael Debole, Steve Esser, Tobi Delbruck, Myron Flickner, Dharmendra Modha

Read paper

Fractal Dimension Invariant Filtering and Its CNN-Based Implementation
Hongteng Xu, Junchi Yan, Nils Persson, Weiyao Lin, Hongyuan Zha

Read paper

Self-critical Sequence Training for Image Captioning
Steven J. Rennie, Etienne Marcheret, Youssef Mroueh, Jarret Ross, Vaibhava Goel

Read paper

Fully-Adaptive Feature Sharing in Multi-Task Networks With Applications in Person Attribute Classification
Yongxi Lu, Abhishek Kumar, Shuangfei Zhai, Yu Cheng, Tara Javidi, Rogerio Feris

Read paper

Fine-Grained Recognition of Thousands of Object Categories With Single-Example Training
Leonid Karlinsky, Joseph Shtok, Yochay Tzur, Asaf Tzadok

Read paper

Personalizing Gesture Recognition Using Hierarchical Bayesian Neural Networks
Ajjen Joshi, Soumya Ghosh, Margrit Betke, Stan Sclaroff, Hanspeter Pfister

Read paper

Automatic Curation of Golf Highlights using Multimodal Excitement Features
Computer Vision in Sports Workshop @CVPR17
Michele Merler, Dhiraj Joshi, Quoc-Bao Nguyen, Stephen Hammer, John Kent, John R. Smith, Rogerio S. Feris

Read paper

Explore career opportunities @ IBM Research