Computer Vision and Multimedia
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.
Computer Vision and Multimedia
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.
Featured Projects
Image Captioning
Oral presentation at CVPR 2017, top entry in MS-COCO Captioning Challenge 2017
Dialog-based Interactive
Image Retrieval
A new learning framework of multi-modal conversational agents
A Low Power, Fully Event-Based Gesture Recognition System
Powered by the first neuromorphic chip
Identifying skin cancer with computer vision
First machine learning system to demonstrate expert-level accuracy on large public dermoscopy dataset
Automatic Curation
of Sports Highlights
Officially used in the Masters, Wimbledon and US Open tournaments
Harnessing A.I. for Augmenting Creativity: Movie Trailer Creation
Best Paper Award, Brave New Ideas at ACM Multimedia 2017
Featured Papers
CVPR 2018 accepted publications
BlockDrop: Dynamic Inference Paths in Residual Networks
Z. Wu, T. Nagarajan, A. Kumar, S. Rennie, L. S. Davis, K. Grauman and R. S. Feris
Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimation
Z. Tang, X. Peng, F. Yang, R. S. Feris and D. Metaxas
Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi- Supervised Semantic Segmentation
Y. Wei, H. Xiao, H. Shi, Z. Jie, J. Feng and T. Huang
Image Super-Resolution via Dual-State Recurrent Networks
H. Wei, S. Chang, D. Liu, M. Yu, M. Witbrock and T. Huang
A Low Power, High Throughput, Fully Event-Based Stereo System
A. Andreopoulos, H. J. Kashyap, T. K. Nayak, A. Amir and M. D. Flickner
NISP: Pruning Networks using Neuron Importance Score Propagation
R. Yu, A. Li, C.-F. Chen, J.-H. Lai, V. Morariu, X. Han, M. Gao, C.-Y. Lin and L. Davis
The Excitement of Sports: Automatic Highlights Using Audio/Visual Cues
M. Merler, D. Joshi, K.-N. C. Mac, Q.-B. Nguyen, J. Kent, S. Hammer, J. Xiong, M. N. Do, J. R. Smith and R. S. Feris
Dialog-based Interactive Image Retrieval
H. Wu, X. Guo, Y. Cheng, S. J. Rennie, G. Tesauro and R. S. Feris
Benchmarks and Workshops
Research Areas
Video Understanding
Extract and interpret salient moments in video based on audio/visual analytics.
Video Understanding
Video Understanding
Extract and interpret salient moments in video based on audio/visual analytics.
Vision & Language
Model the relationship between images and text through captioning and multimodal dialog systems.
Vision & Language
Vision & Language
Model the relationship between images and text through captioning and multimodal dialog systems.
Efficient Visual Analysis
Computer vision operated on neuromorphic, CMOS-integrated circuits.
Efficient Visual Analysis
Efficient Visual Analysis
Computer vision operated on neuromorphic, CMOS-integrated circuits.
Object Detection
Fast and accurate object localization.
Object Detection
Object Detection
Fast and accurate object localization.
Skin Image Analysis
Melanoma recognition in dermoscopy images.
Skin Image Analysis
Skin Image Analysis
Melanoma recognition in dermoscopy images.
Assistive Technology
Computer vision systems to help the visually impaired explore the world.
Assistive Technology
Assistive Technology
Computer vision systems to help the visually impaired explore the world.
Services & APIs
Watson Visual Recognition Service for Core ML.
Services & APIs
Services & APIs
Watson Visual Recognition Service for Core ML.
Visual Learning with Scarce Data
Visual domain adaptation via one or few shot learning.
Visual Learning with Scarce Data
Visual Learning with Scarce Data
Visual domain adaptation via one or few shot learning.
Learn more about IBM’s work in computer vision - including projects in all of these research areas →