Publications
Adapting deep visuomotor representations with weak pairwise constraints.
Workshop on the Algorithmic Foundations of Robotics (WAFR).
(2016). Adversarial Feature Learning.
CoRR. abs/1605.09782,
(2016). Compact Bilinear Pooling.
The IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 317-326.
(2016). Context Encoders: Feature Learning by Inpainting.
The IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2536-2544.
(2016). Cross-modal adaptation for RGB-D detection.
IEEE International Conference on Robotics and Automation (ICRA). 5032-5039.
(2016). Deep Compositional Captioning: Describing Novel Object Categories Without Paired Training Data.
The IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 1-10.
(2016). Deep compositional question answering with neural module networks.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
(2016). Deep learning for tactile understanding from visual and haptic data.
IEEE International Conference on Robotics and Automation (ICRA). 536-543.
(2016). Deep spatial autoencoders for visuomotor learning.
IEEE International Conference on Robotics and Automation (ICRA). 512-519.
(2016). End-to-end training of deep visuomotor policies.
Journal of Machine Learning Research. 17, 1–40.
(2016). Fully Convolutional Networks for Semantic Segmentation.
IEEE Transactions on Pattern Analysis and Machine Intelligence. 39(4), 640-651.
(2016). Large Scale Visual Recognition Through Adaptation Using Joint Representation and Multiple Instance Learning.
J. Mach. Learn. Res.. 17, 4954–4984.
(2016). Learning to Compose Neural Networks for Question Answering.
CoRR. abs/1601.01705,
(2016). Learning to Detect Visual Grasp Affordance.
IEEE Transactions on Automation Science and Engineering. 13(2), 798-809.
(2016). Learning With Side Information Through Modality Hallucination.
The IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 826-834.
(2016). Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding.
CoRR. abs/1606.01847,
(2016). Natural Language Object Retrieval.
The IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
(2016). Neural Module Networks.
The IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 39-48.
(2016). Region-Based Convolutional Networks for Accurate Object Detection and Segmentation.
IEEE Transactions on Pattern Analysis and Machine Intelligence. 38(1), 142-158.
(2016). TSC-DL: Unsupervised trajectory segmentation of multi-modal surgical demonstrations with Deep Learning.
IEEE International Conference on Robotics and Automation (ICRA). 4150-4157.
(2016). Auxiliary Image Regularization for Deep CNNs with Noisy Labels.
CoRR. abs/1511.07069,
(2015). Constrained Convolutional Neural Networks for Weakly Supervised Segmentation.
The IEEE International Conference on Computer Vision (ICCV). 1796-1804.
(2015). Constrained Structured Regression with Convolutional Neural Networks.
CoRR. abs/1511.07497,
(2015). Data-dependent Initializations of Convolutional Neural Networks.
CoRR. abs/1511.06856,
(2015). Deformable Part Models are Convolutional Neural Networks.
The IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 437-446.
(2015).