Learning Detection with Diverse Proposals
Comments Accepted to CVPR 2017
作者
Trevor Darrell
Computer Vision
Learning Features by Watching Objects Move
Comments CVPR 2017
Adversarial Feature Learning
Comments Published as a conference paper at ICLR 2017. Changelog: (v7) Table 2 results improved 1-2% due to averaging predictions over 10 crops at test time, as done in Noroozi & Favaro; Table 3 VOC classification results slightly improved due to minor bugfix. (See v6 changelog for previous versions.)
Visual Discovery at Pinterest
Loss is its own Reward: Self-Supervision for Reinforcement Learning
Grounding of Textual Phrases in Images by Reconstruction
Comments published at ECCV 2016 (oral); updated to final version
Adversarial Discriminative Domain Adaptation
FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
Modeling Relationships in Referential Expressions with Compositional Modular Networks
Context Encoders: Feature Learning by Inpainting
Comments New results on ImageNet Generation
Journal ref CVPR 2016
Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding
Comments Accepted to EMNLP 2016
Data-dependent Initializations of Convolutional Neural Networks
Comments ICLR 2016
Learning Modular Neural Network Policies for Multi-Task and Multi-Robot Transfer
Comments Under review at the International Conference on Robotics and Automation (ICRA) 2017
Utilizing Large Scale Vision and Text Datasets for Image Segmentation from Referring Expressions
Clockwork Convnets for Video Semantic Segmentation
Learning to Compose Neural Networks for Question Answering
Long-term Recurrent Convolutional Networks for Visual Recognition and Description
Comments Originally presented at CVPR 2015 (oral). Updated version (accepted as a TPAMI journal article) includes additional results
Fully Convolutional Networks for Semantic Segmentation
Comments to appear in PAMI (accepted May, 2016); journal edition of arXiv:1411.4038
Deep Compositional Captioning: Describing Novel Object Categories without Paired Training Data
End-to-End Training of Deep Visuomotor Policies
Comments updating with revisions for JMLR final version
Deep Learning for Tactile Understanding From Visual and Haptic Data
Comments Camera ready version for ICRA 2016
Compact Bilinear Pooling
Comments Camera ready version for CVPR
Natural Language Object Retrieval
Comments Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016
Generating Visual Explanations
Segmentation from Natural Language Expressions
Auxiliary Image Regularization for Deep CNNs with Noisy Labels
Comments Published as a conference paper at ICLR 2016
Deep Spatial Autoencoders for Visuomotor Learning
Comments Published in the International Conference on Robotics and Automation (ICRA)
Quantification in-the-wild: data-sets and baselines
Comments This report was prsented at the NIPS 2015 workshop on Transfer and Multi-Task Learning: Trends and New Perspectives. It is 4 pages + 1 page of references followed by a 6 page appendix
