Deep Reinforcement Learning in Computer Vision Papers
In recent years, while use of Computer Vision techniques/models has burgeoned for solving Reinforcement Learning task(such as games), the opposite flow, of using techinques/models from Reinforcement Learning to solve paradigms in Computer Vision has also been seen.
The goal is to understand this penetration of RL in many of the application of Computer Vision through research publications in leading conferences.
Index of Papers
[A] Object Detection
1). Caicedo, Juan C., and Svetlana Lazebnik. "Active object localization with deep reinforcement learning." Proceedings of the IEEE International Conference on Computer Vision. 2015.
2). Bellver, Miriam, et al. "Hierarchical object detection with deep reinforcement learning." arXiv preprint arXiv:1611.03718 (2016).
[B] Action Detection
1). Huang, Jingjia, et al. "A Self-Adaptive Proposal Model for Temporal Action Detection based on Reinforcement Learning." arXiv preprint arXiv:1706.07251 (2017).
2). Yeung, Serena, et al. "End-to-end learning of action detection from frame glimpses in videos." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016.
[C] Visual Tracking
1). Yoo, Sangdoo Yun1 Jongwon Choi1 Youngjoon, Kimin Yun, and Jin Young Choi. "Action-Decision Networks for Visual Tracking with Deep Reinforcement Learning".
2). Zhang, Da, Hamid Maei, Xin Wang, and Yuan-Fang Wang. "Deep Reinforcement Learning for Visual Object Tracking in Videos." arXiv preprint arXiv:1701.08936 (2017).
3). Xiang, Yu, Alexandre Alahi, and Silvio Savarese. "Learning to track: Online multi-object tracking by decision making." In Proceedings of the IEEE International Conference on Computer Vision, pp. 4705-4713. 2015.
[D] Pose-Estimation and View-Planning Problem
1). Krull, Alexander, et al. "PoseAgent: Budget-Constrained 6D Object Pose Estimation via Reinforcement Learning." arXiv preprint arXiv:1612.03779 (2016).
2). Kaba, Mustafa Devrim, Mustafa Gokhan Uzunbas, and Ser Nam Lim. "A Reinforcement Learning Approach to the View Planning Problem." arXiv preprint arXiv:1610.06204 (2016).
[E] Natural Language Problems: Dialog Generation
1). Jason D. Williams, Kavosh Asadi, Geoffrey Zweig. Hybrid Code Networks: practical and efficient end-to-end dialog control with supervised and reinforcement learning ACL 2017.
2). Bhuwan Dhingra, Lihong Li, Xiujun Li, Jianfeng Gao, Yun-Nung Chen, Faisal Ahmed, Li Deng. End-to-End Reinforcement Learning of Dialogue Agents for Information Access. arXiv:1609.00777.
3). Jason D. Williams, Geoffrey Zweig. End-to-end LSTM-based dialog control optimized with supervised and reinforcement learning. arXiv:1606.01269.
[F] Natural Language Problems: Information Extraction
1). Karthik Narasimhan, Adam Yala, Regina Barzilay. Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning. EMNLP 2016.
2). Karthik Narasimhan, Tejas Kulkarni and Regina Barzilay. Language Understanding for Text-based Games using Deep Reinforcement Learning. EMNLP2015.
3). S.R.K. Branavan, H. Chen, L. Zettlemoyer and R. Barzilay. Reinforcement Learning for Mapping Instructions to Actions. ACL 2009.
[G] Image Captioning
1).Ren, Zhou, Xiaoyu Wang, Ning Zhang, Xutao Lv, and Li-Jia Li. "Deep Reinforcement Learning-based Image Captioning with Embedding Reward." arXiv preprint arXiv:1704.03899 (2017).