Multimodal Machine Learning Reading Group
This reading group focuses on recent papers on machine learning methods, including deep neural networks, to represent and integrate multimodal data. We read recently published papers from venues such as NIPS, ICLR, CVPR, ACL, ICML and ICCV conferences. Below are the list of papers and corresponding meeting dates.
Fall 2019 – Wednesday 4-5 pm, GHC 7501
- February 6 (Amir & Paul)
Tied Transformers: Neural Machine Translation with Shared Encoder and Decoder [Presentation Slides]
MEAL: Multi-Model Ensemble via Adversarial Learning [Presentation Slides]
- February 20 (Ying & Yao Chong)
Neural Motifs: Scene Graph Parsing with Global Context. [Presentation Slides]
Do Neural Network Cross-Modal Mappings Really Bridge Modalities? [Presentation Slides]
- March 6 (Zhun & Sai Krishna)
A probabilistic framework for multi-view feature learning with many-to-many associations via neural networks [Presentation Slides]
The Multi-Entity Variational Autoencoder [Presentation Slides]
Jointly Discovering Visual Objects and Spoken Words from Raw Sensory Input [Presentation Slides]
Unsupervised Learning of Spoken Language with Visual Context [Presentation Slides]
- March 20 (Volkan & Meng Xiong)
Grounded Video Description [Presentation Slides]
Show, Control and Tell: A Framework for Generating Controllable and Grounded Captions [Presentation Slides]
- April 3 (Chaitanya & Yongxin)
Neural Ordinary Differential Equations [Presentation Slides]
Look, Imagine and Match: Improving Textual-Visual Cross-Modal Retrieval With Generative Models [Presentation Slides]
- April 17 (Vasu & Hubert)
Branch-Activated Multi-Domain Convolutional Neural Network for Visual Tracking [Presentation Slides]
Universal Transformer [Presentation Slides]
Spring 2018
- Yeh, Raymond, et al. “Interpretable and Globally Optimal Prediction for Textual Grounding using Image Concepts.” Advances in Neural Information Processing Systems , 1/26
- “SoundNet: Learning Sound Representations from Unlabeled Video” – Aytar et. al. , 2/9
- “Inferring Semantic Layout for Hierarchical Text-to-Image Synthesis” – Hong et. al. , 2/23
- “Localizing Moments in Video with Natural Language” – Hendricks et. al. , 3/9
- Das, Kottur, Moura, Lee and Batra, Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning , 3/23
- Lu et al., Neural Baby Talk , 4/9