Gerard de Melo's Publications

Publications: Computer Vision/Multimodality

Publications by Topic: All | NLP | Knowledge Graphs | Computer Vision/Multimodality | IR/Social Media | Theory

• OOGAN: Disentangling GAN with One-Hot Sampling and Orthogonal Regularization  BibTeX
  Bingchen Liu, Yizhe Zhu, Zuohui Fu, Gerard de Melo, Ahmed Elgammal (2020)
  In: Proc. AAAI 2020. AAAI Press.
  Acceptance rate: 20.6%
• Long Short-Term Sample Distillation  BibTeX
  Liang Jiang, Zujie Wen, Zhongping Liang, Yafang Wang, Gerard de Melo, Zhe Li, Liangzhuang Ma, Jiaxing Zhang, Xiaolong Li, Yuan Qi (2020)
  In: Proc. AAAI 2020. AAAI Press.
  Acceptance rate: 20.6%
• Scalable Object-Oriented Sequential Generative Models  BibTeX   Website
  Jindong Jiang, Sepehr Janghorbani, Gerard de Melo, Sungjin Ahn (2020)
  In: Proc. ICLR 2020.
  Acceptance rate: 26.5%
• Illustrate Your Story: Enriching Text with Images  BibTeX   Presentation Video
  Sreyasi Nag Chowdhury, William Cheng, Gerard de Melo, Simon Razniewski, Gerhard Weikum (2020)
  In: Proc. WSDM 2020 (Demonstration Paper). ACM.
• Paralinguistic Recommendations for Affective Word Clouds  BibTeX   Presentation Video
  Tugba Kulahcioglu, Gerard de Melo (2019)
  In: Proc. ACM IUI 2019. ACM.
  Acceptance rate: 25%
• CITE: A Corpus Of Text-Image Discourse Relations  BibTeX   Website
  Malihe Alikhani, Sreyasi Nag Chowdhury, Gerard de Melo, Matthew Stone (2019)
  In: Proc. NAACL-HLT 2019 (Short Paper). Association for Computational Linguistics.
  Acceptance rate: 21.3%
• Leveraging Blowing as a Directly Controlled Interface  BibTeX
  Yeqing Chen, Yulong Bian, Chenglei Yang, Xiyu Bao, Yafang Wang, Gerard de Melo (2019)
  In: Proc. IEEE SmartWorld 2019 (Short Paper). IEEE.
• Catch the Shadow: Person Tracking Under Occlusion with a Single RGB-D Camera  BibTeX
  Wei Gai, Meng Qi, Lu Wang, Chenglei Yang, Mingcong Ma, Juan Liu, Yulong Bian, Gerard de Melo, Shijun Liu, Xiangxu Meng (2019)
  In: Proc. IEEE SmartWorld 2019 (Short Paper). IEEE.
• Optimization Strategies for Real-Time Rendering of Virtual Scenes on Heterogeneous Mobile Devices  BibTeX
  Wei Gai, Xiyu Bao, Meng Qi, Yafang Wang, Juan Liu, Gerard de Melo, Lu Wang, Lizhen Cui, Chenglei Yang, Xiangxu Meng (2019)
  In: Proc. IEEE SmartWorld 2019 (Visual Perception and Visual Computing Paper). IEEE.
• Rotbav: A Toolkit for Constructing Mixed Reality Apps with Real-Time Roaming in Large Indoor Physical Spaces  BibTeX
  Huan Xing, Xiyu Bao, Fan Zhang, Wei Gai, Meng Qi, Juan Liu, Yuliang Shi, Gerard de Melo, Chenglei Yang, Xiangxu Meng (2019)
  In: Proc. IEEE VR 2019 (Poster Paper). IEEE.
• Video Captioning with Multi-Faceted Attention  BibTeX
  Xiang Long, Chuang Gan, Gerard de Melo (2018)
  Transactions of the Association for Computational Linguistics (TACL) 6, 2018, p. 173–184.
  Acceptance rate: 19%
• Attention Clusters: Purely Attention Based Local Feature Integration for Video Classification  BibTeX
  Xiang Long, Chuang Gan, Gerard de Melo, Jiajun Wu, Xiao Liu, Shilei Wen (2018)
  In: Proc. CVPR 2018.
  🏆  Backbone of winning solution in ActivityNet 2017 Kinetics Challenge
  Acceptance rate: 29.6%
• Multimodal Keyless Attention Fusion for Video Classification  BibTeX
  Xiang Long, Chuang Gan, Gerard de Melo, Xiao Liu, Yandong Li, Fu Li, Shilei Wen (2018)
  In: Proc. AAAI 2018. AAAI Press.
  🏆  Backbone of 3rd place ($20,000 prize) solution in the Google Cloud & YouTube-8M Video Understanding Challenge
  Acceptance rate: 25%
• Predicting Semantic Signatures of Fonts  BibTeX   Website
  Tugba Kulahcioglu, Gerard de Melo (2018)
  In: Proc. 12th IEEE International Conference on Semantic Computing.
  🏆  Best Paper Nominee
• FontLex: A Typographical Lexicon based on Affective Associations  BibTeX   Website
  Tugba Kulahcioglu, Gerard de Melo (2018)
  In: Proc. 11th Language Resources and Evaluation Conference (LREC 2018). European Language Resources Association (ELRA).
• Multimodal Question Answering over Structured Data with Ambiguous Entities  BibTeX
  Huadong Li, Yafang Wang, Gerard de Melo, Changhe Tu, Baoquan Chen (2017)
  In: Proc. WWW 2017 (Cognitive Computing Track). ACM.
• Concepts Not Alone: Exploring Pairwise Relationships for Zero-Shot Video Activity Recognition  BibTeX
  Chuang Gan, Ming Lin, Yi Yang, Gerard de Melo, Alexander G. Hauptmann (2016)
  In: Proc. AAAI 2016. AAAI Press.
  Acceptance rate: 26%
• ShapeLearner: Towards Shape-Based Visual Knowledge Harvesting  BibTeX   Website
  Huayong Xu, Yafang Wang, Kang Feng, Gerard de Melo, Wei Wu, Andrei Sharf, Baoquan Chen (2016)
  In: Proc. ECAI 2016. IOS Press Frontiers in Artificial Intelligence and Applications.
  Acceptance rate: 27%
• Seeing is Believing: The Quest for Multimodal Knowledge  BibTeX
  Gerard de Melo, Niket Tandon (2016)
  ACM SIGWEB Newsletter Spring 2016, 2016, p. 4:1–4:9. ACM.
• ShapeExplorer: Querying and Exploring Shapes using Visual Knowledge  BibTeX   Website
  Tong Ge, Yafang Wang, Gerard de Melo, Zengguang Hao, Andrei Sharf, Baoquan Chen (2016)
  In: Proc. EDBT 2016 (Demonstration Paper).
• Visualizing and Curating Knowledge Graphs over Time and Space  BibTeX
  Tong Ge, Yafang Wang, Gerard de Melo, Haofeng Li (2016)
  In: Proc. ACL 2016 (Demonstration Paper). ACL.
• Knowlywood: Mining Activity Knowledge from Hollywood Narratives  BibTeX   Website
  Niket Tandon, Gerard de Melo, Abir De, Gerhard Weikum (2015)
  In: Proc. CIKM 2015. ACM.
  Acceptance rate: 18% (KR Track)
• Perceptually Grounded Selectional Preferences  BibTeX   Poster
  Ekaterina Shutova, Niket Tandon, Gerard de Melo (2015)
  In: Proc. ACL 2015.
  Acceptance rate: 25%
• Lights, Camera, Action: Knowledge Extraction from Movie Scripts  BibTeX
  Niket Tandon, Gerard de Melo, Abir De, Gerhard Weikum (2015)
  In: Proc. WWW 2015 (Poster Paper).
  Acceptance rate: 30%
• Providing Multilingual, Multimodal Answers to Lexical Database Queries  BibTeX
  Gerard de Melo, Gerhard Weikum (2010)
  In: Proc. LREC 2010. ELRA.

Further Information

 

Return to Main Page