| 2025 | ICML | ReFocus: Visual Editing as a Chain of Thought for Structured Image Understanding. | Xingyu Fu, Minqian Liu, Zhengyuan Yang, John Corring, Yijuan Lu, Jianwei Yang, Dan Roth, Dinei A. F. Florncio, Cha Zhang |
| 2023 | AAAI | TrOCR: Transformer-Based Optical Character Recognition with Pre-trained Models. | Minghao Li, Tengchao Lv, Jingye Chen, Lei Cui, Yijuan Lu, Dinei A. F. Florncio, Cha Zhang, Zhoujun Li, Furu Wei |
| 2023 | ACL | From Characters to Words: Hierarchical Pre-trained Language Model for Open-vocabulary Language Understanding. | Li Sun, Florian Luisier, Kayhan Batmanghelich, Dinei A. F. Florncio, Cha Zhang |
| 2023 | ICDAR | Diffusion-Based Document Layout Generation. | Liu He, Yijuan Lu, John Corring, Dinei A. F. Florncio, Cha Zhang |
| 2022 | ACL | XFUND: A Benchmark Dataset for Multilingual Visually Rich Form Understanding. | Yiheng Xu, Tengchao Lv, Lei Cui, Guoxin Wang, Yijuan Lu, Dinei A. F. Florncio, Cha Zhang, Furu Wei |
| 2022 | IJCNLP | A Simple yet Effective Learnable Positional Encoding Method for Improving Document Transformer Model. | Guoxin Wang, Yijuan Lu, Lei Cui, Tengchao Lv, Dinei A. F. Florncio, Cha Zhang |
| 2021 | ACL | LayoutLMv2: Multi-modal Pre-training for Visually-rich Document Understanding. | Yang Xu, Yiheng Xu, Tengchao Lv, Lei Cui, Furu Wei, Guoxin Wang, Yijuan Lu, Dinei A. F. Florncio, Cha Zhang, Wanxiang Che, Min Zhang, Lidong Zhou |
| 2019 | CVPR | RePr: Improved Training of Convolutional Filters. | Aaditya Prakash, James A. Storer, Dinei A. F. Florncio, Cha Zhang |
| 2018 | ICASSP | Deep Learning Based Speech Beamforming. | Kaizhi Qian, Yang Zhang, Shiyu Chang, Xuesong Yang, Dinei A. F. Florncio, Mark Hasegawa-Johnson |
| 2017 | ICIP | Foreground detection in camouflaged scenes. | Shuai Li, Dinei A. F. Florncio, Yaqin Zhao, Chris Cook, Wanqing Li |
| 2017 | ICIP | Progressive graph-signal sampling and encoding for static 3D geometry representation. | Mingyuan Zhao, Gene Cheung, Dinei A. F. Florncio, Xiangyang Ji |
| 2016 | ICIP | Joint denoising / compression of image contours via geometric prior and variable-length context tree. | Amin Zheng, Gene Cheung, Dinei A. F. Florncio |
| 2016 | Interspeech | Speech Enhancement in Multiple-Noise Conditions Using Deep Neural Networks. | Anurag Kumar, Dinei A. F. Florncio |
| 2015 | ICASSP | Maximum a posteriori estimation of room impulse responses. | Dinei A. F. Florncio, Zhengyou Zhang |
| 2014 | ICIP | Image bit-depth enhancement via maximum-a-posteriori estimation of graph AC component. | Pengfei Wan, Gene Cheung, Dinei A. F. Florncio, Cha Zhang, Oscar C. Au |
| 2014 | ICIP | Point cloud attribute compression with graph transform. | Cha Zhang, Dinei A. F. Florncio, Charles T. Loop |
| 2013 | ICRA | Autonomous person following for telepresence robots. | Akansel Cosgun, Dinei A. F. Florncio, Henrik I. Christensen |
| 2013 | IROS | Learning how to increase the chance of human-robot engagement. | Douglas G. Macharet, Dinei A. F. Florncio |
| 2012 | ICIP | Arithmetic edge coding for arbitrarily shaped sub-block motion prediction in depth video compression. | Ismal Daribo, Gene Cheung, Dinei A. F. Florncio |
| 2012 | IROS | A collaborative control system for telepresence robots. | Douglas G. Macharet, Dinei A. F. Florncio |
| 2012 | MMSP | Auditory augmented reality: Object sonification for the visually impaired. | Flavio P. Ribeiro, Dinei A. F. Florncio, Philip A. Chou, Zhengyou Zhang |
| 2012 | PCS | Arbitrarily shaped sub-block motion prediction in texture map compression using depth information. | Ismal Daribo, Dinei A. F. Florncio, Gene Cheung |
| 2011 | ICASSP | CROWDMOS: An approach for crowdsourcing mean opinion score studies. | Flavio P. Ribeiro, Dinei A. F. Florncio, Cha Zhang, Michael L. Seltzer |
| 2011 | ICIP | Crowdsourcing subjective image quality evaluation. | Flavio P. Ribeiro, Dinei A. F. Florncio, Vtor H. Nascimento |
| 2011 | ISCAS | Enhanced adaptive playout scheduling and loss concealment techniques for Voice over IP networks. | Dinei A. F. Florncio, Li-wei He |
| 2011 | MMSP | Region of interest determination using human computation. | Flavio P. Ribeiro, Dinei A. F. Florncio |
| 2010 | ICASSP | L1 regularized room modeling with compact microphone arrays. | Demba E. Ba, Flavio P. Ribeiro, Cha Zhang, Dinei A. F. Florncio |
| 2010 | MMSP | Enhancing loudspeaker-based 3D audio with room modeling. | Myung-Suk Song, Cha Zhang, Dinei A. F. Florncio, Hong-Goo Kang |
| 2010 | SOUPS | Where do security policies come from? | Dinei A. F. Florncio, Cormac Herley |
| 2009 | ICASSP | Multiview video compression and streaming based on predicted viewer position. | Dinei A. F. Florncio, Cha Zhang |
| 2009 | ICASSP | Background recovery from video sequences using motion parameters. | Srenivas Varadarajan, Lina J. Karam, Dinei A. F. Florncio |
| 2009 | MMSP | Improving depth perception with motion parallax and its application in teleconferencing. | Cha Zhang, Zhaozheng Yin, Dinei A. F. Florncio |
| 2008 | ICASSP | Why does PHAT work well in lownoise, reverberative environments? | Cha Zhang, Dinei A. F. Florncio, Zhengyou Zhang |
| 2008 | NSPW | A profitless endeavor: phishing as tragedy of the commons. | Cormac Herley, Dinei A. F. Florncio |
| 2008 | SEC | Protecting Financial Institutions from Brute-Force Attacks. | Cormac Herley, Dinei A. F. Florncio |
| 2007 | ICASSP | Maximum Likelihood Sound Source Localization for Multiple Directional Microphones. | Cha Zhang, Zhengyou Zhang, Dinei A. F. Florncio |
| 2007 | WWW | A large-scale study of web password habits. | Dinei A. F. Florncio, Cormac Herley |
| 2006 | ACSAC | KLASSP: Entering Passwords on a Spyware Infected Machine Using a Shared-Secret Proxy. | Dinei A. F. Florncio, Cormac Herley |
| 2006 | MMSP | Is IEEE 802.11 ready for VoIP? | Arlindo F. da Conceio, Jin Li, Dinei A. F. Florncio, Fabio Kon |
| 2006 | SEC | Analysis and Improvement of Anti-Phishing Schemes. | Dinei A. F. Florncio, Cormac Herley |
| 2005 | ICASSP | Sound source localization for circular arrays of directional microphones. | Yong Rui, Dinei A. F. Florncio, Warren Lam, Jinyan Su |
| 2005 | ICIP | Image de-noising by selective filtering based on double-shot pictures. | Dinei A. F. Florncio |
| 2004 | ICASSP | Time delay estimation in the presence of correlated noise and reverberation. | Yong Rui, Dinei A. F. Florncio |
| 2003 | DCC | Can the sample being transmitted be used to refine its own PDF estimate? | Dinei A. F. Florncio, Patrice Y. Simard |
| 2002 | ICASSP | An improved spread spectrum technique for robust watermarking. | Henrique S. Malvar, Dinei A. F. Florncio |
| 2001 | ICASSP | Multichannel filtering for optimum noise reduction in microphone arrays. | Dinei A. F. Florncio, Henrique S. Malvar |
| 2001 | ICASSP | Speech dereverberation via maximum-kurtosis subband adaptive filtering. | Bradford W. Gillespie, Henrique S. Malvar, Dinei A. F. Florncio |
| 2001 | ICIP | Motion sensitive pre-processing for video. | Dinei A. F. Florncio |
| 1996 | ICASSP | The motion transform: a new motion compensation technique. | Robert M. Armitano, Dinei A. F. Florncio, Ronald W. Schafer |
| 1996 | ICASSP | Perfect reconstructing nonlinear filter banks. | Dinei A. F. Florncio, Ronald W. Schafer |
| 1996 | ICASSP | A pyramidal coder using a nonlinear filter bank. | Ricardo L. de Queiroz, Dinei A. F. Florncio |
| 1996 | ICIP | Motion transforms for video coding. | Dinei A. F. Florncio, Robert M. Armitano, Ronald W. Schafer |
| 1995 | ICASSP | Post-sampling aliasing control for natural images. | Dinei A. F. Florncio, Ronald W. Schafer |
| 1994 | ICIP | A Non-Expansive Pyramidal Morphological Image Coder. | Dinei A. F. Florncio, Ronald W. Schafer |
| 1994 | ISMM | Critical Morphological Sampling and Its Applications to Image Coding. | Dinei A. F. Florncio, Ronald W. Schafer |
| 1991 | ICASSP | On the use of asymmetric windows for reducing the time delay in real-time spectral analysis. | Dinei A. F. Florncio |