Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Radu Soricut

COSMic: A Coherence-Aware Generation Metric for Image Descriptions

Sep 11, 2021
Mert İnan, Piyush Sharma, Baber Khalid, Radu Soricut, Matthew Stone, Malihe Alikhani

* 12 pages, 4 figures, Findings of the Association for Computational Linguistics: EMNLP 2021 

  Access Paper or Ask Questions

H-Transformer-1D: Fast One-Dimensional Hierarchical Attention for Sequences

Jul 25, 2021
Zhenhai Zhu, Radu Soricut

* ACL2021 long paper oral presentation 

  Access Paper or Ask Questions

Bridging the Gap Between Practice and PAC-Bayes Theory in Few-Shot Meta-Learning

May 28, 2021
Nan Ding, Xi Chen, Tomer Levinboim, Sebastian Goodman, Radu Soricut

  Access Paper or Ask Questions

2.5D Visual Relationship Detection

Apr 26, 2021
Yu-Chuan Su, Soravit Changpinyo, Xiangning Chen, Sathish Thoppay, Cho-Jui Hsieh, Lior Shapira, Radu Soricut, Hartwig Adam, Matthew Brown, Ming-Hsuan Yang, Boqing Gong

  Access Paper or Ask Questions

Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts

Feb 17, 2021
Soravit Changpinyo, Piyush Sharma, Nan Ding, Radu Soricut

  Access Paper or Ask Questions

Telling the What while Pointing the Where: Fine-grained Mouse Trace and Language Supervision for Improved Image Retrieval

Feb 09, 2021
Soravit Changpinyo, Jordi Pont-Tuset, Vittorio Ferrari, Radu Soricut

  Access Paper or Ask Questions

Understanding Guided Image Captioning Performance across Domains

Dec 04, 2020
Edwin G. Ng, Bo Pang, Piyush Sharma, Radu Soricut

* 13 pages, 7 figures 

  Access Paper or Ask Questions

Improving Text Generation Evaluation with Batch Centering and Tempered Word Mover Distance

Oct 13, 2020
Xi Chen, Nan Ding, Tomer Levinboim, Radu Soricut

* EMNLP 2020 Eval4NLP Workshop 

  Access Paper or Ask Questions

TeaForN: Teacher-Forcing with N-grams

Oct 09, 2020
Sebastian Goodman, Nan Ding, Radu Soricut

* to be published in EMNLP 2020 

  Access Paper or Ask Questions

Attention that does not Explain Away

Sep 29, 2020
Nan Ding, Xinjie Fan, Zhenzhong Lan, Dale Schuurmans, Radu Soricut

  Access Paper or Ask Questions

Weakly Supervised Content Selection for Improved Image Captioning

Sep 10, 2020
Khyathi Raghavi Chandu, Piyush Sharma, Soravit Changpinyo, Ashish Thapliyal, Radu Soricut

  Access Paper or Ask Questions

Multi-Image Summarization: Textual Summary from a Set of Cohesive Images

Jun 15, 2020
Nicholas Trieu, Sebastian Goodman, Pradyumna Narayana, Kazoo Sone, Radu Soricut

* 9 pages, 5 figures 

  Access Paper or Ask Questions

Clue: Cross-modal Coherence Modeling for Caption Generation

May 02, 2020
Malihe Alikhani, Piyush Sharma, Shengjie Li, Radu Soricut, Matthew Stone

* Accepted as a long paper to ACL 2020 

  Access Paper or Ask Questions

Cross-modal Language Generation using Pivot Stabilization for Web-scale Language Coverage

May 01, 2020
Ashish V. Thapliyal, Radu Soricut

* ACL 2020 

  Access Paper or Ask Questions

Beyond Instructional Videos: Probing for More Diverse Visual-Textual Grounding on YouTube

Apr 29, 2020
Jack Hessel, Zhenhai Zhu, Bo Pang, Radu Soricut

* 8 pages including supplementary materials 

  Access Paper or Ask Questions

Connecting Vision and Language with Localized Narratives

Dec 06, 2019
Jordi Pont-Tuset, Jasper Uijlings, Soravit Changpinyo, Radu Soricut, Vittorio Ferrari

  Access Paper or Ask Questions

Reinforcing an Image Caption Generator Using Off-Line Human Feedback

Nov 21, 2019
Paul Hongsuck Seo, Piyush Sharma, Tomer Levinboim, Bohyung Han, Radu Soricut

* AAAI 2020 

  Access Paper or Ask Questions

ALBERT: A Lite BERT for Self-supervised Learning of Language Representations

Oct 30, 2019
Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, Radu Soricut

  Access Paper or Ask Questions

A Case Study on Combining ASR and Visual Features for Generating Instructional Video Captions

Oct 07, 2019
Jack Hessel, Bo Pang, Zhenhai Zhu, Radu Soricut

* Published in The SIGNLL Conference on Computational Natural Language Learning (CoNLL) 2019 

  Access Paper or Ask Questions

Multi-stage Pretraining for Abstractive Summarization

Sep 23, 2019
Sebastian Goodman, Zhenzhong Lan, Radu Soricut

  Access Paper or Ask Questions

Quality Estimation for Image Captions Based on Large-scale Human Evaluations

Sep 08, 2019
Tomer Levinboim, Ashish Thapliyal, Piyush Sharma, Radu Soricut

* 10 pages (8+2), 5 figures, 3 tables 

  Access Paper or Ask Questions

Decoupled Box Proposal and Featurization with Ultrafine-Grained Semantic Labels Improve Image Captioning and Visual Question Answering

Sep 04, 2019
Soravit Changpinyo, Bo Pang, Piyush Sharma, Radu Soricut

* The 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP 2019) 

  Access Paper or Ask Questions

Informative Image Captioning with External Sources of Information

Jun 20, 2019
Sanqiang Zhao, Piyush Sharma, Tomer Levinboim, Radu Soricut

  Access Paper or Ask Questions

SHAPED: Shared-Private Encoder-Decoder for Text Style Adaptation

Apr 11, 2018
Ye Zhang, Nan Ding, Radu Soricut

* NAACL 2018 

  Access Paper or Ask Questions

Cold-Start Reinforcement Learning with Softmax Policy Gradient

Oct 13, 2017
Nan Ding, Radu Soricut

* Conference on Neural Information Processing Systems 2017. Main paper and supplementary material 

  Access Paper or Ask Questions

Understanding Image and Text Simultaneously: a Dual Vision-Language Machine Comprehension Task

Dec 22, 2016
Nan Ding, Sebastian Goodman, Fei Sha, Radu Soricut

* 11 pages 

  Access Paper or Ask Questions

Multilingual Word Embeddings using Multigraphs

Dec 14, 2016
Radu Soricut, Nan Ding

* 12 pages 

  Access Paper or Ask Questions

Building Large Machine Reading-Comprehension Datasets using Paragraph Vectors

Dec 13, 2016
Radu Soricut, Nan Ding

* 10 pages 

  Access Paper or Ask Questions