1 code implementation • 11 Mar 2024 • Tiancheng Zhao, Peng Liu, Xuan He, Lu Zhang, Kyusong Lee
End-to-end transformer-based detectors (DETRs) have shown exceptional performance in both closed-set and open-vocabulary object detection (OVD) tasks through the integration of language modalities.
1 code implementation • 22 Dec 2023 • Haozhan Shen, Tiancheng Zhao, Mingwei Zhu, Jianwei Yin
Visual grounding, a crucial vision-language task involving the understanding of the visual context based on the query expression, necessitates the model to capture the interactions between objects, as well as various spatial and attribute information.
1 code implementation • 20 Oct 2023 • Mingwei Zhu, Leigang Sha, Yu Shu, Kangjia Zhao, Tiancheng Zhao, Jianwei Yin
Multimodal large language models (MLLMs) have shown great potential in perception and interpretation tasks, but their capabilities in predictive reasoning remain under-explored.
2 code implementations • 25 Aug 2023 • Yiyang Yao, Peng Liu, Tiancheng Zhao, Qianqian Zhang, Jiajia Liao, Chunxin Fang, Kyusong Lee, Qing Wang
Extensive experimental results show that existing top OVD models all fail on the new tasks except for simple object types, demonstrating the value of the proposed dataset in pinpointing the weakness of current OVD models and guiding future research.
Ranked #1 on Negation on OVDEval
1 code implementation • 20 Jun 2023 • Zilun Zhang, Tiancheng Zhao, Yulong Guo, Jianwei Yin
Moreover, we present an image-text paired dataset in the field of remote sensing (RS), RS5M, which has 5 million RS images with English descriptions.
Ranked #1 on Cross-Modal Retrieval on RSITMD (using extra training data)
1 code implementation • 10 Sep 2022 • Tiancheng Zhao, Peng Liu, Kyusong Lee
The advancement of object detection (OD) in open-vocabulary and open-world scenarios is a critical challenge in computer vision.
1 code implementation • 16 Aug 2022 • Jaemin Yoo, Tiancheng Zhao, Leman Akoglu
Self-supervised learning (SSL) has emerged as a promising alternative to create supervisory signals to real-world problems, avoiding the extensive cost of manual labeling.
1 code implementation • 1 Jul 2022 • Tiancheng Zhao, Tianqi Zhang, Mingwei Zhu, Haozhan Shen, Kyusong Lee, Xiaopeng Lu, Jianwei Yin
Inspired by the CheckList for testing natural language processing, we exploit VL-CheckList, a novel framework to understand the capabilities of VLP models.
1 code implementation • EACL 2021 • Xiaopeng Lu, Kyusong Lee, Tiancheng Zhao
Although open-domain question answering (QA) draws great attention in recent years, it requires large amounts of resources for building the full system and is often difficult to reproduce previous results due to complex configurations.
1 code implementation • ACL 2021 • Xiaopeng Lu, Tiancheng Zhao, Kyusong Lee
To the best of our knowledge, VisualSparta is the first transformer-based text-to-image retrieval model that can achieve real-time searching for large-scale datasets, with significant accuracy improvement compared to previous state-of-the-art methods.
Ranked #2 on Image Retrieval on MS COCO
1 code implementation • NAACL 2021 • Tiancheng Zhao, Xiaopeng Lu, Kyusong Lee
We validated our approaches on 4 open-domain question answering (OpenQA) tasks and 11 retrieval question answering (ReQA) tasks.
Ranked #1 on Open-Domain Question Answering on SQuAD1.1 dev
no code implementations • ACL 2020 • Yulan Feng, Shikib Mehri, Maxine Eskenazi, Tiancheng Zhao
This paper discusses the importance of uncovering uncertainty in end-to-end dialog tasks and presents our experimental results on uncertainty classification on the processed Ubuntu Dialog Corpus.
no code implementations • 10 Jun 2020 • Maxine Eskenazi, Tiancheng Zhao
This USER Workshop was convened with the goal of defining future research directions for the burgeoning intelligent agent research community and to communicate them to the National Science Foundation.
no code implementations • 4 Apr 2020 • Yulan Feng, Shikib Mehri, Maxine Eskenazi, Tiancheng Zhao
This paper discusses the importance of uncovering uncertainty in end-to-end dialog tasks, and presents our experimental results on uncertainty classification on the Ubuntu Dialog Corpus.
2 code implementations • WS 2019 • Prakhar Gupta, Shikib Mehri, Tiancheng Zhao, Amy Pavel, Maxine Eskenazi, Jeffrey P. Bigham
The aim of this paper is to mitigate the shortcomings of automatic evaluation of open-domain dialog systems through multi-reference evaluation.
no code implementations • ACL 2019 • Shikib Mehri, Evgeniia Razumovskaia, Tiancheng Zhao, Maxine Eskenazi
This paper examines various unsupervised pretraining objectives for learning dialog context representations.
2 code implementations • ACL 2019 • Jianheng Tang, Tiancheng Zhao, Chenyan Xiong, Xiaodan Liang, Eric P. Xing, Zhiting Hu
We study the problem of imposing conversational goals on open-domain chat agents.
1 code implementation • NAACL 2019 • Weiyan Shi, Tiancheng Zhao, Zhou Yu
The learned dialog structure can shed light on how to analyze human dialogs, and more importantly contribute to the design and evaluation of dialog systems.
3 code implementations • NAACL 2019 • Tiancheng Zhao, Kaige Xie, Maxine Eskenazi
Defining action spaces for conversational agents and optimizing their decision-making process with reinforcement learning is an enduring challenge.
no code implementations • 20 Jan 2019 • Maxine Eskenazi, Shikib Mehri, Evgeniia Razumovskaia, Tiancheng Zhao
Most research on intelligent agents centers on the agent and not on the user.
no code implementations • 31 Oct 2018 • Yijun Xiao, Tiancheng Zhao, William Yang Wang
We introduce an improved variational autoencoder (VAE) for text modeling with topic information explicitly modeled as a Dirichlet latent variable.
4 code implementations • ACL 2019 • Zhiting Hu, Haoran Shi, Bowen Tan, Wentao Wang, Zichao Yang, Tiancheng Zhao, Junxian He, Lianhui Qin, Di Wang, Xuezhe Ma, Zhengzhong Liu, Xiaodan Liang, Wangrong Zhu, Devendra Singh Sachan, Eric P. Xing
The versatile toolkit also fosters technique sharing across different text generation tasks.
no code implementations • WS 2018 • Kyusong Lee, Tiancheng Zhao, Alan W. black, Maxine Eskenazi
When creating a dialog system, developers need to test each version to ensure that it is performing correctly.
no code implementations • WS 2018 • Zhiting Hu, Zichao Yang, Tiancheng Zhao, Haoran Shi, Junxian He, Di Wang, Xuezhe Ma, Zhengzhong Liu, Xiaodan Liang, Lianhui Qin, Devendra Singh Chaplot, Bowen Tan, Xingjiang Yu, Eric Xing
The features make Texar particularly suitable for technique sharing and generalization across different text generation applications.
2 code implementations • WS 2018 • Tiancheng Zhao, Maxine Eskenazi
This paper introduces zero-shot dialog generation (ZSDG), as a step towards neural dialog systems that can instantly generalize to new situations with minimal data.
no code implementations • WS 2018 • Jiaping Zhang, Tiancheng Zhao, Zhou Yu
We propose a multimodal hierarchical reinforcement learning framework that dynamically integrates vision and language for task-oriented visual dialog.
Hierarchical Reinforcement Learning reinforcement-learning +3
2 code implementations • ACL 2018 • Tiancheng Zhao, Kyusong Lee, Maxine Eskenazi
The encoder-decoder dialog model is one of the most prominent methods used to build dialog systems in complex domains.
no code implementations • WS 2017 • Kyusong Lee, Tiancheng Zhao, Yulun Du, Edward Cai, Allen Lu, Eli Pincus, David Traum, Stefan Ultes, Lina M. Rojas-Barahona, Milica Gasic, Steve Young, Maxine Eskenazi
DialPort collects user data for connected spoken dialog systems.
no code implementations • WS 2017 • Tiancheng Zhao, Allen Lu, Kyusong Lee, Maxine Eskenazi
This paper presents a practical and novel framework for building task-oriented dialog systems based on encoder-decoder models.
1 code implementation • ACL 2017 • Tiancheng Zhao, Ran Zhao, Maxine Eskenazi
While recent neural encoder-decoder models have shown great promise in modeling open-domain conversations, they often generate dull and generic responses.
no code implementations • 10 Oct 2016 • Tiancheng Zhao, Ran Zhao, Zhao Meng, Justine Cassell
Social norms are shared rules that govern and facilitate social interaction.
no code implementations • 8 Jun 2016 • Tiancheng Zhao, Kyusong Lee, Maxine Eskenazi
This paper describes a new spoken dialog portal that connects systems produced by the spoken dialog academic research community and gives them access to real users.
1 code implementation • WS 2016 • Tiancheng Zhao, Maxine Eskenazi
This paper presents an end-to-end framework for task-oriented dialog systems using a variant of Deep Recurrent Q-Networks (DRQN).
no code implementations • 29 Mar 2016 • Tiancheng Zhao, Mohammad Gowayyed
We show that it is possible to effectively learn recursive optimal policies for any valid hierarchical decomposition of the original MDP, given a fixed dataset collected from a flat stochastic behavioral policy.
Hierarchical Reinforcement Learning reinforcement-learning +2