no code implementations • NAACL (TrustNLP) 2022 • Brihi Joshi, Aaron Chan, Ziyi Liu, Xiang Ren
For the latter, explanation regularization (ER) aims to improve NLM generalization by pushing the machine rationales to align with human rationales.
no code implementations • 23 Apr 2024 • Yunming Zhang, Dengpan Ye, Sipeng Shen, Caiyun Xie, Ziyi Liu, Jiacheng Deng, Long Tang
This strategy enhances the representation of universal carrier features, mitigating multi-objective optimization conflicts in watermarking.
no code implementations • 20 Apr 2024 • Yangcen Liu, Ziyi Liu, Yuanhao Zhai, Wen Li, David Doerman, Junsong Yuan
To address this problem, we propose the Generalizable Temporal Action Localization task (GTAL), which focuses on improving the generalizability of action localization methods.
no code implementations • 16 Nov 2023 • Ziyi Liu, Isabelle Lee, Yongkang Du, Soumya Sanyal, Jieyu Zhao
In a plethora of recent work, large language models (LLMs) demonstrated impressive reasoning ability, but many proposed downstream reasoning tasks focus on performance-wise evaluation.
no code implementations • 25 Oct 2023 • Yunming Zhang, Dengpan Ye, Caiyun Xie, Long Tang, Chuanxi Chen, Ziyi Liu, Jiacheng Deng
Dual Defense invisibly embeds a single robust watermark within the target face to actively respond to sudden cases of malicious face swapping.
no code implementations • 16 Oct 2023 • Jesse Zhang, Jiahui Zhang, Karl Pertsch, Ziyi Liu, Xiang Ren, Minsuk Chang, Shao-Hua Sun, Joseph J. Lim
Instead, our approach BOSS (BOotStrapping your own Skills) learns to accomplish new tasks by performing "skill bootstrapping," where an agent with a set of primitive skills interacts with the environment to practice new skills without receiving reward feedback for tasks outside of the initial skill set.
1 code implementation • ICCV 2023 • Yuanhao Zhai, Ziyi Liu, Zhenyu Wu, Yi Wu, Chunluan Zhou, David Doermann, Junsong Yuan, Gang Hua
The former prevents the decoder from reconstructing the video background given video features, and thus helps reduce the background information in feature learning.
1 code implementation • 11 May 2023 • Brihi Joshi, Ziyi Liu, Sahana Ramnath, Aaron Chan, Zhewei Tong, Shaoliang Nie, Qifan Wang, Yejin Choi, Xiang Ren
Existing metrics like task performance of the LM generating the rationales, or similarity between generated and gold rationales are not good indicators of their human utility.
1 code implementation • 4 Apr 2023 • Ziyi Liu, Rakshitha Godahewa, Kasun Bandara, Christoph Bergmeir
Handling concept drift in forecasting is essential for many ML methods in use nowadays, however, the prior work only proposes methods to handle concept drift in the classification domain.
1 code implementation • 8 Nov 2022 • Xue Yu, Ziyi Liu, Wu Wang, Yifan Sun
We propose a clustered FL framework that incorporates a nonconvex penalty to pairwise differences of parameters.
no code implementations • 30 Oct 2022 • Dong-Ho Lee, Akshen Kadakia, Brihi Joshi, Aaron Chan, Ziyi Liu, Kiran Narahari, Takashi Shibuya, Ryosuke Mitani, Toshiyuki Sekiya, Jay Pujara, Xiang Ren
Explanation-based model debugging aims to resolve spurious biases by showing human users explanations of model behavior, asking users to give feedback on the behavior, then using the feedback to update the model.
1 code implementation • 14 Sep 2022 • Jingjing Jiang, Ziyi Liu, Nanning Zheng
In this paper, we aim to improve input robustness from an information bottleneck perspective when adapting pretrained VLMs to the downstream VQA task.
1 code implementation • COLING 2022 • Yusen Zhang, Zhongli Li, Qingyu Zhou, Ziyi Liu, Chao Li, Mina Ma, Yunbo Cao, Hongzhi Liu
To automatically correct handwritten assignments, the traditional approach is to use an OCR model to recognize characters and compare them to answers.
1 code implementation • 25 May 2022 • Brihi Joshi, Aaron Chan, Ziyi Liu, Shaoliang Nie, Maziar Sanjabi, Hamed Firooz, Xiang Ren
to align with human rationales (Which input tokens would humans focus on?).
1 code implementation • CVPR 2022 • Ziyi Liu, Zengmao Wang, Bo Du
In this paper, we propose a deep protein subcellular localization method with multi-marginal contrastive learning to perceive the same PSLs in different tissue images and different PSLs within the same tissue image.
1 code implementation • 29 Nov 2021 • Jingjing Jiang, Ziyi Liu, Nanning Zheng
Video Question Answering (VideoQA), aiming to correctly answer the given question based on understanding multi-modal video content, is challenging due to the rich video content.
no code implementations • 9 Nov 2021 • Ziyi Liu, JiaQi Zhang, Yongshuai Hou, Xinran Zhang, Ge Li, Yang Xiang
Background: Electronic Health Records (EHRs) contain rich information of patients' health history, which usually include both structured and unstructured data.
no code implementations • 15 Oct 2021 • Ziyi Liu, Minghui Liao, Fulin Luo, Bo Du
This method constructs the graph by the similarity relationship between cells and adopts GCN to analyze the neighbor embedding information of samples, which makes the similar cell closer to each other on the 2D scatter plot.
1 code implementation • 24 Jul 2021 • Jingjing Jiang, Ziyi Liu, Yifan Liu, Zhixiong Nan, Nanning Zheng
In this paper, we formulate OOD generalization in VQA as a compositional generalization problem and propose a graph generative modeling-based training scheme (X-GGM) to implicitly model the problem.
1 code implementation • 5 Jul 2021 • Ziyi Liu, Jie Yang, Svetlana Yanushkevich, Orly Yadid-Pecht
Embedded systems have a huge market, and utilizing DCNNs' powerful functionality into them will further reduce human intervention.
no code implementations • 30 Mar 2021 • Ziyi Liu, Le Wang, Wei Tang, Junsong Yuan, Nanning Zheng, Gang Hua
To address this challenge, we introduce a framework that learns two feature subspaces respectively for actions and their context.
Action Recognition Weakly-supervised Temporal Action Localization +1
no code implementations • 28 Mar 2021 • Ziyi Liu, Le Wang, Qilin Zhang, Wei Tang, Junsong Yuan, Nanning Zheng, Gang Hua
In this paper, we introduce an Action-Context Separation Network (ACSNet) that explicitly takes into account context for accurate action localization.
Ranked #7 on Weakly Supervised Action Localization on THUMOS’14
Video Polyp Segmentation Weakly Supervised Action Localization +2
no code implementations • 2 Feb 2021 • Jie Yang, Mengchen Lin, Ziyi Liu, Ulian Shahnovich, Orly Yadid-Pecht
It is especially crucial for mobile devices because most of the images taken today are from mobile phones, hence such technology is highly demanded in the consumer market of mobile devices and is essential for a good customer experience.
1 code implementation • 31 Jan 2021 • Jie Yang, Ziyi Liu, Ulian Shahnovich, Orly Yadid-Pecht
HVS perceives luminance differently when under different adaptation levels, and therefore our algorithm uses functions built upon different scales to tone map pixels to different values.
1 code implementation • 31 Jan 2021 • Jie Yang, Ziyi Liu, Mengchen Lin, Svetlana Yanushkevich, Orly Yadid-Pecht
The reformulated Laplacian pyramid always decompose a WDR image into two frequency bands where the low-frequency band is global feature-oriented, and the high-frequency band is local feature-oriented.
no code implementations • 11 Jan 2021 • Ziyi Liu, Jie Yang, Mengchen Lin, Kenneth Kam Fai Lai, Svetlana Yanushkevich, Orly Yadid-Pecht
Furthermore, we show the effect of different face detection procedures on the WDRIs in our database.
no code implementations • 8 Jan 2021 • Ziyi Liu
The dynamic range of our normal life can exceeds 120 dB, however, the smart-phone cameras and the conventional digital cameras can only capture a dynamic range of 90 dB, which sometimes leads to loss of details for the recorded image.
no code implementations • EMNLP (Louhi) 2020 • Ziyi Liu, Giannis Karamanolakis, Daniel Hsu, Luis Gravano
To improve performance without extra annotations, we create artificial training documents in the target language through machine translation and train mBERT jointly for the source (English) and target language.
no code implementations • ICCV 2019 • Ziyi Liu, Le Wang, Qilin Zhang, Zhanning Gao, Zhenxing Niu, Nanning Zheng, Gang Hua
To address this challenge, we propose the Contrast-based Localization EvaluAtioN Network (CleanNet) with our new action proposal evaluator, which provides pseudo-supervision by leveraging the temporal contrast in snippet-level action classification predictions.
Ranked #12 on Weakly Supervised Action Localization on ActivityNet-1.2 (mAP@0.5 metric)
Action Classification Weakly Supervised Action Localization +2
no code implementations • 19 Mar 2018 • Jinliang Zang, Le Wang, Ziyi Liu, Qilin Zhang, Zhenxing Niu, Gang Hua, Nanning Zheng
Research in human action recognition has accelerated significantly since the introduction of powerful machine learning tools such as Convolutional Neural Networks (CNNs).
no code implementations • 1 May 2017 • Ziyi Liu, Siyu Yu, Xiao Wang, Nanning Zheng
Experiments show that our unsupervised approach is efficient and robust for detecting drivable area for self-driving cars.