Search Results for author: Boyang Li

Found 59 papers, 27 papers with code

Toward Knowledge-Enriched Conversational Recommendation Systems

no code implementations NLP4ConvAI (ACL) 2022 Tong Zhang, Yong liu, Boyang Li, Peixiang Zhong, Chen Zhang, Hao Wang, Chunyan Miao

Conversational Recommendation Systems recommend items through language based interactions with users. In order to generate naturalistic conversations and effectively utilize knowledge graphs (KGs) containing background information, we propose a novel Bag-of-Entities loss, which encourages the generated utterances to mention concepts related to the item being recommended, such as the genre or director of a movie.

Knowledge Graphs Recommendation Systems +1

What Are We Measuring When We Evaluate Large Vision-Language Models? An Analysis of Latent Factors and Biases

1 code implementation3 Apr 2024 Anthony Meng Huat Tiong, Junqi Zhao, Boyang Li, Junnan Li, Steven C. H. Hoi, Caiming Xiong

Vision-language (VL) models, pretrained on colossal image-text datasets, have attained broad VL competence that is difficult to evaluate.

Transfer Learning

Interpretable Modeling of Deep Reinforcement Learning Driven Scheduling

no code implementations24 Mar 2024 Boyang Li, Zhiling Lan, Michael E. Papka

In this work, we present a framework called IRL (Interpretable Reinforcement Learning) to address the issue of interpretability of DRL scheduling.

Imitation Learning reinforcement-learning +1

DCDet: Dynamic Cross-based 3D Object Detector

1 code implementation14 Jan 2024 Shuai Liu, Boyang Li, Zhiyu Fang, Kai Huang

We find that the center-based label assignment often fails to generate sufficient positive samples for training, while the anchor-based label assignment tends to encounter an imbalanced issue when handling objects of varying scales.

3D Object Detection Object +2

Training on Synthetic Data Beats Real Data in Multimodal Relation Extraction

no code implementations5 Dec 2023 Zilin Du, Haoxin Li, Xu Guo, Boyang Li

Comparing our method to direct training on synthetic data, we observed a significant improvement of 24. 06% F1 with synthetic text and 26. 42% F1 with synthetic images.

Relation Relation Extraction

Event Causality Is Key to Computational Story Understanding

1 code implementation16 Nov 2023 Yidan Sun, Qin Chao, Boyang Li

Cognitive science and symbolic AI research suggest that event causality provides vital information for story understanding.

Event Causality Identification Sentence +1

A Forward Reachability Perspective on Robust Control Invariance and Discount Factors in Reachability Analysis

no code implementations26 Oct 2023 Jason J. Choi, Donggun Lee, Boyang Li, Jonathan P. How, Koushil Sreenath, Sylvia L. Herbert, Claire J. Tomlin

We also formulate a zero-sum differential game between the control and disturbance, where the inevitable FRT is characterized by the zero-superlevel set of the value function.

May I Ask a Follow-up Question? Understanding the Benefits of Conversations in Neural Network Explainability

no code implementations25 Sep 2023 Tong Zhang, X. Jessie Yang, Boyang Li

With this paper, we investigate if free-form conversations can enhance users' comprehension of static explanations, improve acceptance and trust in the explanation methods, and facilitate human-AI collaboration.

Decision Making

Proof-of-Federated-Learning-Subchain: Free Partner Selection Subchain Based on Federated Learning

no code implementations30 Jul 2023 Boyang Li, Bingyu Shen, Qing Lu, Taeho Jung, Yiyu Shi

In the conducted experiments, the PoFLSC consensus supported the subchain manager to be aware of reservation priority and the core partition of contributors to establish and maintain a competitive subchain.

Federated Learning

Training Multimedia Event Extraction With Generated Images and Captions

no code implementations15 Jun 2023 Zilin Du, Yunxin Li, Xu Guo, Yidan Sun, Boyang Li

Contemporary news reporting increasingly features multimedia content, motivating research on multimedia event extraction.

Event Extraction Structured Prediction

Learning Remote Sensing Object Detection with Single Point Supervision

1 code implementation23 May 2023 Shitian He, Huanxin Zou, Yingqian Wang, Boyang Li, Xu Cao, Ning Jing

In this paper, we make the first attempt to achieve RS object detection with single point supervision, and propose a PSOD method tailored for RS images.

Object object-detection +1

Movie Box Office Prediction With Self-Supervised and Visually Grounded Pretraining

no code implementations20 Apr 2023 Qin Chao, Eunsoo Kim, Boyang Li

Investments in movie production are associated with a high level of risk as movie revenues have long-tailed and bimodal distributions.

Visual Grounding

Monte Carlo Linear Clustering with Single-Point Supervision is Enough for Infrared Small Target Detection

1 code implementation ICCV 2023 Boyang Li, Yingqian Wang, Longguang Wang, Fei Zhang, Ting Liu, Zaiping Lin, Wei An, Yulan Guo

The core idea of this work is to recover the per-pixel mask of each target from the given single point label by using clustering approaches, which looks simple but is indeed challenging since targets are always insalient and accompanied with background clutters.


History-Aware Hierarchical Transformer for Multi-session Open-domain Dialogue System

no code implementations2 Feb 2023 Tong Zhang, Yong liu, Boyang Li, Zhiwei Zeng, Pengwei Wang, Yuan You, Chunyan Miao, Lizhen Cui

HAHT maintains a long-term memory of history conversations and utilizes history information to understand current conversation context and generate well-informed and context-relevant responses.

New method for coherent imaging using incompatible sources

no code implementations12 Jan 2023 Boyang Li

Non-invasive imaging plays a crucial role in the early detection, diagnosis, and treatment of numerous medical conditions.

From Images to Textual Prompts: Zero-Shot Visual Question Answering With Frozen Large Language Models

no code implementations CVPR 2023 Jiaxian Guo, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong, Boyang Li, DaCheng Tao, Steven Hoi

To address this issue, we propose Img2Prompt, a plug-and-play module that provides the prompts that can bridge the aforementioned modality and task disconnections, so that LLMs can perform zero-shot VQA tasks without end-to-end training.

Question Answering Visual Question Answering +1

From Images to Textual Prompts: Zero-shot VQA with Frozen Large Language Models

3 code implementations21 Dec 2022 Jiaxian Guo, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong, Boyang Li, DaCheng Tao, Steven C. H. Hoi

To address this issue, we propose \emph{Img2Prompt}, a plug-and-play module that provides the prompts that can bridge the aforementioned modality and task disconnections, so that LLMs can perform zero-shot VQA tasks without end-to-end training.

Question Answering Visual Question Answering +1

Is GPT-3 a Good Data Annotator?

no code implementations20 Dec 2022 Bosheng Ding, Chengwei Qin, Linlin Liu, Yew Ken Chia, Shafiq Joty, Boyang Li, Lidong Bing

In this paper, we evaluate the performance of GPT-3 as a data annotator by comparing it with traditional data annotation methods and analyzing its output on a range of tasks.

Language Modelling

Mitigating and Evaluating Static Bias of Action Representations in the Background and the Foreground

1 code implementation ICCV 2023 Haoxin Li, YuAn Liu, Hanwang Zhang, Boyang Li

The video background is clearly a source of static bias, but the video foreground, such as the clothing of the actor, can also provide static bias.

Action Recognition Data Augmentation +1

A Survey of Computer Vision Technologies In Urban and Controlled-environment Agriculture

no code implementations20 Oct 2022 Jiayun Luo, Boyang Li, Cyril Leung

In addition, we discuss five key subareas of computer vision and how they related to these CEA problems, as well as eleven vision-based CEA datasets.

Improving the Sample Efficiency of Prompt Tuning with Domain Adaptation

1 code implementation6 Oct 2022 Xu Guo, Boyang Li, Han Yu

Prompt tuning, or the conditioning of a frozen pretrained language model (PLM) with soft prompts learned from data, has demonstrated impressive performance on a wide range of NLP tasks.

Domain Adaptation Language Modelling

MTU-Net: Multi-level TransUNet for Space-based Infrared Tiny Ship Detection

1 code implementation28 Sep 2022 Tianhao Wu, Boyang Li, Yihang Luo, Yingqian Wang, Chao Xiao, Ting Liu, Jungang Yang, Wei An, Yulan Guo

Due to the extremely large image coverage area (e. g., thousands square kilometers), candidate targets in these images are much smaller, dimer, more changeable than those targets observed by aerial-based and land-based imaging devices.

Data Augmentation

Minimalist and High-performance Conversational Recommendation with Uncertainty Estimation for User Preference

no code implementations29 Jun 2022 Yinan Zhang, Boyang Li, Yong liu, You Yuan, Chunyan Miao

Multi-shot CRS is designed to make recommendations multiple times until the user either accepts the recommendation or leaves at the end of their patience.

Attribute Reinforcement Learning (RL)

Efficient Self-supervised Vision Pretraining with Local Masked Reconstruction

1 code implementation1 Jun 2022 Jun Chen, Ming Hu, Boyang Li, Mohamed Elhoseiny

After finetuning the pretrained LoMaR on 384$\times$384 images, it can reach 85. 4% top-1 accuracy, surpassing MAE by 0. 6%.

Image Classification Instance Segmentation +3

A Collaboration Strategy in the Mining Pool for Proof-of-Neural-Architecture Consensus

no code implementations5 May 2022 Boyang Li, Qing Lu, Weiwen Jiang, Taeho Jung, Yiyu Shi

In many recent novel blockchain consensuses, the deep learning training procedure becomes the task for miners to prove their workload, thus the computation power of miners will not purely be spent on the hash puzzle.

Neural Architecture Search

Synopses of Movie Narratives: a Video-Language Dataset for Story Understanding

no code implementations11 Mar 2022 Yidan Sun, Qin Chao, Yangfeng Ji, Boyang Li

Despite recent advances of AI, story understanding remains an open and under-investigated problem.

Retrieval Text Retrieval +1

Improving Tail-Class Representation with Centroid Contrastive Learning

no code implementations19 Oct 2021 Anthony Meng Huat Tiong, Junnan Li, Guosheng Lin, Boyang Li, Caiming Xiong, Steven C. H. Hoi

ICCL interpolates two images from a class-agnostic sampler and a class-aware sampler, and trains the model such that the representation of the interpolative image can be used to retrieve the centroids for both source classes.

Contrastive Learning Image Classification +2

Noise-Resistant Deep Metric Learning with Probabilistic Instance Filtering

no code implementations3 Aug 2021 Chang Liu, Han Yu, Boyang Li, Zhiqi Shen, Zhanning Gao, Peiran Ren, Xuansong Xie, Lizhen Cui, Chunyan Miao

Noisy labels are commonly found in real-world data, which cause performance degradation of deep neural networks.

Metric Learning

Initialization Matters: Regularizing Manifold-informed Initialization for Neural Recommendation Systems

no code implementations9 Jun 2021 Yinan Zhang, Boyang Li, Yong liu, Hao Wang, Chunyan Miao

In this work, we propose a new initialization scheme for user and item embeddings called Laplacian Eigenmaps with Popularity-based Regularization for Isolated Data (LEPORID).

Recommendation Systems

Non-Convex Tensor Low-Rank Approximation for Infrared Small Target Detection

1 code implementation31 May 2021 Ting Liu, Jungang Yang, Boyang Li, Chao Xiao, Yang Sun, Yingqian Wang, Wei An

Considering that different singular values have different importance and should be treated discriminatively, in this paper, we propose a non-convex tensor low-rank approximation (NTLA) method for infrared small target detection.

Latent-Optimized Adversarial Neural Transfer for Sarcasm Detection

1 code implementation NAACL 2021 Xu Guo, Boyang Li, Han Yu, Chunyan Miao

The existence of multiple datasets for sarcasm detection prompts us to apply transfer learning to exploit their commonality.

Meta-Learning Sarcasm Detection +1

VisualGPT: Data-efficient Adaptation of Pretrained Language Models for Image Captioning

1 code implementation CVPR 2022 Jun Chen, Han Guo, Kai Yi, Boyang Li, Mohamed Elhoseiny

To the best of our knowledge, this is the first work that improves data efficiency of image captioning by utilizing LM pretrained on unimodal data.

Decoder Image Captioning +2

HYDRA: Hypergradient Data Relevance Analysis for Interpreting Deep Neural Networks

1 code implementation4 Feb 2021 YuanYuan Chen, Boyang Li, Han Yu, Pengcheng Wu, Chunyan Miao

the weights of training data, HYDRA assesses the contribution of training data toward test data points throughout the training trajectory.

Rolling Shutter Correction

Federated Learning for Personalized Humor Recognition

no code implementations3 Dec 2020 Xu Guo, Han Yu, Boyang Li, Hao Wang, Pengwei Xing, Siwei Feng, Zaiqing Nie, Chunyan Miao

In this paper, we propose the FedHumor approach for the recognition of humorous content in a personalized manner through Federated Learning (FL).

Federated Learning Language Modelling

Data-efficient Alignment of Multimodal Sequences by Aligning Gradient Updates and Internal Feature Distributions

1 code implementation15 Nov 2020 Jianan Wang, Boyang Li, Xiangyu Fan, Jing Lin, Yanwei Fu

The task of video and text sequence alignment is a prerequisite step toward joint understanding of movie videos and screenplays.

Proof of Learning (PoLe): Empowering Machine Learning with Consensus Building on Blockchains

no code implementations29 Jul 2020 Yixiao Lan, Yu-An Liu, Boyang Li

Empirical evaluation shows that SML can detect cheating nodes at small cost to the predictive performance.

BIG-bench Machine Learning valid

An Empirical Study on the Relation between Network Interpretability and Adversarial Robustness

1 code implementation7 Dec 2019 Adam Noack, Isaac Ahern, Dejing Dou, Boyang Li

We demonstrate that training the networks to have interpretable gradients improves their robustness to adversarial perturbations.

Adversarial Robustness Image Classification +2

NormLime: A New Feature Importance Metric for Explaining Deep Neural Networks

no code implementations ICLR 2020 Isaac Ahern, Adam Noack, Luis Guzman-Nateras, Dejing Dou, Boyang Li, Jun Huan

The problem of explaining deep learning models, and model predictions generally, has attracted intensive interest recently.

Feature Importance

Real-Time Adversarial Attacks

1 code implementation31 May 2019 Yuan Gong, Boyang Li, Christian Poellabauer, Yiyu Shi

In recent years, many efforts have demonstrated that modern machine learning algorithms are vulnerable to adversarial attacks, where small, but carefully crafted, perturbations on the input can make them fail.

Adversarial Attack BIG-bench Machine Learning

DLBC: A Deep Learning-Based Consensus in Blockchains for Deep Learning Services

no code implementations15 Apr 2019 Boyang Li, Changhao Chenli, Xiaowei Xu, Yiyu Shi, Taeho Jung

In this paper, we propose DLBC to exploit the computation power of miners for deep learning training as proof of useful work instead of calculating hash values.

Semantic Segmentation

Joint Event Detection and Description in Continuous Video Streams

1 code implementation28 Feb 2018 Huijuan Xu, Boyang Li, Vasili Ramanishka, Leonid Sigal, Kate Saenko

In order to explicitly model temporal relationships between visual events and their captions in a single video, we also propose a two-level hierarchical captioning module that keeps track of context.

Dense Captioning Dense Video Captioning +2

A Neural Multi-sequence Alignment TeCHnique (NeuMATCH)

1 code implementation CVPR 2018 Pelin Dogan, Boyang Li, Leonid Sigal, Markus Gross

The alignment of heterogeneous sequential data (video to text) is an important and challenging problem.

Dynamic Time Warping

Predicting the Quality of Short Narratives from Social Media

no code implementations8 Jul 2017 Tong Wang, Ping Chen, Boyang Li

An important and difficult challenge in building computational models for narratives is the automatic evaluation of narrative quality.

Active Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.