Search Results for author: Martin Renqiang Min

Found 41 papers, 13 papers with code

Retrieval, Analogy, and Composition: A framework for Compositional Generalization in Image Captioning

no code implementations Findings (EMNLP) 2021 Zhan Shi, Hui Liu, Martin Renqiang Min, Christopher Malon, Li Erran Li, Xiaodan Zhu

Image captioning systems are expected to have the ability to combine individual concepts when describing scenes with concept combinations that are not observed during training.

Image Captioning Retrieval

Compositional 3D Scene Synthesis with Scene Graph Guided Layout-Shape Generation

no code implementations19 Mar 2024 Yao Wei, Martin Renqiang Min, George Vosselman, Li Erran Li, Michael Ying Yang

Recent progresses have been made in shape generation with powerful generative models, such as diffusion models, which increases the shape fidelity.

3D Shape Generation Language Modelling +2

Why Not Use Your Textbook? Knowledge-Enhanced Procedure Planning of Instructional Videos

2 code implementations5 Mar 2024 Kumaranage Ravindu Yasas Nagasinghe, Honglu Zhou, Malitha Gunawardhana, Martin Renqiang Min, Daniel Harari, Muhammad Haris Khan

This knowledge, sourced from training procedure plans and structured as a directed weighted graph, equips the agent to better navigate the complexities of step sequencing and its potential variations.

Logical Sequence Navigate

Exploring Compositional Visual Generation with Latent Classifier Guidance

no code implementations25 Apr 2023 Changhao Shi, Haomiao Ni, Kai Li, Shaobo Han, Mingfu Liang, Martin Renqiang Min

We show that this paradigm based on latent classifier guidance is agnostic to pre-trained generative models, and present competitive results for both image generation and sequential manipulation of real and synthetic images.

Image Generation

Conditional Image-to-Video Generation with Latent Flow Diffusion Models

1 code implementation CVPR 2023 Haomiao Ni, Changhao Shi, Kai Li, Sharon X. Huang, Martin Renqiang Min

In this paper, we propose an approach for cI2V using novel latent flow diffusion models (LFDM) that synthesize an optical flow sequence in the latent space based on the given condition to warp the given image.

Image to Video Generation Optical Flow Estimation

Attribute-Centric Compositional Text-to-Image Generation

no code implementations4 Jan 2023 Yuren Cong, Martin Renqiang Min, Li Erran Li, Bodo Rosenhahn, Michael Ying Yang

We further propose an attribute-centric contrastive loss to avoid overfitting to overrepresented attribute compositions.

Attribute Fairness +1

Few-Shot Video Classification via Representation Fusion and Promotion Learning

no code implementations ICCV 2023 Haifeng Xia, Kai Li, Martin Renqiang Min, Zhengming Ding

This operation maximizes the contribution of discriminative frames to further capture the similarity of support and query samples from the same category.

Video Classification

StyleT2I: Toward Compositional and High-Fidelity Text-to-Image Synthesis

1 code implementation CVPR 2022 Zhiheng Li, Martin Renqiang Min, Kai Li, Chenliang Xu

Based on the identified latent directions of attributes, we propose Compositional Attribute Adjustment to adjust the latent code, resulting in better compositionality of image synthesis.

Attribute Fairness +2

Learning Transferable Reward for Query Object Localization with Policy Adaptation

1 code implementation ICLR 2022 Tingfeng Li, Shaobo Han, Martin Renqiang Min, Dimitris N. Metaxas

We propose a reinforcement learning based approach to query object localization, for which an agent is trained to localize objects of interest specified by a small exemplary set.

Metric Learning Object Localization +2

AE-StyleGAN: Improved Training of Style-Based Auto-Encoders

1 code implementation17 Oct 2021 Ligong Han, Sri Harsha Musunuri, Martin Renqiang Min, Ruijiang Gao, Yu Tian, Dimitris Metaxas

StyleGANs have shown impressive results on data generation and manipulation in recent years, thanks to its disentangled style latent space.

Dual Projection Generative Adversarial Networks for Conditional Image Generation

1 code implementation ICCV 2021 Ligong Han, Martin Renqiang Min, Anastasis Stathopoulos, Yu Tian, Ruijiang Gao, Asim Kadav, Dimitris Metaxas

We then propose an improved cGAN model with Auxiliary Classification that directly aligns the fake and real conditionals $P(\text{class}|\text{image})$ by minimizing their $f$-divergence.

Conditional Image Generation

Disentangled Recurrent Wasserstein Autoencoder

no code implementations ICLR 2021 Jun Han, Martin Renqiang Min, Ligong Han, Li Erran Li, Xuan Zhang

Learning disentangled representations leads to interpretable models and facilitates data generation with style transfer, which has been extensively studied on static data such as images in an unsupervised learning framework.

Disentanglement Style Transfer +1

A Deep Generative Model for Molecule Optimization via One Fragment Modification

2 code implementations8 Dec 2020 Ziqi Chen, Martin Renqiang Min, Srinivasan Parthasarathy, Xia Ning

A pipeline of multiple, identical Modof models is implemented into Modof-pipe to modify an input molecule at multiple disconnection sites.

Drug Discovery

Ranking-based Convolutional Neural Network Models for Peptide-MHC Binding Prediction

1 code implementation4 Dec 2020 Ziqi Chen, Martin Renqiang Min, Xia Ning

T-cell receptors can recognize foreign peptides bound to major histocompatibility complex (MHC) class-I proteins, and thus trigger the adaptive immune response.

MHC presentation prediction

Improving Disentangled Text Representation Learning with Information-Theoretic Guidance

no code implementations ACL 2020 Pengyu Cheng, Martin Renqiang Min, Dinghan Shen, Christopher Malon, Yizhe Zhang, Yitong Li, Lawrence Carin

Learning disentangled representations of natural language is essential for many NLP tasks, e. g., conditional text generation, style transfer, personalized dialogue systems, etc.

Conditional Text Generation Representation Learning +2

S3VAE: Self-Supervised Sequential VAE for Representation Disentanglement and Data Generation

no code implementations CVPR 2020 Yizhe Zhu, Martin Renqiang Min, Asim Kadav, Hans Peter Graf

We propose a sequential variational autoencoder to learn disentangled representations of sequential data (e. g., videos and audios) under self-supervision.


Understanding Attention Mechanisms

no code implementations25 Sep 2019 Bingyuan Liu, Yogesh Balaji, Lingzhou Xue, Martin Renqiang Min

Attention mechanisms have advanced the state of the art in several machine learning tasks.

Defending Against Adversarial Examples by Regularized Deep Embedding

no code implementations25 Sep 2019 Yao Li, Martin Renqiang Min, Wenchao Yu, Cho-Jui Hsieh, Thomas Lee, Erik Kruus

Recent studies have demonstrated the vulnerability of deep convolutional neural networks against adversarial examples.

Adversarial Attack Adversarial Robustness

Rethinking Zero-Shot Learning: A Conditional Visual Classification Perspective

1 code implementation ICCV 2019 Kai Li, Martin Renqiang Min, Yun Fu

We instead reformulate ZSL as a conditioned visual classification problem, i. e., classifying visual features based on the classifiers learned from the semantic descriptions.

Classification General Classification +1

A Deep Spatio-Temporal Fuzzy Neural Network for Passenger Demand Prediction

no code implementations13 May 2019 Xiaoyuan Liang, Guiling Wang, Martin Renqiang Min, Yi Qi, Zhu Han

In spite of its importance, passenger demand prediction is a highly challenging problem, because the demand is simultaneously influenced by the complex interactions among many spatial and temporal factors and other external factors such as weather.

Disentangled Deep Autoencoding Regularization for Robust Image Classification

no code implementations27 Feb 2019 Zhenyu Duan, Martin Renqiang Min, Li Erran Li, Mingbo Cai, Yi Xu, Bingbing Ni

In spite of achieving revolutionary successes in machine learning, deep convolutional neural networks have been recently found to be vulnerable to adversarial attacks and difficult to generalize to novel test images with reasonably large geometric transformations.

Classification General Classification +2

Learning K-way D-dimensional Discrete Codes for Compact Embedding Representations

1 code implementation ICML 2018 Ting Chen, Martin Renqiang Min, Yizhou Sun

Conventional embedding methods directly associate each symbol with a continuous embedding vector, which is equivalent to applying a linear transformation based on a "one-hot" encoding of the discrete symbols.

On the Use of Word Embeddings Alone to Represent Natural Language Sequences

no code implementations ICLR 2018 Dinghan Shen, Guoyin Wang, Wenlin Wang, Martin Renqiang Min, Qinliang Su, Yizhe Zhang, Ricardo Henao, Lawrence Carin

In this paper, we conduct an extensive comparative study between Simple Word Embeddings-based Models (SWEMs), with no compositional parameters, relative to employing word embeddings within RNN/CNN-based models.

Sentence Word Embeddings

Learning K-way D-dimensional Discrete Code For Compact Embedding Representations

no code implementations8 Nov 2017 Ting Chen, Martin Renqiang Min, Yizhou Sun

Conventional embedding methods directly associate each symbol with a continuous embedding vector, which is equivalent to applying linear transformation based on "one-hot" encoding of the discrete symbols.

Language Modelling

Parametric t-Distributed Stochastic Exemplar-centered Embedding

no code implementations14 Oct 2017 Martin Renqiang Min, Hongyu Guo, Dinghan Shen

Parametric embedding methods such as parametric t-SNE (pt-SNE) have been widely adopted for data visualization and out-of-sample data embedding without further computationally expensive optimization or approximation.

Data Visualization

Exemplar-Centered Supervised Shallow Parametric Data Embedding

no code implementations21 Feb 2017 Martin Renqiang Min, Hongyu Guo, Dongjin Song

Our strategy learns a shallow high-order parametric embedding function and compares training/test data only with learned or precomputed exemplars, resulting in a cost function with linear computational complexity for both training and testing.

Dimensionality Reduction General Classification +3

A Context-aware Attention Network for Interactive Question Answering

no code implementations22 Dec 2016 Huayu Li, Martin Renqiang Min, Yong Ge, Asim Kadav

Employing these attention mechanisms, our model accurately understands when it can output an answer or when it requires generating a supplementary question for additional input depending on different contexts.

Question Answering Sentence

Adaptive Feature Abstraction for Translating Video to Text

no code implementations23 Nov 2016 Yunchen Pu, Martin Renqiang Min, Zhe Gan, Lawrence Carin

Previous models for video captioning often use the output from a specific layer of a Convolutional Neural Network (CNN) as video features.

Video Captioning

A Shallow High-Order Parametric Approach to Data Visualization and Compression

no code implementations16 Aug 2016 Martin Renqiang Min, Hongyu Guo, Dongjin Song

These exemplars in combination with the feature mapping learned by HOPE effectively capture essential data variations.

Computational Efficiency Data Visualization +4

Accelerating Deep Neural Network Training with Inconsistent Stochastic Gradient Descent

no code implementations17 Mar 2016 Linnan Wang, Yi Yang, Martin Renqiang Min, Srimat Chakradhar

Then we present the study of ISGD batch size to the learning rate, parallelism, synchronization cost, system saturation and scalability.

A Deep Learning Model for Structured Outputs with High-order Interaction

no code implementations29 Apr 2015 Hongyu Guo, Xiaodan Zhu, Martin Renqiang Min

Many real-world applications are associated with structured data, where not only input but also output has interplay.

Classification General Classification +2

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