Search Results for author: Qi Zhao

Found 87 papers, 35 papers with code

Deep Reinforcement Learning Enabled Joint Deployment and Beamforming in STAR-RIS Assisted Networks

no code implementations7 Sep 2023 Zhuoyuan Ma, Qi Zhao, Bai Yan, Jin Zhang

The paper constructs a STAR-RIS assisted multi-user multiple-input single-output (MU-MISO) mobile wireless network and jointly optimizes the dynamic deployment strategy of STAR-RIS and the hybrid beamforming strategy to maximize the long-term total communication rate of users.

Decision Making

AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?

no code implementations31 Jul 2023 Qi Zhao, Ce Zhang, Shijie Wang, Changcheng Fu, Nakul Agarwal, Kwonjoon Lee, Chen Sun

We propose to formulate the LTA task from two perspectives: a bottom-up approach that predicts the next actions autoregressively by modeling temporal dynamics; and a top-down approach that infers the goal of the actor and plans the needed procedure to accomplish the goal.

Action Anticipation Long Term Action Anticipation

Change Detection Methods for Remote Sensing in the Last Decade: A Comprehensive Review

no code implementations9 May 2023 Guangliang Cheng, Yunmeng Huang, Xiangtai Li, Shuchang Lyu, Zhaoyang Xu, Qi Zhao, Shiming Xiang

We first introduce some preliminary knowledge for the change detection task, such as problem definition, datasets, evaluation metrics, and transformer basics, as well as provide a detailed taxonomy of existing algorithms from three different perspectives: algorithm granularity, supervision modes, and learning frameworks in the methodology section.

Change Detection Change detection for remote sensing images

DNeRV: Modeling Inherent Dynamics via Difference Neural Representation for Videos

no code implementations CVPR 2023 Qi Zhao, M. Salman Asif, Zhan Ma

DNeRV achieves competitive results against the state-of-the-art neural compression approaches and outperforms existing implicit methods on downstream inpainting and interpolation for $960 \times 1920$ videos.

Video Compression

Cooperative Coevolution for Non-Separable Large-Scale Black-Box Optimization: Convergence Analyses and Distributed Accelerations

1 code implementation11 Apr 2023 Qiqi Duan, Chang Shao, Guochen Zhou, Haobin Yang, Qi Zhao, Yuhui Shi

Given the ubiquity of non-separable optimization problems in real worlds, in this paper we analyze and extend the large-scale version of the well-known cooperative coevolution (CC), a divide-and-conquer optimization framework, on non-separable functions.

Distributed Computing

Divide and Conquer: Answering Questions with Object Factorization and Compositional Reasoning

1 code implementation CVPR 2023 Shi Chen, Qi Zhao

They have yet to develop the capability to address novel objects or spurious biases in real-world scenarios, and also fall short of interpreting the rationales behind their decisions.

Decision Making Visual Reasoning

AutoOptLib: A Library of Automatically Designing Metaheuristic Optimization Algorithms in MATLAB

1 code implementation12 Mar 2023 Qi Zhao, Bai Yan, Taiwei Hu, Xianglong Chen, Yuhui Shi

Metaheuristic algorithms are widely-recognized solvers for challenging optimization problems with multi-modality, discretization, large-scale, multi-objectivity, etc.

Metaheuristic Optimization

A Survey on Automated Design of Metaheuristic Algorithms

no code implementations12 Mar 2023 Qi Zhao, Qiqi Duan, Bai Yan, Shi Cheng, Yuhui Shi

In the survey, we first present the concept of automated design of metaheuristic algorithms and provide a taxonomy by abstracting the automated design process into four parts, i. e., design space, design strategies, performance evaluation strategies, and targeted problems.

Self-Training Guided Disentangled Adaptation for Cross-Domain Remote Sensing Image Semantic Segmentation

1 code implementation13 Jan 2023 Qi Zhao, Shuchang Lyu, Binghao Liu, Lijiang Chen, Hongbo Zhao

We first propose source student backbone and target student backbone to respectively extract the source-style and target-style feature for both source and target images.

Semantic Segmentation

Improved Pump Setpoint Selection Using a Calibrated Hydraulic Model of a High-Pressure Irrigation System

no code implementations26 Aug 2022 Ye Wang, Qi Zhao, Wenyan Wu, Ailsa Willis, Angus R. Simpson, Erik Weyer

This paper presents a case study of the operational management of the Robinvale high-pressure piped irrigation water delivery system (RVHPS) in Australia.


A Multi-Modality Ovarian Tumor Ultrasound Image Dataset for Unsupervised Cross-Domain Semantic Segmentation

1 code implementation14 Jul 2022 Qi Zhao, Shuchang Lyu, Wenpei Bai, Linghan Cai, Binghao Liu, Meijing Wu, Xiubo Sang, Min Yang, Lijiang Chen

To solve this problem, we propose a Multi-Modality Ovarian Tumor Ultrasound (MMOTU) image dataset containing 1469 2d ultrasound images and 170 contrast enhanced ultrasonography (CEUS) images with pixel-wise and global-wise annotations.

Domain Adaptation Tumor Segmentation

Attention in Reasoning: Dataset, Analysis, and Modeling

1 code implementation20 Apr 2022 Shi Chen, Ming Jiang, Jinhui Yang, Qi Zhao

In this work, we propose an Attention with Reasoning capability (AiR) framework that uses attention to understand and improve the process leading to task outcomes.

Question Answering Visual Question Answering

Efficient and practical quantum compiler towards multi-qubit systems with deep reinforcement learning

no code implementations14 Apr 2022 Qiuhao Chen, Yuxuan Du, Qi Zhao, Yuling Jiao, Xiliang Lu, Xingyao Wu

We systematically evaluate the performance of our proposal in compiling quantum operators with both inverse-closed and inverse-free universal basis sets.

Q-Learning reinforcement-learning +1

AutoOpt: A General Framework for Automatically Designing Metaheuristic Optimization Algorithms with Diverse Structures

1 code implementation3 Apr 2022 Qi Zhao, Bai Yan, Xianglong Chen, Taiwei Hu, Shi Cheng, Yuhui Shi

However, the specific algorithm prototype and linear algorithm representation in the current automated design pipeline restrict the design within a fixed algorithm structure, which hinders discovering novelties and diversity across the metaheuristic family.

Metaheuristic Optimization

Artificial Intelligence Enables Real-Time and Intuitive Control of Prostheses via Nerve Interface

no code implementations16 Mar 2022 Diu Khue Luu, Anh Tuan Nguyen, Ming Jiang, Markus W. Drealan, Jian Xu, Tong Wu, Wing-kin Tam, Wenfeng Zhao, Brian Z. H. Lim, Cynthia K. Overstreet, Qi Zhao, Jonathan Cheng, Edward W. Keefer, Zhi Yang

Objective: The next generation prosthetic hand that moves and feels like a real hand requires a robust neural interconnection between the human minds and machines.

REX: Reasoning-aware and Grounded Explanation

1 code implementation CVPR 2022 Shi Chen, Qi Zhao

Finally, with our new data and method, we perform extensive analyses to study the effectiveness of our explanation under different settings, including multi-task learning and transfer learning.

Decision Making Explanation Generation +3

Speckle-based optical cryptosystem and its application for human face recognition via deep learning

no code implementations26 Jan 2022 Qi Zhao, Huanhao Li, Zhipeng Yu, Chi Man Woo, Tianting Zhong, Shengfu Cheng, Yuanjin Zheng, Honglin Liu, Jie Tian, Puxiang Lai

A scattering ground glass is exploited to generate physical secret keys of gigabit length and encrypt face images via seemingly random optical speckles at light speed.

Face Recognition

Learning to Minimize the Remainder in Supervised Learning

1 code implementation23 Jan 2022 Yan Luo, Yongkang Wong, Mohan S. Kankanhalli, Qi Zhao

To this end, we propose a new learning approach, namely gradient adjustment learning (GAL), to leverage the knowledge learned from the past training iterations to adjust vanilla gradients, such that the remainders are minimized and the approximations are improved.

Image Classification Image Retrieval +3

Learning to Predict Gradients for Semi-Supervised Continual Learning

1 code implementation23 Jan 2022 Yan Luo, Yongkang Wong, Mohan Kankanhalli, Qi Zhao

To explore these issues, we formulate a new semi-supervised continual learning method, which can be generically applied to existing continual learning models.

Continual Learning

VisualHow: Multimodal Problem Solving

1 code implementation CVPR 2022 Jinhui Yang, Xianyu Chen, Ming Jiang, Shi Chen, Louis Wang, Qi Zhao

With an overarching goal of developing intelligent systems to assist humans in various daily activities, we propose VisualHow, a free-form and open-ended research that focuses on understanding a real-life problem and deriving its solution by incorporating key components across multiple modalities.

Query and Attention Augmentation for Knowledge-Based Explainable Reasoning

1 code implementation CVPR 2022 Yifeng Zhang, Ming Jiang, Qi Zhao

Explainable visual question answering (VQA) models have been developed with neural modules and query-based knowledge incorporation to answer knowledge-requiring questions.

Question Answering Visual Question Answering

NN-Baker: A Neural-network Infused Algorithmic Framework for Optimization Problems on Geometric Intersection Graphs

no code implementations NeurIPS 2021 Evan McCarty, Qi Zhao, Anastasios Sidiropoulos, Yusu Wang

This leads to a mixed algorithmic-ML framework, which we call NN-Baker that has the capacity to approximately solve a family of graph optimization problems (e. g, maximum independent set and minimum vertex cover) in time linear to input graph size, and only polynomial to approximation parameter.

Combinatorial Optimization

Attention-based Feature Decomposition-Reconstruction Network for Scene Text Detection

no code implementations29 Nov 2021 Qi Zhao, YuFei Wang, Shuchang Lyu, Lijiang Chen

In this paper, we propose attention-based feature decomposition-reconstruction network for scene text detection, which utilizes contextual information and low-level feature to enhance the performance of segmentation-based text detector.

Scene Text Detection Text Detection

ezcox: An R/CRAN Package for Cox Model Batch Processing and Visualization

1 code implementation27 Oct 2021 Shixiang Wang, Xue-Song Liu, Jianfeng Li, Qi Zhao

Cox analysis is a common clinical data analysis technique to link valuable variables to clinical outcomes including dead and relapse.

A Feature Consistency Driven Attention Erasing Network for Fine-Grained Image Retrieval

no code implementations9 Oct 2021 Qi Zhao, Xu Wang, Shuchang Lyu, Binghao Liu, Yifan Yang

To handle these two issues, we propose a feature consistency driven attention erasing network (FCAENet) for fine-grained image retrieval.

Image Retrieval Retrieval

Learning to Predict Trustworthiness with Steep Slope Loss

1 code implementation NeurIPS 2021 Yan Luo, Yongkang Wong, Mohan S. Kankanhalli, Qi Zhao

Secondly, due to the data complexity, it is challenging to differentiate the incorrect predictions from the correct ones on real-world large-scale datasets.

Hybrid Beamforming for RIS-Aided Communications: Fitness Landscape Analysis and Niching Genetic Algorithm

no code implementations19 Sep 2021 Bai Yan, Qi Zhao, Jin Zhang, J. Andrew Zhang, Xin Yao

To investigate the number and distribution of local optima, we conduct a fitness landscape analysis on the sum rate maximization problems.

Empirical Study of Named Entity Recognition Performance Using Distribution-aware Word Embedding

no code implementations3 Sep 2021 Xin Chen, Qi Zhao, Xinyang Liu

And the result shows that the performance of NER will be improved if the word specificity is incorporated into existing NER methods.

named-entity-recognition Named Entity Recognition +2

Leveraging Human Attention in Novel Object Captioning

1 code implementation Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence 2021 Xianyu Chen, Ming Jiang, Qi Zhao

Image captioning models depend on training with paired image-text corpora, which poses various challenges in describing images containing novel objects absent from the training data.

Image Captioning

A Self-Distillation Embedded Supervised Affinity Attention Model for Few-Shot Segmentation

1 code implementation14 Aug 2021 Qi Zhao, Binghao Liu, Shuchang Lyu, Huojin Chen

To deal with the above two issues, we propose self-distillation embedded supervised affinity attention model to improve the performance of few-shot segmentation task.

Few-Shot Semantic Segmentation Semantic Segmentation

Predicting Human Scanpaths in Visual Question Answering

1 code implementation CVPR 2021 Xianyu Chen, Ming Jiang, Qi Zhao

Conditioned on a task guidance map, the proposed model learns question-specific attention patterns to generate scanpaths.

Question Answering Scanpath prediction +2

Explicit Knowledge Incorporation for Visual Reasoning

no code implementations CVPR 2021 Yifeng Zhang, Ming Jiang, Qi Zhao

Existing explainable and explicit visual reasoning methods only perform reasoning based on visual evidence but do not take into account knowledge beyond what is in the visual scene.

Visual Reasoning

Multiobjective Bilevel Evolutionary Approach for Off-Grid Direction-of-Arrival Estimation

no code implementations14 Jun 2021 Bai Yan, Qi Zhao, Jin Zhang, J. Andrew Zhang, Xin Yao

We formulate a multiobjective off-grid DOA estimation model to realize this idea, by which the source number can be automatically identified together with DOA estimation.

Direction of Arrival Estimation

Evolutionary Robust Clustering Over Time for Temporal Data

no code implementations14 Jun 2021 Qi Zhao, Bai Yan, Yuhui Shi

In many clustering scenes, data samples' attribute values change over time.


Gridless Evolutionary Approach for Line Spectral Estimation with Unknown Model Order

no code implementations14 Jun 2021 Bai Yan, Qi Zhao, Jin Zhang, J. Andrew Zhang, Xin Yao

To overcome the above shortcomings of relaxation, we propose a novel idea of simultaneously estimating the frequencies and model order by means of the atomic $l_0$ norm.

Multiobjective Optimization

A Portable, Self-Contained Neuroprosthetic Hand with Deep Learning-Based Finger Control

no code implementations24 Mar 2021 Anh Tuan Nguyen, Markus W. Drealan, Diu Khue Luu, Ming Jiang, Jian Xu, Jonathan Cheng, Qi Zhao, Edward W. Keefer, Zhi Yang

This enables the implementation of the neuroprosthetic hand as a portable and self-contained unit with real-time control of individual finger movements.


Embedded Knowledge Distillation in Depth-Level Dynamic Neural Network

no code implementations1 Mar 2021 Qi Zhao, Shuchang Lyu, Zhiwei Zhang, Ting-Bing Xu, Guangliang Cheng

In real applications, different computation-resource devices need different-depth networks (e. g., ResNet-18/34/50) with high-accuracy.

Knowledge Distillation Transfer Learning

Self-Distillation for Few-Shot Image Captioning

1 code implementation IEEE Winter Conference on Applications of Computer Vision 2021 Xianyu Chen, Ming Jiang, Qi Zhao

We propose an ensemble-based self-distillation method that allows image captioning models to be trained with unpaired images and captions.

Image Captioning

MM-FSOD: Meta and metric integrated few-shot object detection

no code implementations30 Dec 2020 Yuewen Li, Wenquan Feng, Shuchang Lyu, Qi Zhao, Xuliang Li

In this paper, we present an effective object detection framework (MM-FSOD) that integrates metric learning and meta-learning to tackle the few-shot object detection task.

Few-Shot Object Detection Meta-Learning +2

MGML: Multi-Granularity Multi-Level Feature Ensemble Network for Remote Sensing Scene Classification

no code implementations29 Dec 2020 Qi Zhao, Shuchang Lyu, Yuewen Li, Yujing Ma, Lijiang Chen

To avoid the interference from confusing information, we propose Multi-granularity Multi-Level Feature Ensemble Module (MGML-FEM) which can provide diverse predictions by full-channel feature generator (FC-FG).

Classification Ensemble Learning +2

One-shot dynamical resource theory

no code implementations4 Dec 2020 Xiao Yuan, Pei Zeng, Minbo Gao, Qi Zhao

Focusing on a general dynamical resource theory of quantum channels, here we consider tasks of one-shot resource distillation and dilution with a single copy of the resource.

Quantum Physics

A Deep Learning Framework for Predicting Digital Asset Price Movement from Trade-by-trade Data

no code implementations11 Oct 2020 Qi Zhao

Moreover, this study shows that the LSTM model could extract universal features from trade-by-trade data, as the learned parameters well maintain their high performance on other cryptocurrency instruments that were not included in training data.

Review of Machine-Learning Methods for RNA Secondary Structure Prediction

no code implementations1 Sep 2020 Qi Zhao, Zheng Zhao, Xiaoya Fan, Zhengwei Yuan, Qian Mao, YuDong Yao

Recently, with the increasing availability of RNA structure data, new methods based on machine-learning technologies, especially deep learning, have alleviated the issue.

BIG-bench Machine Learning

AiR: Attention with Reasoning Capability

1 code implementation ECCV 2020 Shi Chen, Ming Jiang, Jinhui Yang, Qi Zhao

In this work, we propose an Attention with Reasoning capability (AiR) framework that uses attention to understand and improve the process leading to task outcomes.

Saliency Prediction with External Knowledge

no code implementations27 Jul 2020 Yifeng Zhang, Ming Jiang, Qi Zhao

At the core of the method is a new Graph Semantic Saliency Network (GraSSNet) that constructs a graph that encodes semantic relationships learned from external knowledge.

Graph Attention Saliency Prediction

Leveraging Bottom-Up and Top-Down Attention for Few-Shot Object Detection

no code implementations23 Jul 2020 Xianyu Chen, Ming Jiang, Qi Zhao

Few-shot object detection aims at detecting objects with few annotated examples, which remains a challenging research problem yet to be explored.

Few-Shot Learning Few-Shot Object Detection +1

Representation Learning for Information Extraction from Form-like Documents

1 code implementation ACL 2020 Bodhisattwa Majumder, Navneet Potti, Sandeep Tata, James B. Wendt, Qi Zhao, Marc Najork

We propose a novel approach using representation learning for tackling the problem of extracting structured information from form-like document images.

Representation Learning

Active Learning for Skewed Data Sets

no code implementations23 May 2020 Abbas Kazerouni, Qi Zhao, Jing Xie, Sandeep Tata, Marc Najork

Furthermore, there is usually only a small amount of initial training data available when building machine-learned models to solve such problems.

Active Learning

GradMix: Multi-source Transfer across Domains and Tasks

no code implementations9 Feb 2020 Junnan Li, Ziwei Xu, Yongkang Wong, Qi Zhao, Mohan Kankanhalli

Therefore, it is important to develop algorithms that can leverage off-the-shelf labeled dataset to learn useful knowledge for the target task.

Action Recognition Meta-Learning +1

Direction Concentration Learning: Enhancing Congruency in Machine Learning

1 code implementation17 Dec 2019 Yan Luo, Yongkang Wong, Mohan S. Kankanhalli, Qi Zhao

We propose a Direction Concentration Learning (DCL) method to improve congruency in the learning process, where enhancing congruency influences the convergence path to be less circuitous.

Ranked #8 on Image Classification on Tiny ImageNet Classification (using extra training data)

BIG-bench Machine Learning Continual Learning +2

Human Annotations Improve GAN Performances

no code implementations15 Nov 2019 Juanyong Duan, Sim Heng Ong, Qi Zhao

Unlike previous paradigms that directly ask annotators to distinguish between real and fake data in a straightforward way, we propose and annotate a set of carefully designed attributes that encode important image information at various levels, to understand the differences between fake and real images.

Designing metabolic division of labor in microbial communities

1 code implementation30 Apr 2019 Meghan Thommes, Taiyao Wang, Qi Zhao, Ioannis C. Paschalidis, Daniel Segrè

Specifically, we searched for communities able to survive under constraints (such as a limited number of reactions) that would not be sustainable by individual species.

Learning metrics for persistence-based summaries and applications for graph classification

1 code implementation NeurIPS 2019 Qi Zhao, Yusu Wang

However often in practice, the choice of the weight function should depend on the nature of the specific type of data one considers, and it is thus highly desirable to learn a best weight function (and thus metric for persistence diagrams) from labelled data.

Graph Classification Computational Geometry

$\mathcal{G}$-softmax: Improving Intra-class Compactness and Inter-class Separability of Features

1 code implementation8 Apr 2019 Yan Luo, Yongkang Wong, Mohan Kankanhalli, Qi Zhao

In addition, analysis of the intra-class compactness and inter-class separability demonstrates the advantages of the proposed function over the softmax function, which is consistent with the performance improvement.

General Classification Multi-Label Classification

Boosted Attention: Leveraging Human Attention for Image Captioning

no code implementations ECCV 2018 Shi Chen, Qi Zhao

Visual attention has shown usefulness in image captioning, with the goal of enabling a caption model to selectively focus on regions of interest.

Image Captioning

Theory of variational quantum simulation

no code implementations20 Dec 2018 Xiao Yuan, Suguru Endo, Qi Zhao, Ying Li, Simon Benjamin

In this work, we introduce variational quantum simulation of mixed states under general stochastic evolution.

Quantum Physics

Learning to Learn from Noisy Labeled Data

1 code implementation CVPR 2019 Junnan Li, Yongkang Wong, Qi Zhao, Mohan Kankanhalli

Despite the success of deep neural networks (DNNs) in image classification tasks, the human-level performance relies on massive training data with high-quality manual annotations, which are expensive and time-consuming to collect.

Ranked #24 on Image Classification on Clothing1M (using extra training data)

Learning with noisy labels Meta-Learning

A high threshold code for modular hardware with asymmetric noise

no code implementations4 Dec 2018 Xiaosi Xu, Qi Zhao, Xiao Yuan, Simon C. Benjamin

We consider an approach to fault tolerant quantum computing based on a simple error detecting code operating as the substrate for a conventional surface code.

Quantum Physics

Unsupervised Learning of View-invariant Action Representations

1 code implementation NeurIPS 2018 Junnan Li, Yongkang Wong, Qi Zhao, Mohan S. Kankanhalli

Different from previous works in video representation learning, our unsupervised learning task is to predict 3D motion in multiple target views using video representation from a source view.

Action Recognition Representation Learning +1

Interact as You Intend: Intention-Driven Human-Object Interaction Detection

no code implementations29 Aug 2018 Bingjie Xu, Junnan Li, Yongkang Wong, Mohan S. Kankanhalli, Qi Zhao

The recent advances in instance-level detection tasks lay strong foundation for genuine comprehension of the visual scenes.

Human-Object Interaction Detection

Egocentric Spatial Memory

1 code implementation31 Jul 2018 Mengmi Zhang, Keng Teck Ma, Shih-Cheng Yen, Joo Hwee Lim, Qi Zhao, Jiashi Feng

Egocentric spatial memory (ESM) defines a memory system with encoding, storing, recognizing and recalling the spatial information about the environment from an egocentric perspective.

Feature Engineering

Video Storytelling: Textual Summaries for Events

no code implementations25 Jul 2018 Junnan Li, Yongkang Wong, Qi Zhao, Mohan S. Kankanhalli

Video storytelling introduces new challenges, mainly due to the diversity of the story and the length and complexity of the video.

Emotional Attention: A Study of Image Sentiment and Visual Attention

no code implementations CVPR 2018 Shaojing Fan, Zhiqi Shen, Ming Jiang, Bryan L. Koenig, Juan Xu, Mohan S. Kankanhalli, Qi Zhao

In this paper, we present the first study to focus on the relation between emotional properties of an image and visual attention.

Saliency Prediction

Advancing System Performance with Redundancy: From Biological to Artificial Designs

no code implementations14 Feb 2018 Anh Tuan Nguyen, Jian Xu, Diu Khue Luu, Qi Zhao, Zhi Yang

We envision that our theory would provide a framework for the future development of bio-inspired redundant artificial systems as well as assist the studies of the fundamental mechanisms governing various biological processes.

Egocentric Spatial Memory Network

no code implementations ICLR 2018 Mengmi Zhang, Keng Teck Ma, Joo Hwee Lim, Shih-Cheng Yen, Qi Zhao, Jiashi Feng

During the exploration, our proposed ESM network model updates belief of the global map based on local observations using a recurrent neural network.

Navigate Simultaneous Localization and Mapping

Learning Visual Attention to Identify People With Autism Spectrum Disorder

no code implementations ICCV 2017 Ming Jiang, Qi Zhao

This paper presents a novel method for quantitative and objective diagnoses of Autism Spectrum Disorder (ASD) using eye tracking and deep neural networks.

Attention Transfer from Web Images for Video Recognition

no code implementations3 Aug 2017 Junnan Li, Yongkang Wong, Qi Zhao, Mohan Kankanhalli

However, due to the domain shift problem, the performance of Web images trained deep classifiers tend to degrade when directly deployed to videos.

Action Recognition Temporal Action Localization +1

Dual-Glance Model for Deciphering Social Relationships

1 code implementation ICCV 2017 Junnan Li, Yongkang Wong, Qi Zhao, Mohan S. Kankanhalli

Since the beginning of early civilizations, social relationships derived from each individual fundamentally form the basis of social structure in our daily life.

object-detection Object Detection +2

Deep Future Gaze: Gaze Anticipation on Egocentric Videos Using Adversarial Networks

1 code implementation CVPR 2017 Mengmi Zhang, Keng Teck Ma, Joo Hwee Lim, Qi Zhao, Jiashi Feng

Through competition with discriminator, the generator progressively improves quality of the future frames and thus anticipates future gaze better.

Gaze Prediction

Dex: Incremental Learning for Complex Environments in Deep Reinforcement Learning

1 code implementation19 Jun 2017 Nick Erickson, Qi Zhao

This paper introduces Dex, a reinforcement learning environment toolkit specialized for training and evaluation of continual learning methods as well as general reinforcement learning problems.

Continual Learning General Reinforcement Learning +3

Foveation-based Mechanisms Alleviate Adversarial Examples

no code implementations19 Nov 2015 Yan Luo, Xavier Boix, Gemma Roig, Tomaso Poggio, Qi Zhao

To see this, first, we report results in ImageNet that lead to a revision of the hypothesis that adversarial perturbations are a consequence of CNNs acting as a linear classifier: CNNs act locally linearly to changes in the image regions with objects recognized by the CNN, and in other regions the CNN may act non-linearly.

Foveation Translation

SALICON: Saliency in Context

no code implementations CVPR 2015 Ming Jiang, Shengsheng Huang, Juanyong Duan, Qi Zhao

Saliency in Context (SALICON) is an ongoing effort that aims at understanding and predicting visual attention.

Saliency Prediction

Label Consistent Quadratic Surrogate Model for Visual Saliency Prediction

no code implementations CVPR 2015 Yan Luo, Yongkang Wong, Qi Zhao

In addition, since new datasets are built and shared in the community from time to time, it would be good not to retrain the entire model when new data are added.

Saliency Prediction

Learning of Proto-object Representations via Fixations on Low Resolution

no code implementations23 Dec 2014 Chengyao Shen, Xun Huang, Qi Zhao

Visualizations also show that these features are selective to potential objects in the scene and the responses of these features work well in predicting eye fixations on the images when combined with learned weights.

Noise Characterization, Modeling, and Reduction for In Vivo Neural Recording

no code implementations NeurIPS 2009 Zhi Yang, Qi Zhao, Edward Keefer, Wentai Liu

Multiple noise sources have been studied through analytical models as well as empirical measurements.

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