Search Results for author: Qi Feng

Found 33 papers, 17 papers with code

Fisher information dissipation for time inhomogeneous stochastic differential equations

no code implementations1 Feb 2024 Qi Feng, Xinzhe Zuo, Wuchen Li

We also verify the convergence condition for the underdamped Langevin dynamics.

Reconfigurable Intelligent Surface-Enabled Array Radar for Interference Mitigation

no code implementations20 Jan 2024 Shengyao Chen, Qi Feng, Longyao Ran, Feng Xi, Zhong Liu

To maximize the output signal-to-interference-plus-noise ratio (SINR) of receive array, we formulate the codesign of transmit beamforming and RIS-assisted receive beamforming into a nonconvex constrained fractional programming problem, and then propose an alternating minimization-based algorithm to jointly optimize the transmitor beamfmer, receive beamformer and RIS reflection coefficients.

Reflected Schrödinger Bridge for Constrained Generative Modeling

no code implementations6 Jan 2024 Wei Deng, Yu Chen, Nicole Tianjiao Yang, Hengrong Du, Qi Feng, Ricky T. Q. Chen

Diffusion models have become the go-to method for large-scale generative models in real-world applications.

Pointing out Human Answer Mistakes in a Goal-Oriented Visual Dialogue

no code implementations19 Sep 2023 Ryosuke Oshima, Seitaro Shinagawa, Hideki Tsunashima, Qi Feng, Shigeo Morishima

Effective communication between humans and intelligent agents has promising applications for solving complex problems.

Language Modelling

Enhancing Perception and Immersion in Pre-Captured Environments through Learning-Based Eye Height Adaptation

no code implementations24 Aug 2023 Qi Feng, Hubert P. H. Shum, Shigeo Morishima

To explore this influence, we first propose a pilot study that captures real environments with multiple eye heights and asks participants to judge the egocentric distances and immersion.

Semantic Segmentation

Improving the Gap in Visual Speech Recognition Between Normal and Silent Speech Based on Metric Learning

no code implementations23 May 2023 Sara Kashiwagi, Keitaro Tanaka, Qi Feng, Shigeo Morishima

This paper presents a novel metric learning approach to address the performance gap between normal and silent speech in visual speech recognition (VSR).

Metric Learning speech-recognition +1

The 7th AI City Challenge

no code implementations15 Apr 2023 Milind Naphade, Shuo Wang, David C. Anastasiu, Zheng Tang, Ming-Ching Chang, Yue Yao, Liang Zheng, Mohammed Shaiqur Rahman, Meenakshi S. Arya, Anuj Sharma, Qi Feng, Vitaly Ablavsky, Stan Sclaroff, Pranamesh Chakraborty, Sanjita Prajapati, Alice Li, Shangru Li, Krishna Kunadharaju, Shenxin Jiang, Rama Chellappa

The AI City Challenge's seventh edition emphasizes two domains at the intersection of computer vision and artificial intelligence - retail business and Intelligent Traffic Systems (ITS) - that have considerable untapped potential.


Non-reversible Parallel Tempering for Deep Posterior Approximation

no code implementations20 Nov 2022 Wei Deng, Qian Zhang, Qi Feng, Faming Liang, Guang Lin

Notably, in big data scenarios, we obtain an appealing communication cost $O(P\log P)$ based on the optimal window size.

AIA: Attention in Attention Within Collaborate Domains

1 code implementation Pattern Recognition and Computer Vision 2022 Le Zhang, Qi Feng, Yao Lu, Chang Liu, and Guangming Lu

Attention mechanisms can effectively improve the performance of the mobile networks with a limited computational complexity cost.

Deep Attention Position

Efficient CNN Architecture Design Guided by Visualization

1 code implementation21 Jul 2022 Liangqi Zhang, Haibo Shen, Yihao Luo, Xiang Cao, Leixilan Pan, Tianjiang Wang, Qi Feng

Our VGNetG-1. 0MP achieves 67. 7% top-1 accuracy with 0. 99M parameters and 69. 2% top-1 accuracy with 1. 14M parameters on ImageNet classification dataset.

Image Classification

Self-supervised Implicit Glyph Attention for Text Recognition

1 code implementation CVPR 2023 Tongkun Guan, Chaochen Gu, Jingzheng Tu, Xue Yang, Qi Feng, Yudi Zhao, Xiaokang Yang, Wei Shen

Supervised attention can alleviate the above issue, but it is character category-specific, which requires extra laborious character-level bounding box annotations and would be memory-intensive when handling languages with larger character categories.

Scene Text Recognition Text Segmentation

360 Depth Estimation in the Wild -- The Depth360 Dataset and the SegFuse Network

1 code implementation16 Feb 2022 Qi Feng, Hubert P. H. Shum, Shigeo Morishima

In this work, we first establish a large-scale dataset with varied settings called Depth360 to tackle the training data problem.

Autonomous Driving Depth Estimation +2

Rethinking the Data Annotation Process for Multi-view 3D Pose Estimation with Active Learning and Self-Training

1 code implementation27 Dec 2021 Qi Feng, Kun He, He Wen, Cem Keskin, Yuting Ye

Notably, on CMU Panoptic Studio, we are able to reduce the turn-around time by 60% and annotation cost by 80% when compared to the conventional annotation process.

3D Pose Estimation Active Learning +1

Industrial Scene Text Detection with Refined Feature-attentive Network

1 code implementation25 Oct 2021 Tongkun Guan, Chaochen Gu, Changsheng Lu, Jingzheng Tu, Qi Feng, Kaijie Wu, Xinping Guan

Then, an attentive refinement network is developed by the attention map to rectify the location deviation of candidate boxes.

Scene Text Detection Text Detection

Abnormal Occupancy Grid Map Recognition using Attention Network

1 code implementation18 Oct 2021 Fuqin Deng, Hua Feng, Mingjian Liang, Qi Feng, Ningbo Yi, Yong Yang, Yuan Gao, Junfeng Chen, Tin Lun Lam

The occupancy grid map is a critical component of autonomous positioning and navigation in the mobile robotic system, as many other systems' performance depends heavily on it.

Non-reversible Parallel Tempering for Uncertainty Approximation in Deep Learning

no code implementations29 Sep 2021 Wei Deng, Qian Zhang, Qi Feng, Faming Liang, Guang Lin

Parallel tempering (PT), also known as replica exchange, is the go-to workhorse for simulations of multi-modal distributions.

Deep Signature FBSDE Algorithm

no code implementations24 Aug 2021 Qi Feng, Man Luo, Zhaoyu Zhang

We propose a deep signature/log-signature FBSDE algorithm to solve forward-backward stochastic differential equations (FBSDEs) with state and path dependent features.

Dynamic Multi-Scale Loss Optimization for Object Detection

no code implementations9 Aug 2021 Yihao Luo, Xiang Cao, Juntao Zhang, Peng Cheng, Tianjiang Wang, Qi Feng

With the continuous improvement of the performance of object detectors via advanced model architectures, imbalance problems in the training process have received more attention.

Object object-detection +1

CE-FPN: Enhancing Channel Information for Object Detection

1 code implementation19 Mar 2021 Yihao Luo, Juntao Zhang, Xiang Cao, Jingjuan Guo, Haibo Shen, Tianjiang Wang, Qi Feng

Instead of the original 1x1 convolution and linear upsampling, it mitigates the information loss due to channel reduction.

Miscellaneous Object +2

CityFlow-NL: Tracking and Retrieval of Vehicles at City Scale by Natural Language Descriptions

1 code implementation12 Jan 2021 Qi Feng, Vitaly Ablavsky, Stan Sclaroff

In this paper, we focus on two foundational tasks: the Vehicle Retrieval by NL task and the Vehicle Tracking by NL task, which take advantage of the proposed CityFlow-NL benchmark and provide a strong basis for future research on the multi-target multi-camera tracking by NL description task.

Multi-Object Tracking Retrieval +1

Dynamic Curves for Decentralized Autonomous Cryptocurrency Exchanges

no code implementations7 Jan 2021 Bhaskar Krishnamachari, Qi Feng, Eugenio Grippo

In particular, dramatic market price changes can result in low liquidity with respect to one or more of the assets and reduce the total value of the LP.

Entropy dissipation for some non-reversible stochastic differential equations

no code implementations16 Nov 2020 Qi Feng, Wuchen Li

We formulate explicit bounds to guarantee the exponential dissipation for some non-gradient stochastic differential equations towards their invariant distributions.

Probability Dynamical Systems Optimization and Control

Accelerating Convergence of Replica Exchange Stochastic Gradient MCMC via Variance Reduction

1 code implementation ICLR 2021 Wei Deng, Qi Feng, Georgios Karagiannis, Guang Lin, Faming Liang

Replica exchange stochastic gradient Langevin dynamics (reSGLD) has shown promise in accelerating the convergence in non-convex learning; however, an excessively large correction for avoiding biases from noisy energy estimators has limited the potential of the acceleration.

Non-convex Learning via Replica Exchange Stochastic Gradient MCMC

2 code implementations ICML 2020 Wei Deng, Qi Feng, Liyao Gao, Faming Liang, Guang Lin

Replica exchange Monte Carlo (reMC), also known as parallel tempering, is an important technique for accelerating the convergence of the conventional Markov Chain Monte Carlo (MCMC) algorithms.

Ranked #77 on Image Classification on CIFAR-100 (using extra training data)

Image Classification

SiamSNN: Siamese Spiking Neural Networks for Energy-Efficient Object Tracking

no code implementations17 Mar 2020 Yihao Luo, Min Xu, Caihong Yuan, Xiang Cao, Liangqi Zhang, Yan Xu, Tianjiang Wang, Qi Feng

Recently spiking neural networks (SNNs), the third-generation of neural networks has shown remarkable capabilities of energy-efficient computing, which is a promising alternative for deep neural networks (DNNs) with high energy consumption.

Image Classification Visual Object Tracking

Siamese Natural Language Tracker: Tracking by Natural Language Descriptions with Siamese Trackers

1 code implementation CVPR 2021 Qi Feng, Vitaly Ablavsky, Qinxun Bai, Stan Sclaroff

We propose a novel Siamese Natural Language Tracker (SNLT), which brings the advancements in visual tracking to the tracking by natural language (NL) descriptions task.

Region Proposal Visual Object Tracking +1

Learning to Separate: Detecting Heavily-Occluded Objects in Urban Scenes

1 code implementation ECCV 2020 Chenhongyi Yang, Vitaly Ablavsky, Kaihong Wang, Qi Feng, Margrit Betke

While visual object detection with deep learning has received much attention in the past decade, cases when heavy intra-class occlusions occur have not been studied thoroughly.

object-detection Object Detection +1

Real-time Visual Object Tracking with Natural Language Description

no code implementations26 Jul 2019 Qi Feng, Vitaly Ablavsky, Qinxun Bai, Guorong Li, Stan Sclaroff

In benchmarks, our method is competitive with state of the art trackers, while it outperforms all other trackers on targets with unambiguous and precise language annotations.

Object Visual Object Tracking

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