Search Results for author: Hui Cheng

Found 22 papers, 8 papers with code

OmniGS: Omnidirectional Gaussian Splatting for Fast Radiance Field Reconstruction using Omnidirectional Images

no code implementations4 Apr 2024 Longwei Li, Huajian Huang, Sai-Kit Yeung, Hui Cheng

In this paper, we present OmniGS, a novel omnidirectional Gaussian splatting system, to take advantage of omnidirectional images for fast radiance field reconstruction.

FedDiv: Collaborative Noise Filtering for Federated Learning with Noisy Labels

1 code implementation19 Dec 2023 Jichang Li, Guanbin Li, Hui Cheng, Zicheng Liao, Yizhou Yu

However, these prior methods do not learn noise filters by exploiting knowledge across all clients, leading to sub-optimal and inferior noise filtering performance and thus damaging training stability.

Federated Learning Learning with noisy labels +1

360Loc: A Dataset and Benchmark for Omnidirectional Visual Localization with Cross-device Queries

no code implementations29 Nov 2023 Huajian Huang, Changkun Liu, Yipeng Zhu, Hui Cheng, Tristan Braud, Sai-Kit Yeung

We propose a virtual camera approach to generate lower-FoV query frames from 360$^\circ$ images, which ensures a fair comparison of performance among different query types in visual localization tasks.

Visual Localization

Photo-SLAM: Real-time Simultaneous Localization and Photorealistic Mapping for Monocular, Stereo, and RGB-D Cameras

1 code implementation28 Nov 2023 Huajian Huang, Longwei Li, Hui Cheng, Sai-Kit Yeung

In addition to actively densifying hyper primitives based on geometric features, we further introduce a Gaussian-Pyramid-based training method to progressively learn multi-level features, enhancing photorealistic mapping performance.

Neural Rendering

Improving Knowledge Distillation via Transferring Learning Ability

1 code implementation24 Apr 2023 Long Liu, Tong Li, Hui Cheng

Existing knowledge distillation methods generally use a teacher-student approach, where the student network solely learns from a well-trained teacher.

Knowledge Distillation

Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning

2 code implementations12 Nov 2022 Ziyi Zhang, Weikai Chen, Hui Cheng, Zhen Li, Siyuan Li, Liang Lin, Guanbin Li

We investigate a practical domain adaptation task, called source-free domain adaptation (SFUDA), where the source-pretrained model is adapted to the target domain without access to the source data.

Contrastive Learning Source-Free Domain Adaptation

Less is More: Adaptive Curriculum Learning for Thyroid Nodule Diagnosis

1 code implementation2 Jul 2022 Haifan Gong, Hui Cheng, Yifan Xie, Shuangyi Tan, Guanqi Chen, Fei Chen, Guanbin Li

Thyroid nodule classification aims at determining whether the nodule is benign or malignant based on a given ultrasound image.


Safe Learning-based Gradient-free Model Predictive Control Based on Cross-entropy Method

no code implementations24 Feb 2021 Lei Zheng, Rui Yang, Zhixuan Wu, Jiesen Panb, Hui Cheng

In this paper, a safe and learning-based control framework for model predictive control (MPC) is proposed to optimize nonlinear systems with a non-differentiable objective function under uncertain environmental disturbances.

Gaussian Processes Robotics

MetaGrasp: Data Efficient Grasping by Affordance Interpreter Network

no code implementations18 Feb 2019 Junhao Cai, Hui Cheng, Zhanpeng Zhang, Jingcheng Su

Although the model is trained using only RGB image, when changing the background textures, it also performs well and can achieve even 94% accuracy on the set of adversarial objects, which outperforms current state-of-the-art methods.

Deep Reasoning with Knowledge Graph for Social Relationship Understanding

1 code implementation2 Jul 2018 Zhouxia Wang, Tianshui Chen, Jimmy Ren, Weihao Yu, Hui Cheng, Liang Lin

And this structured knowledge can be efficiently integrated into the deep neural network architecture to promote social relationship understanding by an end-to-end trainable Graph Reasoning Model (GRM), in which a propagation mechanism is learned to propagate node message through the graph to explore the interaction between persons of interest and the contextual objects.

Visual Social Relationship Recognition

Recurrent 3D Pose Sequence Machines

no code implementations CVPR 2017 Mude Lin, Liang Lin, Xiaodan Liang, Keze Wang, Hui Cheng

3D human articulated pose recovery from monocular image sequences is very challenging due to the diverse appearances, viewpoints, occlusions, and also the human 3D pose is inherently ambiguous from the monocular imagery.

3D Human Pose Estimation 3D Pose Estimation

Knowledge-Guided Recurrent Neural Network Learning for Task-Oriented Action Prediction

no code implementations15 Jul 2017 Liang Lin, Lili Huang, Tianshui Chen, Yukang Gan, Hui Cheng

This paper aims at task-oriented action prediction, i. e., predicting a sequence of actions towards accomplishing a specific task under a certain scene, which is a new problem in computer vision research.

Common Sense Reasoning valid

Human Pose Estimation from Depth Images via Inference Embedded Multi-task Learning

no code implementations13 Aug 2016 Keze Wang, Shengfu Zhai, Hui Cheng, Xiaodan Liang, Liang Lin

In this paper, we propose a novel inference-embedded multi-task learning framework for predicting human pose from still depth images, which is implemented with a deep architecture of neural networks.

Multi-Task Learning Pose Estimation +1

LSTM-CF: Unifying Context Modeling and Fusion with LSTMs for RGB-D Scene Labeling

1 code implementation18 Apr 2016 Zhen Li, Yukang Gan, Xiaodan Liang, Yizhou Yu, Hui Cheng, Liang Lin

Another long short-term memorized fusion layer is set up to integrate the contexts along the vertical direction from different channels, and perform bi-directional propagation of the fused vertical contexts along the horizontal direction to obtain true 2D global contexts.

Scene Labeling

Zero-Shot Event Detection by Multimodal Distributional Semantic Embedding of Videos

no code implementations2 Dec 2015 Mohamed Elhoseiny, Jingen Liu, Hui Cheng, Harpreet Sawhney, Ahmed Elgammal

To our knowledge, this is the first Zero-Shot event detection model that is built on top of distributional semantics and extends it in the following directions: (a) semantic embedding of multimodal information in videos (with focus on the visual modalities), (b) automatically determining relevance of concepts/attributes to a free text query, which could be useful for other applications, and (c) retrieving videos by free text event query (e. g., "changing a vehicle tire") based on their content.

Event Detection

Depth Extraction from Videos Using Geometric Context and Occlusion Boundaries

no code implementations25 Oct 2015 S. Hussain Raza, Omar Javed, Aveek Das, Harpreet Sawhney, Hui Cheng, Irfan Essa

We propose to learn and infer depth in videos from appearance, motion, occlusion boundaries, and geometric context of the scene.

Depth Estimation Pose Estimation

Cluster Synchronization of Coupled Systems with Nonidentical Linear Dynamics

no code implementations26 Feb 2015 Zhongchang Liu, Wing Shing Wong, Hui Cheng

This paper considers the cluster synchronization problem of generic linear dynamical systems whose system models are distinct in different clusters.

Pedestrian Detection in Low-resolution Imagery by Learning Multi-scale Intrinsic Motion Structures (MIMS)

no code implementations CVPR 2014 Jiejie Zhu, Omar Javed, Jingen Liu, Qian Yu, Hui Cheng, Harpreet Sawhney

In this paper, we give a comparative evaluation of the proposed method and demonstrate that MIMS outperforms the state of the art approaches in identifying pedestrians from low resolution airborne videos.

Optical Flow Estimation Pedestrian Detection

3D Visual Proxemics: Recognizing Human Interactions in 3D from a Single Image

no code implementations CVPR 2013 Ishani Chakraborty, Hui Cheng, Omar Javed

g Unlike previous approaches that directly map people/face locations in 2D image space into features for classification, we first estimate camera viewpoint and people positions in 3D space and then extract spatial configuration features from explicit 3D people positions.

General Classification

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