Search Results for author: Wei Hua

Found 21 papers, 10 papers with code

Roadside Monocular 3D Detection via 2D Detection Prompting

no code implementations1 Apr 2024 Yechi Ma, Shuoquan Wei, Churun Zhang, Wei Hua, Yanan Li, Shu Kong

Our method builds on a key insight that, compared with 3D detectors, a 2D detector is much easier to train and performs significantly better w. r. t detections on the 2D image plane.

Long-Tailed 3D Detection via 2D Late Fusion

no code implementations18 Dec 2023 Yechi Ma, Neehar Peri, Shuoquan Wei, Wei Hua, Deva Ramanan, Yanan Li, Shu Kong

Autonomous vehicles (AVs) must accurately detect objects from both common and rare classes for safe navigation, motivating the problem of Long-Tailed 3D Object Detection (LT3D).

3D Object Detection Autonomous Vehicles +2

Beyond Isolation: Multi-Agent Synergy for Improving Knowledge Graph Construction

1 code implementation5 Dec 2023 Hongbin Ye, Honghao Gui, Aijia Zhang, Tong Liu, Wei Hua, Weiqiang Jia

Knowledge graph construction (KGC) is a multifaceted undertaking involving the extraction of entities, relations, and events.

Event Extraction graph construction

Holistic Inverse Rendering of Complex Facade via Aerial 3D Scanning

no code implementations20 Nov 2023 Zixuan Xie, Rengan Xie, Rong Li, Kai Huang, Pengju Qiao, Jingsen Zhu, Xu Yin, Qi Ye, Wei Hua, Yuchi Huo, Hujun Bao

In this work, we use multi-view aerial images to reconstruct the geometry, lighting, and material of facades using neural signed distance fields (SDFs).

Benchmarking Inverse Rendering +2

M$^3$CS: Multi-Target Masked Point Modeling with Learnable Codebook and Siamese Decoders

no code implementations23 Sep 2023 Qibo Qiu, Honghui Yang, Wenxiao Wang, Shun Zhang, Haiming Gao, Haochao Ying, Wei Hua, Xiaofei He

Specifically, with masked point cloud as input, M$^3$CS introduces two decoders to predict masked representations and the original points simultaneously.


Cognitive Mirage: A Review of Hallucinations in Large Language Models

1 code implementation13 Sep 2023 Hongbin Ye, Tong Liu, Aijia Zhang, Wei Hua, Weiqiang Jia

Our contribution are threefold: (1) We provide a detailed and complete taxonomy for hallucinations appearing in text generation tasks; (2) We provide theoretical analyses of hallucinations in LLMs and provide existing detection and improvement methods; (3) We propose several research directions that can be developed in the future.

Hallucination Text Generation

SelFLoc: Selective Feature Fusion for Large-scale Point Cloud-based Place Recognition

no code implementations1 Jun 2023 Qibo Qiu, Haiming Gao, Wenxiao Wang, Zhiyi Su, Tian Xie, Wei Hua, Xiaofei He

To enhance message passing along particular axes, Stacked Asymmetric Convolution Block (SACB) is designed, which is one of the main contributions in this paper.

Autonomous Vehicles

Visual Information Extraction in the Wild: Practical Dataset and End-to-end Solution

1 code implementation12 May 2023 Jianfeng Kuang, Wei Hua, Dingkang Liang, Mingkun Yang, Deqiang Jiang, Bo Ren, Xiang Bai

We evaluate the existing end-to-end methods for VIE on the proposed dataset and observe that the performance of these methods has a distinguishable drop from SROIE (a widely used English dataset) to our proposed dataset due to the larger variance of layout and entities.

Contrastive Learning Optical Character Recognition (OCR)

SOOD: Towards Semi-Supervised Oriented Object Detection

1 code implementation CVPR 2023 Wei Hua, Dingkang Liang, Jingyu Li, Xiaolong Liu, Zhikang Zou, Xiaoqing Ye, Xiang Bai

Semi-Supervised Object Detection (SSOD), aiming to explore unlabeled data for boosting object detectors, has become an active task in recent years.

Object object-detection +4

I$^2$-SDF: Intrinsic Indoor Scene Reconstruction and Editing via Raytracing in Neural SDFs

no code implementations14 Mar 2023 Jingsen Zhu, Yuchi Huo, Qi Ye, Fujun Luan, Jifan Li, Dianbing Xi, Lisha Wang, Rui Tang, Wei Hua, Hujun Bao, Rui Wang

In this work, we present I$^2$-SDF, a new method for intrinsic indoor scene reconstruction and editing using differentiable Monte Carlo raytracing on neural signed distance fields (SDFs).

Indoor Scene Reconstruction Novel View Synthesis

Turning a CLIP Model into a Scene Text Detector

1 code implementation CVPR 2023 Wenwen Yu, Yuliang Liu, Wei Hua, Deqiang Jiang, Bo Ren, Xiang Bai

Recently, pretraining approaches based on vision language models have made effective progresses in the field of text detection.

Domain Adaptation Scene Text Detection +1

I2-SDF: Intrinsic Indoor Scene Reconstruction and Editing via Raytracing in Neural SDFs

no code implementations CVPR 2023 Jingsen Zhu, Yuchi Huo, Qi Ye, Fujun Luan, Jifan Li, Dianbing Xi, Lisha Wang, Rui Tang, Wei Hua, Hujun Bao, Rui Wang

Further, we propose to decompose the neural radiance field into spatially-varying material of the scene as a neural field through surface-based, differentiable Monte Carlo raytracing and emitter semantic segmentations, which enables physically based and photorealistic scene relighting and editing applications.

Indoor Scene Reconstruction Novel View Synthesis

SASFormer: Transformers for Sparsely Annotated Semantic Segmentation

1 code implementation5 Dec 2022 Hui Su, Yue Ye, Wei Hua, Lechao Cheng, Mingli Song

In this work, we propose a simple yet effective sparse annotated semantic segmentation framework based on segformer, dubbed SASFormer, that achieves remarkable performance.

Segmentation Semantic Segmentation +2

An Interactive Image-based Modeling System

no code implementations28 Mar 2022 Zhi He, Rui Wang, Wei Hua, Yuchi Huo

This paper propose a interactive 3D modeling method and corresponding system based on single or multiple uncalibrated images.

Camera Calibration

AttentionNAS: Spatiotemporal Attention Cell Search for Video Classification

no code implementations ECCV 2020 Xiaofang Wang, Xuehan Xiong, Maxim Neumann, AJ Piergiovanni, Michael S. Ryoo, Anelia Angelova, Kris M. Kitani, Wei Hua

The discovered attention cells can be seamlessly inserted into existing backbone networks, e. g., I3D or S3D, and improve video classification accuracy by more than 2% on both Kinetics-600 and MiT datasets.

Classification General Classification +1

MediaPipe: A Framework for Building Perception Pipelines

2 code implementations14 Jun 2019 Camillo Lugaresi, Jiuqiang Tang, Hadon Nash, Chris McClanahan, Esha Uboweja, Michael Hays, Fan Zhang, Chuo-Ling Chang, Ming Guang Yong, Juhyun Lee, Wan-Teh Chang, Wei Hua, Manfred Georg, Matthias Grundmann

A developer can use MediaPipe to build prototypes by combining existing perception components, to advance them to polished cross-platform applications and measure system performance and resource consumption on target platforms.

Distributed, Parallel, and Cluster Computing

Progressive Neural Architecture Search

18 code implementations ECCV 2018 Chenxi Liu, Barret Zoph, Maxim Neumann, Jonathon Shlens, Wei Hua, Li-Jia Li, Li Fei-Fei, Alan Yuille, Jonathan Huang, Kevin Murphy

We propose a new method for learning the structure of convolutional neural networks (CNNs) that is more efficient than recent state-of-the-art methods based on reinforcement learning and evolutionary algorithms.

Evolutionary Algorithms General Classification +3

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