Search Results for author:
Found 56 papers, 31 papers with code
RhyRNN: Rhythmic RNN for Recognizing Events in Long and Complex Videos
We study the behavior of RhyRNN and empirically show that our method works well even when mph{only event-level labels are available} in the training stage (compared to algorithms requiring sub-activity labels for recognition), and thus is more practical when the sub-activity labels are missing or difficult to obtain.
Symmetry Discovery for Different Data Types
However, constructing equivariant neural networks typically requires prior knowledge of data types and symmetries, which is difficult to achieve in most tasks.
Affine Equivariant Networks Based on Differential Invariants
In this paper we build affine equivariant networks based on differential invariants from the viewpoint of symmetric PDEs without discretizing or sampling the group.
Towards Knowledge-driven Autonomous Driving
This paper explores the emerging knowledge-driven autonomous driving technologies.
Optimizing the Placement of Roadside LiDARs for Autonomous Driving
We define perceptual gain as the increased perceptual capability when a new LiDAR is placed.
UniSeg: A Unified Multi-Modal LiDAR Segmentation Network and the OpenPCSeg Codebase
Besides, we construct the OpenPCSeg codebase, which is the largest and most comprehensive outdoor LiDAR segmentation codebase.
Ranked #2 on
3D Semantic Segmentation
on SemanticKITTI
(using extra training data)
LimSim: A Long-term Interactive Multi-scenario Traffic Simulator
With the growing popularity of digital twin and autonomous driving in transportation, the demand for simulation systems capable of generating high-fidelity and reliable scenarios is increasing.
DetZero: Rethinking Offboard 3D Object Detection with Long-term Sequential Point Clouds
Extensive experiments on Waymo Open Dataset show our DetZero outperforms all state-of-the-art onboard and offboard 3D detection methods.
Ranked #1 on
3D Multi-Object Tracking
on Waymo Open Dataset
StreetSurf: Extending Multi-view Implicit Surface Reconstruction to Street Views
We present a novel multi-view implicit surface reconstruction technique, termed StreetSurf, that is readily applicable to street view images in widely-used autonomous driving datasets, such as Waymo-perception sequences, without necessarily requiring LiDAR data.
Calib-Anything: Zero-training LiDAR-Camera Extrinsic Calibration Method Using Segment Anything
The research on extrinsic calibration between Light Detection and Ranging(LiDAR) and camera are being promoted to a more accurate, automatic and generic manner.
AD-PT: Autonomous Driving Pre-Training with Large-scale Point Cloud Dataset
It is a long-term vision for Autonomous Driving (AD) community that the perception models can learn from a large-scale point cloud dataset, to obtain unified representations that can achieve promising results on different tasks or benchmarks.
SUG: Single-dataset Unified Generalization for 3D Point Cloud Classification
In this paper, different from previous 2D DG works, we focus on the 3D DG problem and propose a Single-dataset Unified Generalization (SUG) framework that only leverages a single source dataset to alleviate the unforeseen domain differences faced by a well-trained source model.
Catch Missing Details: Image Reconstruction with Frequency Augmented Variational Autoencoder
The popular VQ-VAE models reconstruct images through learning a discrete codebook but suffer from a significant issue in the rapid quality degradation of image reconstruction as the compression rate rises.
Perception Imitation: Towards Synthesis-free Simulator for Autonomous Vehicles
We propose a perception imitation method to simulate results of a certain perception model, and discuss a new heuristic route of autonomous driving simulator without data synthesis.
VideoXum: Cross-modal Visual and Textural Summarization of Videos
We propose a new joint video and text summarization task.
Ranked #1 on
Video Summarization
on videoxum
SCPNet: Semantic Scene Completion on Point Cloud
We propose a simple yet effective label rectification strategy, which uses off-the-shelf panoptic segmentation labels to remove the traces of dynamic objects in completion labels, greatly improving the performance of deep models especially for those moving objects.
Ranked #2 on
3D Semantic Scene Completion
on SemanticKITTI
Uni3D: A Unified Baseline for Multi-dataset 3D Object Detection
In this paper, we study the task of training a unified 3D detector from multiple datasets.
Bi3D: Bi-domain Active Learning for Cross-domain 3D Object Detection
Unsupervised Domain Adaptation (UDA) technique has been explored in 3D cross-domain tasks recently.
Rethinking Range View Representation for LiDAR Segmentation
We show that, for the first time, a range view method is able to surpass the point, voxel, and multi-view fusion counterparts in the competing LiDAR semantic and panoptic segmentation benchmarks, i. e., SemanticKITTI, nuScenes, and ScribbleKITTI.
Ranked #4 on
3D Semantic Segmentation
on SemanticKITTI
Dynamic Scenario Representation Learning for Motion Forecasting with Heterogeneous Graph Convolutional Recurrent Networks
Due to the complex and changing interactions in dynamic scenarios, motion forecasting is a challenging problem in autonomous driving.
Ranked #1 on
Trajectory Prediction
on Argoverse2
LoGoNet: Towards Accurate 3D Object Detection with Local-to-Global Cross-Modal Fusion
Notably, LoGoNet ranks 1st on Waymo 3D object detection leaderboard and obtains 81. 02 mAPH (L2) detection performance.
SensorX2car: Sensors-to-car calibration for autonomous driving in road scenarios
However, most prior methods focus on extrinsic calibration between sensors, and few focus on the misalignment between the sensors and the vehicle coordinate system.
CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIP
For the first time, our pre-trained network achieves annotation-free 3D semantic segmentation with 20. 8% and 25. 08% mIoU on nuScenes and ScanNet, respectively.
UniDA3D: Unified Domain Adaptive 3D Semantic Segmentation Pipeline
Different from previous studies that only focus on a single adaptation task, UniDA3D can tackle several adaptation tasks in 3D segmentation field, by designing a unified source-and-target active sampling strategy, which selects a maximally-informative subset from both source and target domains for effective model adaptation.
LWSIS: LiDAR-guided Weakly Supervised Instance Segmentation for Autonomous Driving
In this paper, we present a more artful framework, LiDAR-guided Weakly Supervised Instance Segmentation (LWSIS), which leverages the off-the-shelf 3D data, i. e., Point Cloud, together with the 3D boxes, as natural weak supervisions for training the 2D image instance segmentation models.
Analyzing Infrastructure LiDAR Placement with Realistic LiDAR Simulation Library
Through simulating point cloud data in different LiDAR placements, we can evaluate the perception accuracy of these placements using multiple detection models.
Online LiDAR-Camera Extrinsic Parameters Self-checking
This calibration task is multi-modal, where the rich color and texture information captured by the camera and the accurate three-dimensional spatial information from the LiDAR is incredibly significant for downstream tasks.
Homogeneous Multi-modal Feature Fusion and Interaction for 3D Object Detection
To address these problems, we construct the homogeneous structure between the point cloud and images to avoid projective information loss by transforming the camera features into the LiDAR 3D space.
Open Vocabulary Multi-Label Classification with Dual-Modal Decoder on Aligned Visual-Textual Features
In computer vision, multi-label recognition are important tasks with many real-world applications, but classifying previously unseen labels remains a significant challenge.
Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation
This article addresses the problem of distilling knowledge from a large teacher model to a slim student network for LiDAR semantic segmentation.
Ranked #8 on
3D Semantic Segmentation
on SemanticKITTI
OpenCalib: A Multi-sensor Calibration Toolbox for Autonomous Driving
To this end, we present OpenCalib, a calibration toolbox that contains a rich set of various sensor calibration methods.
Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysis
Point cloud completion is a generation and estimation issue derived from the partial point clouds, which plays a vital role in the applications in 3D computer vision.
CROON: Automatic Multi-LiDAR Calibration and Refinement Method in Road Scene
Sensor-based environmental perception is a crucial part of the autonomous driving system.
$β$-DARTS: Beta-Decay Regularization for Differentiable Architecture Search
Neural Architecture Search~(NAS) has attracted increasingly more attention in recent years because of its capability to design deep neural networks automatically.
Multi-modal Sensor Fusion for Auto Driving Perception: A Survey
Multi-modal fusion is a fundamental task for the perception of an autonomous driving system, which has recently intrigued many researchers.
b-DARTS: Beta-Decay Regularization for Differentiable Architecture Search
Neural Architecture Search (NAS) has attracted increasingly more attention in recent years because of its capability to design deep neural network automatically.
MOC-GAN: Mixing Objects and Captions to Generate Realistic Images
Correspondingly, a MOC-GAN is proposed to mix the inputs of two modalities to generate realistic images.
Perception Entropy: A Metric for Multiple Sensors Configuration Evaluation and Design
To tackle these issues, we propose a novel method based on conditional entropy in Bayesian theory to evaluate the sensor configurations containing both cameras and LiDARs.
CRLF: Automatic Calibration and Refinement based on Line Feature for LiDAR and Camera in Road Scenes
For autonomous vehicles, an accurate calibration for LiDAR and camera is a prerequisite for multi-sensor perception systems.
Lexically-constrained Text Generation through Commonsense Knowledge Extraction and Injection
Conditional text generation has been a challenging task that is yet to see human-level performance from state-of-the-art models.
Exploring the Hierarchy in Relation Labels for Scene Graph Generation
By assigning each relationship a single label, current approaches formulate the relationship detection as a classification problem.
Deep Learning of Determinantal Point Processes via Proper Spectral Sub-gradient
Determinantal point processes (DPPs) is an effective tool to deliver diversity on multiple machine learning and computer vision tasks.
Recognizing Video Events with Varying Rhythms
In this paper, we investigate the problem of recognizing long and complex events with varying action rhythms, which has not been considered in the literature but is a practical challenge.
PasteGAN: A Semi-Parametric Method to Generate Image from Scene Graph
Therefore, to generate the images with preferred objects and rich interactions, we propose a semi-parametric method, PasteGAN, for generating the image from the scene graph and the image crops, where spatial arrangements of the objects and their pair-wise relationships are defined by the scene graph and the object appearances are determined by the given object crops.
Disentangling Pose from Appearance in Monochrome Hand Images
Hand pose estimation from the monocular 2D image is challenging due to the variation in lighting, appearance, and background.
Perceive Where to Focus: Learning Visibility-aware Part-level Features for Partial Person Re-identification
The visibility awareness allows VPM to extract region-level features and compare two images with focus on their shared regions (which are visible on both images).
Ranked #12 on
Person Re-Identification
on Market-1501-C
Plan-Recognition-Driven Attention Modeling for Visual Recognition
We build an event recognition system, ER-PRN, which takes Pixel Dynamics Network as a subroutine, to recognize events based on observations augmented by plan-recognition-driven attention.
Mean Local Group Average Precision (mLGAP): A New Performance Metric for Hashing-based Retrieval
In this paper, we introduce a new metric named Mean Local Group Average Precision (mLGAP) for better evaluation of the performance of hashing-based retrieval.
Question-Guided Hybrid Convolution for Visual Question Answering
Most state-of-the-art VQA methods fuse the high-level textual and visual features from the neural network and abandon the visual spatial information when learning multi-modal features. To address these problems, question-guided kernels generated from the input question are designed to convolute with visual features for capturing the textual and visual relationship in the early stage.
Ranked #14 on
Visual Question Answering (VQA)
on CLEVR
Factorizable Net: An Efficient Subgraph-based Framework for Scene Graph Generation
Generating scene graph to describe all the relations inside an image gains increasing interests these years.
Ranked #1 on
Scene Graph Generation
on VRD
Training Neural Networks by Using Power Linear Units (PoLUs)
Experimental results show that our proposed activation function outperforms other state-of-the-art models with most networks.
Recognizing Plans by Learning Embeddings from Observed Action Distributions
The first involves resampling the distribution sequences to single action sequences, from which we could learn an action affinity model based on learned action (word) embeddings for plan recognition.
Semantically Consistent Image Completion with Fine-grained Details
Image completion has achieved significant progress due to advances in generative adversarial networks (GANs).
Visual Question Generation as Dual Task of Visual Question Answering
Recently visual question answering (VQA) and visual question generation (VQG) are two trending topics in the computer vision, which have been explored separately.
Scene Graph Generation from Objects, Phrases and Region Captions
Object detection, scene graph generation and region captioning, which are three scene understanding tasks at different semantic levels, are tied together: scene graphs are generated on top of objects detected in an image with their pairwise relationship predicted, while region captioning gives a language description of the objects, their attributes, relations, and other context information.
Ranked #2 on
Object Detection
on Visual Genome
ViP-CNN: Visual Phrase Guided Convolutional Neural Network
In this paper, each visual relationship is considered as a phrase with three components.
