Search Results for author:
Found 43 papers, 18 papers with code
Promptable Closed-loop Traffic Simulation
Simulation stands as a cornerstone for safe and efficient autonomous driving development.
Wolf: Captioning Everything with a World Summarization Framework
Finally, we establish a benchmark for video captioning and introduce a leaderboard, aiming to accelerate advancements in video understanding, captioning, and data alignment.
Tokenize the World into Object-level Knowledge to Address Long-tail Events in Autonomous Driving
The autonomous driving industry is increasingly adopting end-to-end learning from sensory inputs to minimize human biases in system design.
NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking
On a large set of challenging scenarios, we observe that simple methods with moderate compute requirements such as TransFuser can match recent large-scale end-to-end driving architectures such as UniAD.
Language-Image Models with 3D Understanding
Our experiments on outdoor benchmarks demonstrate that Cube-LLM significantly outperforms existing baselines by 21. 3 points of AP-BEV on the Talk2Car dataset for 3D grounded reasoning and 17. 7 points on the DriveLM dataset for complex reasoning about driving scenarios, respectively.
PARA-Drive: Parallelized Architecture for Real-time Autonomous Driving
Recent works have proposed end-to-end autonomous vehicle (AV) architectures comprised of differentiable modules achieving state-of-the-art driving performance.
Augmenting Lane Perception and Topology Understanding with Standard Definition Navigation Maps
We propose a novel framework to integrate SD maps into online map prediction and propose a Transformer-based encoder, SD Map Encoder Representations from transFormers, to leverage priors in SD maps for the lane-topology prediction task.
EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision
We present EmerNeRF, a simple yet powerful approach for learning spatial-temporal representations of dynamic driving scenes.
Language Conditioned Traffic Generation
In this work, we turn to language as a source of supervision for dynamic traffic scene generation.
Robust Trajectory Prediction against Adversarial Attacks
We demonstrate that our method is able to improve the performance by 46% on adversarial data and at the cost of only 3% performance degradation on clean data, compared to the model trained with clean data.
Multiface: A Dataset for Neural Face Rendering
Along with the release of the dataset, we conduct ablation studies on the influence of different model architectures toward the model's interpolation capacity of novel viewpoint and expressions.
Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking
Instead of relying only on the linear state estimate (i. e., estimation-centric approach), we use object observations (i. e., the measurements by object detector) to compute a virtual trajectory over the occlusion period to fix the error accumulation of filter parameters during the occlusion period.
Ranked #2 on
Multiple Object Tracking
on CroHD
Whose Track Is It Anyway? Improving Robustness to Tracking Errors With Affinity-Based Trajectory Prediction
This is typically caused by the propagation of errors from tracking to prediction, such as noisy tracks, fragments, and identity switches.
MTP: Multi-Hypothesis Tracking and Prediction for Reduced Error Propagation
Recently, there has been tremendous progress in developing each individual module of the standard perception-planning robot autonomy pipeline, including detection, tracking, prediction of other agents' trajectories, and ego-agent trajectory planning.
Multi-Echo LiDAR for 3D Object Detection
LiDAR sensors can be used to obtain a wide range of measurement signals other than a simple 3D point cloud, and those signals can be leveraged to improve perception tasks like 3D object detection.
Multi-Modality Task Cascade for 3D Object Detection
To provide a more integrated approach, we propose a novel Multi-Modality Task Cascade network (MTC-RCNN) that leverages 3D box proposals to improve 2D segmentation predictions, which are then used to further refine the 3D boxes.
Wide-Baseline Multi-Camera Calibration using Person Re-Identification
We address the problem of estimating the 3D pose of a network of cameras for large-environment wide-baseline scenarios, e. g., cameras for construction sites, sports stadiums, and public spaces.
AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecasting
Instead, we would prefer a method that allows an agent's state at one time to directly affect another agent's state at a future time.
Ranked #10 on
Trajectory Prediction
on ETH/UCY
Supervision by Registration and Triangulation for Landmark Detection
End-to-end training is made possible by differentiable registration and 3D triangulation modules.
Visio-Temporal Attention for Multi-Camera Multi-Target Association
We propose a inter-tracklet (person to person) attention mechanism that learns a representation for a target tracklet while taking into account other tracklets across multiple views.
AutoSelect: Automatic and Dynamic Detection Selection for 3D Multi-Object Tracking
Also, this threshold is sensitive to many factors such as target object category so we need to re-search the threshold if these factors change.
End-to-End 3D Multi-Object Tracking and Trajectory Forecasting
To evaluate this hypothesis, we propose a unified solution for 3D MOT and trajectory forecasting which also incorporates two additional novel computational units.
Graph Neural Networks for 3D Multi-Object Tracking
3D Multi-object tracking (MOT) is crucial to autonomous systems.
AB3DMOT: A Baseline for 3D Multi-Object Tracking and New Evaluation Metrics
Additionally, 3D MOT datasets such as KITTI evaluate MOT methods in 2D space and standardized 3D MOT evaluation tools are missing for a fair comparison of 3D MOT methods.
Joint Object Detection and Multi-Object Tracking with Graph Neural Networks
Despite the fact that the two components are dependent on each other, prior works often design detection and data association modules separately which are trained with separate objectives.
Ranked #1 on
Multi-Object Tracking
on 2D MOT 2015
When We First Met: Visual-Inertial Person Localization for Co-Robot Rendezvous
We propose a method to learn a visual-inertial feature space in which the motion of a person in video can be easily matched to the motion measured by a wearable inertial measurement unit (IMU).
GNN3DMOT: Graph Neural Network for 3D Multi-Object Tracking with Multi-Feature Learning
As a result, the feature of one object is informed of the features of other objects so that the object feature can lean towards the object with similar feature (i. e., object probably with a same ID) and deviate from objects with dissimilar features (i. e., object probably with different IDs), leading to a more discriminative feature for each object; (2) instead of obtaining the feature from either 2D or 3D space in prior work, we propose a novel joint feature extractor to learn appearance and motion features from 2D and 3D space simultaneously.
GNN3DMOT: Graph Neural Network for 3D Multi-Object Tracking With 2D-3D Multi-Feature Learning
As a result, the feature of one object is informed of the features of other objects so that the object feature can lean towards the object with similar feature (i. e., object probably with a same ID) and deviate from objects with dissimilar features (i. e., object probably with different IDs), leading to a more discriminative feature for each object; (2) instead of obtaining the feature from either 2D or 3D space in prior work, we propose a novel joint feature extractor to learn appearance and motion features from 2D and 3D space simultaneously.
Inverting the Pose Forecasting Pipeline with SPF2: Sequential Pointcloud Forecasting for Sequential Pose Forecasting
Through experiments on a robotic manipulation dataset and two driving datasets, we show that SPFNet is effective for the SPF task, our forecast-then-detect pipeline outperforms the detect-then-forecast approaches to which we compared, and that pose forecasting performance improves with the addition of unlabeled data.
PTP: Parallelized Tracking and Prediction with Graph Neural Networks and Diversity Sampling
We evaluate on KITTI and nuScenes datasets showing that our method with socially-aware feature learning and diversity sampling achieves new state-of-the-art performance on 3D MOT and trajectory prediction.
Learning Shape Representations for Clothing Variations in Person Re-Identification
To tackle the re-ID problem in the context of clothing changes, we propose a novel representation learning model which is able to generate a body shape feature representation without being affected by clothing color or patterns.
3D Multi-Object Tracking: A Baseline and New Evaluation Metrics
Additionally, 3D MOT datasets such as KITTI evaluate MOT methods in the 2D space and standardized 3D MOT evaluation tools are missing for a fair comparison of 3D MOT methods.
Ranked #16 on
Multiple Object Tracking
on KITTI Test (Online Methods)
Learning Spatio-Temporal Features with Two-Stream Deep 3D CNNs for Lipreading
We evaluate different combinations of front-end and back-end modules with the grayscale video and optical flow inputs on the LRW dataset.
Monocular 3D Object Detection with Pseudo-LiDAR Point Cloud
Following the pipeline of two-stage 3D detection algorithms, we detect 2D object proposals in the input image and extract a point cloud frustum from the pseudo-LiDAR for each proposal.
On the Importance of Video Action Recognition for Visual Lipreading
We focus on the word-level visual lipreading, which requires to decode the word from the speaker's video.
Future Near-Collision Prediction from Monocular Video: Feasibility, Dataset, and Challenges
Our results show that our proposed multi-stream CNN is the best model for predicting time to near-collision.
Robotics
Deep Reinforcement Learning for Autonomous Driving
To deal with these challenges, we first adopt the deep deterministic policy gradient (DDPG) algorithm, which has the capacity to handle complex state and action spaces in continuous domain.
CyLKs: Unsupervised Cycle Lucas-Kanade Network for Landmark Tracking
Across a majority of modern learning-based tracking systems, expensive annotations are needed to achieve state-of-the-art performance.
Image Labeling with Markov Random Fields and Conditional Random Fields
Most existing methods for object segmentation in computer vision are formulated as a labeling task.
GroundNet: Monocular Ground Plane Normal Estimation with Geometric Consistency
We focus on estimating the 3D orientation of the ground plane from a single image.
Supervision-by-Registration: An Unsupervised Approach to Improve the Precision of Facial Landmark Detectors
In this paper, we present supervision-by-registration, an unsupervised approach to improve the precision of facial landmark detectors on both images and video.
Ranked #1 on
Facial Landmark Detection
on 300-VW (C)
Rotational Rectification Network: Enabling Pedestrian Detection for Mobile Vision
To address this issue, we propose a Rotational Rectification Network (R2N) that can be inserted into any CNN-based pedestrian (or object) detector to adapt it to significant changes in camera rotation.
Visual Compiler: Synthesizing a Scene-Specific Pedestrian Detector and Pose Estimator
We introduce the concept of a Visual Compiler that generates a scene specific pedestrian detector and pose estimator without any pedestrian observations.
