Search Results for author:
Found 68 papers, 29 papers with code
LDMapNet-U: An End-to-End System for City-Scale Lane-Level Map Updating
By reconceptualizing the update task as an end-to-end map generation process grounded in historical map data, we introduce a paradigm shift in map updating that simultaneously generates vectorized maps and change information.
Zero-order Control Barrier Functions for Sampled-Data Systems with State and Input Dependent Safety Constraints
We propose a novel zero-order control barrier function (ZOCBF) for sampled-data systems to ensure system safety.
TopoSD: Topology-Enhanced Lane Segment Perception with SDMap Prior
Recent advances in autonomous driving systems have shifted towards reducing reliance on high-definition maps (HDMaps) due to the huge costs of annotation and maintenance.
MGMapNet: Multi-Granularity Representation Learning for End-to-End Vectorized HD Map Construction
The construction of Vectorized High-Definition (HD) map typically requires capturing both category and geometry information of map elements.
Uni$^2$Det: Unified and Universal Framework for Prompt-Guided Multi-dataset 3D Detection
We present Uni$^2$Det, a brand new framework for unified and universal multi-dataset training on 3D detection, enabling robust performance across diverse domains and generalization to unseen domains.
Safety of Linear Systems under Severe Sensor Attacks
For the offline phase, we derive conditions on safe sets for all possible sensor attacks that may be encountered during system deployment.
Single Image Dehazing Using Scene Depth Ordering
In this paper, we propose a depth order guided single image dehazing method, which utilizes depth order in hazy images to guide the dehazing process to achieve a similar depth perception in corresponding dehazing results.
Explore the LiDAR-Camera Dynamic Adjustment Fusion for 3D Object Detection
This module adjusts the feature distributions from both the camera and LiDAR, bringing them closer to the ground truth domain and minimizing differences.
OPEN: Object-wise Position Embedding for Multi-view 3D Object Detection
Accurate depth information is crucial for enhancing the performance of multi-view 3D object detection.
BEVWorld: A Multimodal World Model for Autonomous Driving via Unified BEV Latent Space
The world model consists of two parts: the multi-modal tokenizer and the latent BEV sequence diffusion model.
Decoupled Pseudo-labeling for Semi-Supervised Monocular 3D Object Detection
Additionally, we present a DepthGradient Projection (DGP) module to mitigate optimization conflicts caused by noisy depth supervision of pseudo-labels, effectively decoupling the depth gradient and removing conflicting gradients.
Gradient-based Sampling for Class Imbalanced Semi-supervised Object Detection
To tackle the confirmation bias from incorrect pseudo labels of minority classes, the class-rebalancing sampling module resamples unlabeled data following the guidance of the gradient-based reweighting module.
PointMamba: A Simple State Space Model for Point Cloud Analysis
Unlike traditional Transformers, PointMamba employs a linear complexity algorithm, presenting global modeling capacity while significantly reducing computational costs.
A contract negotiation scheme for safety verification of interconnected systems
This paper proposes a (control) barrier function synthesis and safety verification scheme for interconnected nonlinear systems based on assume-guarantee contracts (AGC) and sum-of-squares (SOS) techniques.
Forward Flow for Novel View Synthesis of Dynamic Scenes
This paper proposes a neural radiance field (NeRF) approach for novel view synthesis of dynamic scenes using forward warping.
Continuous-time control synthesis under nested signal temporal logic specifications
In this work, we propose a novel approach for the continuous-time control synthesis of nonlinear systems under nested signal temporal logic (STL) specifications.
Semi-supervised Cycle-GAN for face photo-sketch translation in the wild
Experiments show that SCG achieves competitive performance on public benchmarks and superior results on photos in the wild.
Semi-DETR: Semi-Supervised Object Detection with Detection Transformers
Specifically, we propose a Stage-wise Hybrid Matching strategy that combines the one-to-many assignment and one-to-one assignment strategies to improve the training efficiency of the first stage and thus provide high-quality pseudo labels for the training of the second stage.
CityTrack: Improving City-Scale Multi-Camera Multi-Target Tracking by Location-Aware Tracking and Box-Grained Matching
Targets in urban traffic scenes often undergo occlusion, illumination changes, and perspective changes, making it difficult to associate targets across different cameras accurately.
Multi-Modal 3D Object Detection by Box Matching
Extensive experiments on the nuScenes dataset demonstrate that our method is much more stable in dealing with challenging cases such as asynchronous sensors, misaligned sensor placement, and degenerated camera images than existing fusion methods.
Ranked #48 on
3D Object Detection
on nuScenes
Construction of Control Barrier Functions Using Predictions with Finite Horizon
We show that, based on ideas similar to the Hamilton-Jacobi reachability analysis, the knowledge on the subset of a control-invariant set allows us to obtain a time-invariant CBF for the time-invariant dynamics under consideration.
ByteTrackV2: 2D and 3D Multi-Object Tracking by Associating Every Detection Box
We propose a hierarchical data association strategy to mine the true objects in low-score detection boxes, which alleviates the problems of object missing and fragmented trajectories.
Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detection
It employs a "divide-and-conquer" strategy and separately exploits positives for the classification and localization task, which is more robust to the assignment ambiguity.
Ranked #1 on
Semi-Supervised Object Detection
on COCO 10% labeled data
(detector metric)
CAPE: Camera View Position Embedding for Multi-View 3D Object Detection
In this paper, we address the problem of detecting 3D objects from multi-view images.
Ranked #8 on
3D Object Detection
on nuScenes Camera Only
Improving Video Retrieval by Adaptive Margin
While most video retrieval methods overlook that phenomenon, we propose an adaptive margin changed with the distance between positive and negative pairs to solve the aforementioned issue.
StereoDistill: Pick the Cream from LiDAR for Distilling Stereo-based 3D Object Detection
In this paper, we propose a cross-modal distillation method named StereoDistill to narrow the gap between the stereo and LiDAR-based approaches via distilling the stereo detectors from the superior LiDAR model at the response level, which is usually overlooked in 3D object detection distillation.
Command-Driven Articulated Object Understanding and Manipulation
The key of Cart is to utilize the prediction of object structures to connect visual observations with user commands for effective manipulations.
A Simple Vision Transformer for Weakly Semi-supervised 3D Object Detection
Advanced 3D object detection methods usually rely on large-scale, elaborately labeled datasets to achieve good performance.
CFCG: Semi-Supervised Semantic Segmentation via Cross-Fusion and Contour Guidance Supervision
Current state-of-the-art semi-supervised semantic segmentation (SSSS) methods typically adopt pseudo labeling and consistency regularization between multiple learners with different perturbations.
Repainting and Imitating Learning for Lane Detection
In this paper, we target at finding an enhanced feature space where the lane features are distinctive while maintaining a similar distribution of lanes in the wild.
Detaching and Boosting: Dual Engine for Scale-Invariant Self-Supervised Monocular Depth Estimation
Monocular depth estimation (MDE) in the self-supervised scenario has emerged as a promising method as it refrains from the requirement of ground truth depth.
SoccerNet 2022 Challenges Results
The SoccerNet 2022 challenges were the second annual video understanding challenges organized by the SoccerNet team.
Spatial Pruned Sparse Convolution for Efficient 3D Object Detection
3D scenes are dominated by a large number of background points, which is redundant for the detection task that mainly needs to focus on foreground objects.
Compatibility checking of multiple control barrier functions for input constrained systems
State and input constraints are ubiquitous in control system design.
AGO-Net: Association-Guided 3D Point Cloud Object Detection Network
A feasible method is investigated to construct conceptual scenes without external datasets.
Paint and Distill: Boosting 3D Object Detection with Semantic Passing Network
In this work, we propose a novel semantic passing framework, named SPNet, to boost the performance of existing lidar-based 3D detection models with the guidance of rich context painting, with no extra computation cost during inference.
Neural Deformable Voxel Grid for Fast Optimization of Dynamic View Synthesis
The second module contains a density and a color grid to model the geometry and density of the scene.
A Simple Structure For Building A Robust Model
As deep learning applications, especially programs of computer vision, are increasingly deployed in our lives, we have to think more urgently about the security of these applications. One effective way to improve the security of deep learning models is to perform adversarial training, which allows the model to be compatible with samples that are deliberately created for use in attacking the model. Based on this, we propose a simple architecture to build a model with a certain degree of robustness, which improves the robustness of the trained network by adding an adversarial sample detection network for cooperative training.
GitNet: Geometric Prior-based Transformation for Birds-Eye-View Segmentation
Birds-eye-view (BEV) semantic segmentation is critical for autonomous driving for its powerful spatial representation ability.
Reusing the Task-specific Classifier as a Discriminator: Discriminator-free Adversarial Domain Adaptation
Such NWD can be coupled with the classifier to serve as a discriminator satisfying the K-Lipschitz constraint without the requirements of additional weight clipping or gradient penalty strategy.
Ranked #2 on
Domain Adaptation
on ImageCLEF-DA
Rope3D: TheRoadside Perception Dataset for Autonomous Driving and Monocular 3D Object Detection Task
On the other hand, the data captured from roadside cameras have strengths over frontal-view data, which is believed to facilitate a safer and more intelligent autonomous driving system.
TWIST: Two-Way Inter-Label Self-Training for Semi-Supervised 3D Instance Segmentation
We explore the way to alleviate the label-hungry problem in a semi-supervised setting for 3D instance segmentation.
Rope3D: The Roadside Perception Dataset for Autonomous Driving and Monocular 3D Object Detection Task
On the other hand, the data captured from roadside cameras have strengths over frontal-view data, which is believed to facilitate a safer and more intelligent autonomous driving system.
The Devil is in the Task: Exploiting Reciprocal Appearance-Localization Features for Monocular 3D Object Detection
Low-cost monocular 3D object detection plays a fundamental role in autonomous driving, whereas its accuracy is still far from satisfactory.
SGM3D: Stereo Guided Monocular 3D Object Detection
Monocular 3D object detection aims to predict the object location, dimension and orientation in 3D space alongside the object category given only a monocular image.
Weakly-Supervised Spatio-Temporal Anomaly Detection in Surveillance Video
In this paper, we introduce a novel task, referred to as Weakly-Supervised Spatio-Temporal Anomaly Detection (WSSTAD) in surveillance video.
DSANet: Dynamic Segment Aggregation Network for Video-Level Representation Learning
Long-range and short-range temporal modeling are two complementary and crucial aspects of video recognition.
Ranked #6 on
Action Recognition
on ActivityNet
Good Practices and A Strong Baseline for Traffic Anomaly Detection
In this paper, we propose a straightforward and efficient framework that includes pre-processing, a dynamic track module, and post-processing.
On the Undesired Equilibria Induced by Control Barrier Function Based Quadratic Programs
In this paper, we analyze the system behavior for general nonlinear control-affine systems when a control barrier function-induced quadratic program-based controller is employed for feedback.
High-order Barrier Functions: Robustness, Safety and Performance-Critical Control
Furthermore, the proposed formulation accounts for "performance-critical" control: it guarantees that a subset of the forward invariant set will admit any existing, bounded control law, while still ensuring forward invariance of the set.
Revealing the Reciprocal Relations Between Self-Supervised Stereo and Monocular Depth Estimation
Second, we introduce an occlusion-aware distillation (OA Distillation) module, which leverages the predicted depths from StereoNet in non-occluded regions to train our monocular depth estimation network named SingleNet.
Understanding Image Retrieval Re-Ranking: A Graph Neural Network Perspective
We argue that the first phase equals building the k-nearest neighbor graph, while the second phase can be viewed as spreading the message within the graph.
Ranked #1 on
Image Retrieval
on Oxford5k
Coherent Loss: A Generic Framework for Stable Video Segmentation
Video segmentation approaches are of great importance for numerous vision tasks especially in video manipulation for entertainment.
Discriminative Sounding Objects Localization via Self-supervised Audiovisual Matching
First, we propose to learn robust object representations by aggregating the candidate sound localization results in the single source scenes.
Face Sketch Synthesis with Style Transfer using Pyramid Column Feature
We utilize a fully convolutional neural network (FCNN) to create the content image, and propose a style transfer approach to introduce textures and shadings based on a newly proposed pyramid column feature.
PointTrack++ for Effective Online Multi-Object Tracking and Segmentation
In this work, we present PointTrack++, an effective on-line framework for MOTS, which remarkably extends our recently proposed PointTrack framework.
Segment as Points for Efficient Online Multi-Object Tracking and Segmentation
The resulting online MOTS framework, named PointTrack, surpasses all the state-of-the-art methods including 3D tracking methods by large margins (5. 4% higher MOTSA and 18 times faster over MOTSFusion) with the near real-time speed (22 FPS).
Multi-Object Tracking
Multi-Object Tracking and Segmentation
+1
Associate-3Ddet: Perceptual-to-Conceptual Association for 3D Point Cloud Object Detection
Object detection from 3D point clouds remains a challenging task, though recent studies pushed the envelope with the deep learning techniques.
ZoomNet: Part-Aware Adaptive Zooming Neural Network for 3D Object Detection
The pipeline of ZoomNet begins with an ordinary 2D object detection model which is used to obtain pairs of left-right bounding boxes.
Dynamic Inference: A New Approach Toward Efficient Video Action Recognition
In a nutshell, we treat input frames and network depth of the computational graph as a 2-dimensional grid, and several checkpoints are placed on this grid in advance with a prediction module.
Perspective-Guided Convolution Networks for Crowd Counting
In this paper, we propose a novel perspective-guided convolution (PGC) for convolutional neural network (CNN) based crowd counting (i. e. PGCNet), which aims to overcome the dramatic intra-scene scale variations of people due to the perspective effect.
Recognizing Part Attributes with Insufficient Data
Although great progress has been made to apply object-level recognition, recognizing the attributes of parts remains less applicable since the training data for part attributes recognition is usually scarce especially for internet-scale applications.
Multi-Agent Reinforcement Learning Based Frame Sampling for Effective Untrimmed Video Recognition
Video Recognition has drawn great research interest and great progress has been made.
Ranked #7 on
Action Recognition
on ActivityNet
Semi-Supervised Learning for Face Sketch Synthesis in the Wild
Instead of supervising the network with ground truth sketches, we first perform patch matching in feature space between the input photo and photos in a small reference set of photo-sketch pairs.
Ranked #1 on
Face Sketch Synthesis
on CUHK
Fine-grained Video Categorization with Redundancy Reduction Attention
Specifically, it firstly summarizes the video by weight-summing all feature vectors in the feature maps of selected frames with a spatio-temporal soft attention, and then predicts which channels to suppress or to enhance according to this summary with a learned non-linear transform.
Ranked #12 on
Action Recognition
on ActivityNet
Improving Annotation for 3D Pose Dataset of Fine-Grained Object Categories
Existing 3D pose datasets of object categories are limited to generic object types and lack of fine-grained information.
3D Pose Estimation for Fine-Grained Object Categories
The new dataset is available at www. umiacs. umd. edu/~wym/3dpose. html
Multipoint Filtering with Local Polynomial Approximation and Range Guidance
By using the hybrid of the local polynomial model and color/intensity based range guidance, the proposed method not only preserves edges but also does a much better job in preserving spatial variation than existing popular filtering methods.
