TALISMAN: Targeted Active Learning for Object Detection with Rare Classes and Slices Using Submodular Mutual Information
An Efficient Person Clustering Algorithm for Open Checkout-Free Groceries
POP: Mining POtential Performance of New Fashion Products via Webly Cross-Modal Query Expansion
Pose Forecasting in Industrial Human-Robot Collaboration
Actor-Centered Representations for Action Localization in Streaming Videos
Bandwidth-Aware Adaptive Codec for DNN Inference Offloading in IoT
Domain Knowledge-Informed Self-Supervised Representations for Workout Form Assessment
Towards Scale-Aware, Robust, and Generalizable Unsupervised Monocular Depth Estimation by Integrating IMU Motion Dynamics
TIPS: Text-Induced Pose Synthesis
Addressing Heterogeneity in Federated Learning via Distributional Transformation
Where in the World Is This Image? Transformer-Based Geo-Localization in the Wild
Colorization for In Situ Marine Plankton Images
Efficient Deep Visual and Inertial Odometry with Adaptive Visual Modality Selection
A Sketch Is Worth a Thousand Words: Image Retrieval with Text and Sketch
A Cloud 3D Dataset and Application-Specific Learned Image Compression in Cloud 3D
AutoTransition: Learning to Recommend Video Transition Effects
Online Segmentation of LiDAR Sequences: Dataset and Algorithm
Open-World Semantic Segmentation for LIDAR Point Clouds
KING: Generating Safety-Critical Driving Scenarios for Robust Imitation via Kinematics Gradients
Differentiable Raycasting for Self-Supervised Occupancy Forecasting
InAction: Interpretable Action Decision Making for Autonomous Driving
CramNet: Camera-Radar Fusion with Ray-Constrained Cross-Attention for Robust 3D Object Detection
CODA: A Real-World Road Corner Case Dataset for Object Detection in Autonomous Driving
Motion Inspired Unsupervised Perception and Prediction in Autonomous Driving
StretchBEV: Stretching Future Instance Prediction Spatially and Temporally
RCLane: Relay Chain Prediction for Lane Detection
Drive&Segment: Unsupervised Semantic Segmentation of Urban Scenes via Cross-Modal Distillation
CenterFormer: Center-based Transformer for 3D Object Detection
Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patches
ST-P3: End-to-End Vision-Based Autonomous Driving via Spatial-Temporal Feature Learning
PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark
PointFix: Learning to Fix Domain Bias for Robust Online Stereo Adaptation
BRNet: Exploring Comprehensive Features for Monocular Depth Estimation
SiamDoGe: Domain Generalizable Semantic Segmentation Using Siamese Network
Context-Aware Streaming Perception in Dynamic Environments
Context-Aware Streaming Perception in Dynamic Environments
Multimodal Transformer for Automatic 3D Annotation and Object Detection
Dynamic 3D Scene Analysis by Point Cloud Accumulation
Homogeneous Multi-modal Feature Fusion and Interaction for 3D Object Detection
JPerceiver: Joint Perception Network for Depth, Pose and Layout Estimation in Driving Scenes
Semi-Supervised 3D Object Detection with Proficient Teachers
Point Cloud Compression with Sibling Context and Surface Priors.