Search Results for author:
Found 17 papers, 9 papers with code
JiSAM: Alleviate Labeling Burden and Corner Case Problems in Autonomous Driving via Minimal Real-World Data
However, the over-reliance on real labeled data in LiDAR perception limits the scale of on-road attempts.
Temporal Overlapping Prediction: A Self-supervised Pre-training Method for LiDAR Moving Object Segmentation
Moving object segmentation (MOS) on LiDAR point clouds is crucial for autonomous systems like self-driving vehicles.
TREND: Unsupervised 3D Representation Learning via Temporal Forecasting for LiDAR Perception
Labeling LiDAR point clouds is notoriously time-and-energy-consuming, which spurs recent unsupervised 3D representation learning methods to alleviate the labeling burden in LiDAR perception via pretrained weights.
CLAP: Unsupervised 3D Representation Learning for Fusion 3D Perception via Curvature Sampling and Prototype Learning
In this paper, we explore joint unsupervised pre-training for fusion 3D perception via differentiable rendering and propose CLAP, short for Curvature sampLing and swApping Prototype assignment prediction.
MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGI
Large Vision-Language Models (LVLMs) show significant strides in general-purpose multimodal applications such as visual dialogue and embodied navigation.
Position: Towards Implicit Prompt For Text-To-Image Models
We call for increased attention to the potential and risks of implicit prompts in the T2I community and further investigation into the capabilities and impacts of implicit prompts, advocating for a balanced approach that harnesses their benefits while mitigating their risks.
RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesis
Robotic behavior synthesis, the problem of understanding multimodal inputs and generating precise physical control for robots, is an important part of Embodied AI.
Ranked #196 on
Visual Question Answering
on MM-Vet
CurriculumLoc: Enhancing Cross-Domain Geolocalization through Multi-Stage Refinement
Visual geolocalization is a cost-effective and scalable task that involves matching one or more query images, taken at some unknown location, to a set of geo-tagged reference images.
SPOT: Scalable 3D Pre-training via Occupancy Prediction for Learning Transferable 3D Representations
Annotating 3D LiDAR point clouds for perception tasks is fundamental for many applications e. g., autonomous driving, yet it still remains notoriously labor-intensive.
MV-JAR: Masked Voxel Jigsaw and Reconstruction for LiDAR-Based Self-Supervised Pre-Training
This paper introduces the Masked Voxel Jigsaw and Reconstruction (MV-JAR) method for LiDAR-based self-supervised pre-training and a carefully designed data-efficient 3D object detection benchmark on the Waymo dataset.
CtrlFormer: Learning Transferable State Representation for Visual Control via Transformer
In visual control, learning transferable state representation that can transfer between different control tasks is important to reduce the training sample size.
CO^3: Cooperative Unsupervised 3D Representation Learning for Autonomous Driving
In this paper, we propose CO^3, namely Cooperative Contrastive Learning and Contextual Shape Prediction, to learn 3D representation for outdoor-scene point clouds in an unsupervised manner.
RestoreFormer: High-Quality Blind Face Restoration from Undegraded Key-Value Pairs
Blind face restoration is to recover a high-quality face image from unknown degradations.
CycleMLP: A MLP-like Architecture for Dense Prediction
We build a family of models which surpass existing MLPs and even state-of-the-art Transformer-based models, e. g., Swin Transformer, while using fewer parameters and FLOPs.
Ranked #15 on
Semantic Segmentation
on DensePASS
RaLL: End-to-end Radar Localization on Lidar Map Using Differentiable Measurement Model
In this paper, we propose an end-to-end deep learning framework for Radar Localization on Lidar Map (RaLL) to bridge the gap, which not only achieves the robust radar localization but also exploits the mature lidar mapping technique, thus reducing the cost of radar mapping.
Graph Partitioning and Graph Neural Network based Hierarchical Graph Matching for Graph Similarity Computation
Next, a novel graph neural network with an attention mechanism is designed to map each subgraph into an embedding vector.
CoSimGNN: Towards Large-scale Graph Similarity Computation
In this paper, we focus on similarity computation for large-scale graphs and propose the "embedding-coarsening-matching" framework CoSimGNN, which first embeds and coarsens large graphs with adaptive pooling operation and then deploys fine-grained interactions on the coarsened graphs for final similarity scores.
