Search Results for author:
Found 32 papers, 24 papers with code
Period-LLM: Extending the Periodic Capability of Multimodal Large Language Model
Periodic or quasi-periodic phenomena reveal intrinsic characteristics in various natural processes, such as weather patterns, movement behaviors, traffic flows, and biological signals.
Sage Deer: A Super-Aligned Driving Generalist Is Your Copilot
This benchmark measures the deer's perceptual decision-making ability and the super alignment's accuracy.
Lighten CARAFE: Dynamic Lightweight Upsampling with Guided Reassemble Kernels
Experiments on several mainstream vision tasks show that our DLU achieves comparable and even better performance to the original CARAFE, but with much lower complexity, e. g., DLU requires 91% fewer parameters and at least 63% fewer FLOPs (Floating Point Operations) than CARAFE in the case of 16x upsampling, but outperforms the CARAFE by 0. 3% mAP in object detection.
Divide and Conquer: Improving Multi-Camera 3D Perception with 2D Semantic-Depth Priors and Input-Dependent Queries
Additionally, the input-independent nature of initial queries also limits the learning capacity of Transformer-based models.
GPT as Psychologist? Preliminary Evaluations for GPT-4V on Visual Affective Computing
In conclusion, this paper provides valuable insights into the potential applications and challenges of MLLMs in human-centric computing.
FedGT: Federated Node Classification with Scalable Graph Transformer
However, existing methods have the following limitations: (1) The links between local subgraphs are missing in subgraph federated learning.
Learning Coupled Dictionaries from Unpaired Data for Image Super-Resolution
The difficulty of acquiring high-resolution (HR) and low-resolution (LR) image pairs in real scenarios limits the performance of existing learning-based image super-resolution (SR) methods in the real world.
MC-Stereo: Multi-peak Lookup and Cascade Search Range for Stereo Matching
This architecture mitigates the multi-peak distribution problem in matching through the multi-peak lookup strategy, and integrates the coarse-to-fine concept into the iterative framework via the cascade search range.
Rethinking Dual-Stream Super-Resolution Semantic Learning in Medical Image Segmentation
In this paper, we rethink these frameworks and reveal that the feature similarity between tasks is insufficient to constrain vessels or lesion segmentation in the medical field, due to their small proportion in the image.
PVP: Pre-trained Visual Parameter-Efficient Tuning
Large-scale pre-trained transformers have demonstrated remarkable success in various computer vision tasks.
Ranked #4 on
Image Classification
on VTAB-1k
(using extra training data)
Small but Mighty: Enhancing 3D Point Clouds Semantic Segmentation with U-Next Framework
While the fundamental framework of point cloud semantic segmentation has been largely overlooked, with most existing approaches rely on the U-Net architecture by default.
Backdoor Defense via Deconfounded Representation Learning
The other clean model dedicates to capturing the desired causal effects by minimizing the mutual information with the confounding representations from the backdoored model and employing a sample-wise re-weighting scheme.
BUFFER: Balancing Accuracy, Efficiency, and Generalizability in Point Cloud Registration
Extensive experiments on real-world scenarios demonstrate that our method achieves the best of both worlds in accuracy, efficiency, and generalization.
Hierarchical Graph Transformer with Adaptive Node Sampling
The Transformer architecture has achieved remarkable success in a number of domains including natural language processing and computer vision.
DevNet: Self-supervised Monocular Depth Learning via Density Volume Construction
Self-supervised depth learning from monocular images normally relies on the 2D pixel-wise photometric relation between temporally adjacent image frames.
4DAC: Learning Attribute Compression for Dynamic Point Clouds
In addition, we also propose a deep conditional entropy model to estimate the probability distribution of the transformed coefficients, by incorporating temporal context from consecutive point clouds and the motion estimation/compensation modules.
Meta-Sampler: Almost-Universal yet Task-Oriented Sampling for Point Clouds
In this work, we propose an almost-universal sampler, in our quest for a sampler that can learn to preserve the most useful points for a particular task, yet be inexpensive to adapt to different tasks, models, or datasets.
Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Clouds
To reduce the memory and computational cost, existing point-based pipelines usually adopt task-agnostic random sampling or farthest point sampling to progressively downsample input point clouds, despite the fact that not all points are equally important to the task of object detection.
No Pain, Big Gain: Classify Dynamic Point Cloud Sequences with Static Models by Fitting Feature-level Space-time Surfaces
Scene flow is a powerful tool for capturing the motion field of 3D point clouds.
Ranked #1 on
3D Action Recognition
on NTU RGB+D
STPLS3D: A Large-Scale Synthetic and Real Aerial Photogrammetry 3D Point Cloud Dataset
Specifically, we introduce a synthetic aerial photogrammetry point clouds generation pipeline that takes full advantage of open geospatial data sources and off-the-shelf commercial packages.
3DAC: Learning Attribute Compression for Point Clouds
Finally, the estimated probabilities are used to further compress these transform coefficients to a final attributes bitstream.
SensatUrban: Learning Semantics from Urban-Scale Photogrammetric Point Clouds
Each point in the dataset has been labelled with fine-grained semantic annotations, resulting in a dataset that is three times the size of the previous existing largest photogrammetric point cloud dataset.
Box2Seg: Learning Semantics of 3D Point Clouds with Box-Level Supervision
In this paper, we introduce a neural architecture, termed Box2Seg, to learn point-level semantics of 3D point clouds with bounding box-level supervision.
Detecting and Tracking Small and Dense Moving Objects in Satellite Videos: A Benchmark
Satellite video cameras can provide continuous observation for a large-scale area, which is important for many remote sensing applications.
Learning Semantic Segmentation of Large-Scale Point Clouds with Random Sampling
We study the problem of efficient semantic segmentation of large-scale 3D point clouds.
SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Clouds
Labelling point clouds fully is highly time-consuming and costly.
SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration
Extracting robust and general 3D local features is key to downstream tasks such as point cloud registration and reconstruction.
Ranked #2 on
Point Cloud Registration
on ETH (trained on 3DMatch)
Towards Semantic Segmentation of Urban-Scale 3D Point Clouds: A Dataset, Benchmarks and Challenges
An essential prerequisite for unleashing the potential of supervised deep learning algorithms in the area of 3D scene understanding is the availability of large-scale and richly annotated datasets.
Axiom-based Grad-CAM: Towards Accurate Visualization and Explanation of CNNs
To have a better understanding and usage of Convolution Neural Networks (CNNs), the visualization and interpretation of CNNs has attracted increasing attention in recent years.
Deep Learning for 3D Point Clouds: A Survey
To stimulate future research, this paper presents a comprehensive review of recent progress in deep learning methods for point clouds.
RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds
We study the problem of efficient semantic segmentation for large-scale 3D point clouds.
Ranked #2 on
3D Semantic Segmentation
on Toronto-3D
Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds
The framework directly regresses 3D bounding boxes for all instances in a point cloud, while simultaneously predicting a point-level mask for each instance.
Ranked #14 on
3D Instance Segmentation
on S3DIS
(mPrec metric)
