Search Results for author:
Found 37 papers, 16 papers with code
Scene-R1: Video-Grounded Large Language Models for 3D Scene Reasoning without 3D Annotations
We introduce Scene-R1, a video-grounded framework that learns to reason about 3D scenes without any point-wise 3D instance supervision by pairing reinforcement-learning-driven reasoning with a two-stage grounding pipeline.
How Do Images Align and Complement LiDAR? Towards a Harmonized Multi-modal 3D Panoptic Segmentation
LiDAR-based 3D panoptic segmentation often struggles with the inherent sparsity of data from LiDAR sensors, which makes it challenging to accurately recognize distant or small objects.
Uncertainty Meets Diversity: A Comprehensive Active Learning Framework for Indoor 3D Object Detection
Active learning has emerged as a promising approach to reduce the substantial annotation burden in 3D object detection tasks, spurring several initiatives in outdoor environments.
MotionLab: Unified Human Motion Generation and Editing via the Motion-Condition-Motion Paradigm
Human motion generation and editing are key components of computer graphics and vision.
AugRefer: Advancing 3D Visual Grounding via Cross-Modal Augmentation and Spatial Relation-based Referring
3D visual grounding (3DVG), which aims to correlate a natural language description with the target object within a 3D scene, is a significant yet challenging task.
A Closer Look on Gender Stereotypes in Movie Recommender Systems and Their Implications with Privacy
In the second phase, four inference algorithms were applied to detect gender stereotypes by combining the findings from the first phase with users' feedback data.
Collaborative Tree Search for Enhancing Embodied Multi-Agent Collaboration
Embodied agents based on large language models (LLMs) face significant challenges in collaborative tasks, requiring effective communication and reasonable division of labor to ensure efficient and correct task completion.
Provably Secure Robust Image Steganography via Cross-Modal Error Correction
To leverage provably secure steganography with more effective and high-performance image generation models, and to ensure that stego images can accurately extract secret messages even after being uploaded to social networks and subjected to lossy processing such as JPEG compression, we propose a high-quality, provably secure, and robust image steganography method based on state-of-the-art autoregressive (AR) image generation models using Vector-Quantized (VQ) tokenizers.
Domain Expansion and Boundary Growth for Open-Set Single-Source Domain Generalization
In this paper, we propose a novel learning approach based on domain expansion and boundary growth to expand the scarce source samples and enlarge the boundaries across the known classes that indirectly broaden the boundary between the known and unknown classes.
GaussianBlock: Building Part-Aware Compositional and Editable 3D Scene by Primitives and Gaussians
In this paper, we propose a novel part-aware compositional reconstruction method, called GaussianBlock, that enables semantically coherent and disentangled representations, allowing for precise and physical editing akin to building blocks, while simultaneously maintaining high fidelity.
EventHallusion: Diagnosing Event Hallucinations in Video LLMs
To mitigate this gap, we propose EventHallusion, a novel benchmark that focuses on assessing the VideoLLMs' hallucination toward event, the crux of video analysis.
On-the-fly Point Feature Representation for Point Clouds Analysis
In this paper, we propose On-the-fly Point Feature Representation (OPFR), which captures abundant geometric information explicitly through Curve Feature Generator module.
Unlocking Textual and Visual Wisdom: Open-Vocabulary 3D Object Detection Enhanced by Comprehensive Guidance from Text and Image
Open-vocabulary 3D object detection (OV-3DDet) aims to localize and recognize both seen and previously unseen object categories within any new 3D scene.
Syn-to-Real Unsupervised Domain Adaptation for Indoor 3D Object Detection
Our approach includes an object-aware augmentation strategy to effectively diversify the source domain data, and we introduce a two-branch adaptation framework consisting of an adversarial training branch and a pseudo labeling branch, in order to simultaneously reach holistic-level and class-level domain alignment.
Enhancing Generalizability of Representation Learning for Data-Efficient 3D Scene Understanding
The field of self-supervised 3D representation learning has emerged as a promising solution to alleviate the challenge presented by the scarcity of extensive, well-annotated datasets.
CT3D++: Improving 3D Object Detection with Keypoint-induced Channel-wise Transformer
Firstly, we propose CT3D, which sequentially performs raw-point-based embedding, a standard Transformer encoder, and a channel-wise decoder for point features within each proposal.
Improving 3D Occupancy Prediction through Class-balancing Loss and Multi-scale Representation
3D environment recognition is essential for autonomous driving systems, as autonomous vehicles require a comprehensive understanding of surrounding scenes.
Look Before You Decide: Prompting Active Deduction of MLLMs for Assumptive Reasoning
Recently, Multimodal Large Language Models (MLLMs) have achieved significant success across multiple disciplines due to their exceptional instruction-following capabilities and extensive world knowledge.
View-Consistent 3D Editing with Gaussian Splatting
However, this approach faces a critical issue of multi-view inconsistency, where the guidance images exhibit significant discrepancies across views, leading to mode collapse and visual artifacts of 3DGS.
Dual-Perspective Knowledge Enrichment for Semi-Supervised 3D Object Detection
Our DPKE enriches the knowledge of limited training data, particularly unlabeled data, from two perspectives: data-perspective and feature-perspective.
LASO: Language-guided Affordance Segmentation on 3D Object
With this regard we propose a novel task Language-guided Affordance Segmentation on 3D Object (LASO) which challenges a model to segment a 3D object's part relevant to a given affordance question.
Generalized Few-Shot Point Cloud Segmentation Via Geometric Words
Existing fully-supervised point cloud segmentation methods suffer in the dynamic testing environment with emerging new classes.
Towards Robust Few-shot Point Cloud Semantic Segmentation
Few-shot point cloud semantic segmentation aims to train a model to quickly adapt to new unseen classes with only a handful of support set samples.
Style-Hallucinated Dual Consistency Learning: A Unified Framework for Visual Domain Generalization
Furthermore, we present a novel style hallucination module (SHM) to generate style-diversified samples that are essential to consistency learning.
Synthetic-to-Real Domain Generalized Semantic Segmentation for 3D Indoor Point Clouds
In addition, we augment the point patterns of the source data and introduce non-parametric multi-prototypes to ameliorate the intra-class variance enlarged by the augmented point patterns.
Myopia prediction for adolescents via time-aware deep learning
Result: The mean absolute prediction error on the testing set was 0. 273-0. 257 for spherical equivalent, ranging from 0. 189-0. 160 to 0. 596-0. 473 if we consider different lengths of historical records and different prediction durations.
Rethinking IoU-based Optimization for Single-stage 3D Object Detection
Since Intersection-over-Union (IoU) based optimization maintains the consistency of the final IoU prediction metric and losses, it has been widely used in both regression and classification branches of single-stage 2D object detectors.
Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentation
Furthermore, we present a novel style hallucination module (SHM) to generate style-diversified samples that are essential to consistency learning.
Ranked #8 on
Robust Object Detection
on DWD
Static-Dynamic Co-Teaching for Class-Incremental 3D Object Detection
Deep learning-based approaches have shown remarkable performance in the 3D object detection task.
URIR: Recommendation algorithm of user RNN encoder and item encoder based on knowledge graph
This implies that URIR can effectively use knowledge graph to obtain better user codes and item codes, thereby obtaining better recommendation results.
Few-shot 3D Point Cloud Semantic Segmentation
These fully supervised approaches heavily rely on large amounts of labeled training data that are difficult to obtain and cannot segment new classes after training.
Few-shot 3D Point Cloud Semantic Segmentation
Segmentation
+1
SESS: Self-Ensembling Semi-Supervised 3D Object Detection
The performance of existing point cloud-based 3D object detection methods heavily relies on large-scale high-quality 3D annotations.
MRI Reconstruction Using Deep Bayesian Estimation
Purpose: To develop a deep learning-based Bayesian inference for MRI reconstruction.
Automatic Detection of ECG Abnormalities by using an Ensemble of Deep Residual Networks with Attention
Heart disease is one of the most common diseases causing morbidity and mortality.
PS^2-Net: A Locally and Globally Aware Network for Point-Based Semantic Segmentation
In this paper, we present the PS^2-Net -- a locally and globally aware deep learning framework for semantic segmentation on 3D scene-level point clouds.
Automatic Detection of Atrial Fibrillation Based on Continuous Wavelet Transform and 2D Convolutional Neural Networks
The proposed method analyzed the time-frequency features of the electrocardiogram (ECG), thus being different to conventional AF detecting methods that implement isolating atrial or ventricular activities.
Ranked #2 on
Atrial Fibrillation Detection
on MIT-BIH AF
