Search Results for author:
Found 16 papers, 9 papers with code
Structure-Aware Correspondence Learning for Relative Pose Estimation
Despite the success of existing 3D correspondence-based methods, the reliance on explicit feature matching suffers from small overlaps in visible regions and unreliable feature estimation for invisible regions.
State Space Model Meets Transformer: A New Paradigm for 3D Object Detection
To the best of our knowledge, this is the first method to model queries as system states and scene points as system inputs, which can simultaneously update scene point features and query features with linear complexity.
Ranked #1 on
3D Object Detection
on ScanNetV2
Learning Shape-Independent Transformation via Spherical Representations for Category-Level Object Pose Estimation
Category-level object pose estimation aims to determine the pose and size of novel objects in specific categories.
Rethinking Masked Representation Learning for 3D Point Cloud Understanding
Recently, masked point modeling-based methods have shown significant performance improvements for point cloud understanding, yet these methods rely on overlapping grouping strategies (k-nearest neighbor algorithm) resulting in early leakage of structural information of mask groups, and overlook the semantic modeling of object components resulting in parts with the same semantics having obvious feature differences due to position differences.
Ranked #7 on
Few-Shot 3D Point Cloud Classification
on ModelNet40 5-way (20-shot)
(using extra training data)
3D Part Segmentation
Few-Shot 3D Point Cloud Classification
+1
DN-4DGS: Denoised Deformable Network with Temporal-Spatial Aggregation for Dynamic Scene Rendering
Dynamic scenes rendering is an intriguing yet challenging problem.
MotionGS: Exploring Explicit Motion Guidance for Deformable 3D Gaussian Splatting
Specifically, we first introduce an optical flow decoupling module that decouples optical flow into camera flow and motion flow, corresponding to camera movement and object motion respectively.
Plane2Depth: Hierarchical Adaptive Plane Guidance for Monocular Depth Estimation
Specifically, in the proposed plane guided depth generator (PGDG), we design a set of plane queries as prototypes to softly model planes in the scene and predict per-pixel plane coefficients.
Pamba: Enhancing Global Interaction in Point Clouds via State Space Model
Transformers have demonstrated impressive results for 3D point cloud semantic segmentation.
Ranked #6 on
3D Semantic Segmentation
on ScanNet200
Instance-Adaptive and Geometric-Aware Keypoint Learning for Category-Level 6D Object Pose Estimation
(2) The second design is a Geometric-Aware Feature Aggregation module, which can efficiently integrate the local and global geometric information into keypoint features.
Proxy-RLHF: Decoupling Generation and Alignment in Large Language Model with Proxy
Reinforcement Learning from Human Feedback (RLHF) is the prevailing approach to ensure Large Language Models (LLMs) align with human values.
Unifying Visual and Vision-Language Tracking via Contrastive Learning
Single object tracking aims to locate the target object in a video sequence according to the state specified by different modal references, including the initial bounding box (BBOX), natural language (NL), or both (NL+BBOX).
Ranked #2 on
Visual Object Tracking
on AVisT
RHOBIN Challenge: Reconstruction of Human Object Interaction
Modeling the interaction between humans and objects has been an emerging research direction in recent years.
Not Every Side Is Equal: Localization Uncertainty Estimation for Semi-Supervised 3D Object Detection
Semi-supervised 3D object detection from point cloud aims to train a detector with a small number of labeled data and a large number of unlabeled data.
Proposal-Based Multiple Instance Learning for Weakly-Supervised Temporal Action Localization
Weakly-supervised temporal action localization aims to localize and recognize actions in untrimmed videos with only video-level category labels during training.
Ranked #3 on
Weakly Supervised Action Localization
on THUMOS’14
Multiple Instance Learning
Weakly Supervised Action Localization
+2
Uncertainty Guided Collaborative Training for Weakly Supervised Temporal Action Detection
To alleviate this problem, we propose a novel Uncertainty Guided Collaborative Training (UGCT) strategy, which mainly includes two key designs: (1) The first design is an online pseudo label generation module, in which the RGB and FLOW streams work collaboratively to learn from each other.
Action Unit Memory Network for Weakly Supervised Temporal Action Localization
In this paper, we present an Action Unit Memory Network (AUMN) for weakly supervised temporal action localization, which can mitigate the above two challenges by learning an action unit memory bank.
Ranked #7 on
Weakly Supervised Action Localization
on THUMOS14
