Search Results for author:
Found 24 papers, 8 papers with code
3D Open-Vocabulary Panoptic Segmentation with 2D-3D Vision-Language Distillation
3D panoptic segmentation is a challenging perception task, especially in autonomous driving.
Point Cloud Self-supervised Learning via 3D to Multi-view Masked Autoencoder
However, a notable limitation of these approaches is that they do not fully utilize the multi-view attributes inherent in 3D point clouds, which is crucial for a deeper understanding of 3D structures.
Bridging the Domain Gap: Self-Supervised 3D Scene Understanding with Foundation Models
Foundation models have achieved remarkable results in 2D and language tasks like image segmentation, object detection, and visual-language understanding.
AsyInst: Asymmetric Affinity with DepthGrad and Color for Box-Supervised Instance Segmentation
Through systematic analysis, we found that the commonly used pairwise affinity loss has two limitations: (1) it works with color affinity but leads to inferior performance with other modalities such as depth gradient, (2)the original affinity loss does not prevent trivial predictions as intended but actually accelerates this process due to the affinity loss term being symmetric.
Class-Level Confidence Based 3D Semi-Supervised Learning
Firstly, a dynamic thresholding strategy is proposed to utilize more unlabeled data, especially for low learning status classes.
R4D: Utilizing Reference Objects for Long-Range Distance Estimation
An edge in the graph encodes the relative distance information between a pair of target and reference objects.
Depth Estimation Matters Most: Improving Per-Object Depth Estimation for Monocular 3D Detection and Tracking
Monocular image-based 3D perception has become an active research area in recent years owing to its applications in autonomous driving.
Disentangling Object Motion and Occlusion for Unsupervised Multi-frame Monocular Depth
Conventional self-supervised monocular depth prediction methods are based on a static environment assumption, which leads to accuracy degradation in dynamic scenes due to the mismatch and occlusion problems introduced by object motions.
Learning from Temporal Gradient for Semi-supervised Action Recognition
Our method achieves the state-of-the-art performance on three video action recognition benchmarks (i. e., Kinetics-400, UCF-101, and HMDB-51) under several typical semi-supervised settings (i. e., different ratios of labeled data).
Multimodal Semi-Supervised Learning for 3D Objects
This paper explores how the coherence of different modelities of 3D data (e. g. point cloud, image, and mesh) can be used to improve data efficiency for both 3D classification and retrieval tasks.
Self-Supervised Modality-Invariant and Modality-Specific Feature Learning for 3D Objects
Our proposed novel self-supervised model learns two types of distinct features: modality-invariant features and modality-specific features.
Advancing Self-supervised Monocular Depth Learning with Sparse LiDAR
Unlike the existing methods that use sparse LiDAR mainly in a manner of time-consuming iterative post-processing, our model fuses monocular image features and sparse LiDAR features to predict initial depth maps.
Ranked #1 on
Depth Completion
on KITTI
Cross-Modal Center Loss for 3D Cross-Modal Retrieval
Cross-modal retrieval aims to learn discriminative and modal-invariant features for data from different modalities.
Cross-modal Center Loss
Cross-modal retrieval aims to learn discriminative and modal-invariant features for data from different modalities.
Self-supervised Modal and View Invariant Feature Learning
By exploring the inherent multi-modality attributes of 3D objects, in this paper, we propose to jointly learn modal-invariant and view-invariant features from different modalities including image, point cloud, and mesh with heterogeneous networks for 3D data.
An Isolated-Signing RGBD Dataset of 100 American Sign Language Signs Produced by Fluent ASL Signers
We have collected a new dataset consisting of color and depth videos of fluent American Sign Language (ASL) signers performing sequences of 100 ASL signs from a Kinect v2 sensor.
Recognizing American Sign Language Nonmanual Signal Grammar Errors in Continuous Videos
Our system is able to recognize grammatical elements on ASL-HW-RGBD from manual gestures, facial expressions, and head movements and successfully detect 8 ASL grammatical mistakes.
Self-supervised Feature Learning by Cross-modality and Cross-view Correspondences
Specifically, 2D image features of rendered images from different views are extracted by a 2D convolutional neural network, and 3D point cloud features are extracted by a graph convolution neural network.
VideoSSL: Semi-Supervised Learning for Video Classification
To minimize the dependence on a large annotated dataset, our proposed semi-supervised method trains from a small number of labeled examples and exploits two regulatory signals from unlabeled data.
Recognizing American Sign Language Manual Signs from RGB-D Videos
In this paper, we propose a 3D Convolutional Neural Network (3DCNN) based multi-stream framework to recognize American Sign Language (ASL) manual signs (consisting of movements of the hands, as well as non-manual face movements in some cases) in real-time from RGB-D videos, by fusing multimodality features including hand gestures, facial expressions, and body poses from multi-channels (RGB, depth, motion, and skeleton joints).
Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey
This paper provides an extensive review of deep learning-based self-supervised general visual feature learning methods from images or videos.
Self-Supervised Image Classification
Self-Supervised Learning
LGAN: Lung Segmentation in CT Scans Using Generative Adversarial Network
Lung segmentation in computerized tomography (CT) images is an important procedure in various lung disease diagnosis.
Coarse-to-fine Semantic Segmentation from Image-level Labels
The enhanced coarse mask is fed to a fully convolutional neural network to be recursively refined.
Self-Supervised Spatiotemporal Feature Learning via Video Rotation Prediction
The success of deep neural networks generally requires a vast amount of training data to be labeled, which is expensive and unfeasible in scale, especially for video collections.
Ranked #42 on
Self-Supervised Action Recognition
on HMDB51
Self-Supervised Action Recognition
Temporal Action Localization
+1
