Search Results for author:
Found 34 papers, 5 papers with code
Super Normal Vector for Activity Recognition Using Depth Sequences
This paper presents a new framework for human activity recognition from video sequences captured by a depth camera.
Unambiguous Text Localization and Retrieval for Cluttered Scenes
Text instance as one category of self-described objects provides valuable information for understanding and describing cluttered scenes.
Self-Guiding Multimodal LSTM - when we do not have a perfect training dataset for image captioning
Afterwards, during the training of sg-LSTM on the rest training data, this guiding information serves as additional input to the network along with the image representations and the ground-truth descriptions.
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
Discovering Spatio-Temporal Action Tubes
In this paper, we address the challenging problem of spatial and temporal action detection in videos.
Incremental Scene Synthesis
We present a method to incrementally generate complete 2D or 3D scenes with the following properties: (a) it is globally consistent at each step according to a learned scene prior, (b) real observations of a scene can be incorporated while observing global consistency, (c) unobserved regions can be hallucinated locally in consistence with previous observations, hallucinations and global priors, and (d) hallucinations are statistical in nature, i. e., different scenes can be generated from the same observations.
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.
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.
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
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).
3DFPN-HS$^2$: 3D Feature Pyramid Network Based High Sensitivity and Specificity Pulmonary Nodule Detection
Accurate detection of pulmonary nodules with high sensitivity and specificity is essential for automatic lung cancer diagnosis from CT scans.
Accurate and Robust Pulmonary Nodule Detection by 3D Feature Pyramid Network with Self-supervised Feature Learning
Accurate detection of pulmonary nodules with high sensitivity and specificity is essential for automatic lung cancer diagnosis from CT scans.
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.
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.
Weakly Supervised Semantic Segmentation in 3D Graph-Structured Point Clouds of Wild Scenes
The deficiency of 3D segmentation labels is one of the main obstacles to effective point cloud segmentation, especially for scenes in the wild with varieties of different objects.
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 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.
Monocular Human Pose Estimation: A Survey of Deep Learning-based Methods
Vision-based monocular human pose estimation, as one of the most fundamental and challenging problems in computer vision, aims to obtain posture of the human body from input images or video sequences.
Cross-modal Center Loss
Cross-modal retrieval aims to learn discriminative and modal-invariant features for data from different modalities.
FESTA: Flow Estimation via Spatial-Temporal Attention for Scene Point Clouds
Scene flow depicts the dynamics of a 3D scene, which is critical for various applications such as autonomous driving, robot navigation, AR/VR, etc.
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.
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
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.
Deep Learning-based Action Detection in Untrimmed Videos: A Survey
The task of temporal activity detection in untrimmed videos aims to localize the temporal boundary of actions and classify the action categories.
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.
The State of Aerial Surveillance: A Survey
The rapid emergence of airborne platforms and imaging sensors are enabling new forms of aerial surveillance due to their unprecedented advantages in scale, mobility, deployment and covert observation capabilities.
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.
PSMNet: Position-aware Stereo Merging Network for Room Layout Estimation
In this paper, we propose a new deep learning-based method for estimating room layout given a pair of 360 panoramas.
Sequential Point Clouds: A Survey
Point cloud has drawn more and more research attention as well as real-world applications.
ASL-Homework-RGBD Dataset: An annotated dataset of 45 fluent and non-fluent signers performing American Sign Language homeworks
We are releasing a dataset containing videos of both fluent and non-fluent signers using American Sign Language (ASL), which were collected using a Kinect v2 sensor.
POTLoc: Pseudo-Label Oriented Transformer for Point-Supervised Temporal Action Localization
This paper tackles the challenge of point-supervised temporal action detection, wherein only a single frame is annotated for each action instance in the training set.
ADM-Loc: Actionness Distribution Modeling for Point-supervised Temporal Action Localization
This paper addresses the challenge of point-supervised temporal action detection, in which only one frame per action instance is annotated in the training set.
Burst Denoising via Temporally Shifted Wavelet Transforms
As a result, imaging pipelines often rely on computational photography to improve SNR by fusing multiple short exposures.
