Search Results for author:
Found 41 papers, 14 papers with code
Semantic Embedding Space for Zero-Shot Action Recognition
In this framework a mapping is constructed between visual features and a human interpretable semantic description of each category, allowing categories to be recognised in the absence of any training data.
Ranked #31 on
Zero-Shot Action Recognition
on UCF101
Discovery of Shared Semantic Spaces for Multi-Scene Video Query and Summarization
The growing rate of public space CCTV installations has generated a need for automated methods for exploiting video surveillance data including scene understanding, query, behaviour annotation and summarization.
Transductive Zero-Shot Action Recognition by Word-Vector Embedding
This is a more challenging problem than existing ZSL of still images and/or attributes, because the mapping between video spacetime features of actions and the semantic space is more complex and harder to learn for the purpose of generalising over any cross-category domain shift.
Latent Model Ensemble with Auto-localization
Deep Convolutional Neural Networks (CNN) have exhibited superior performance in many visual recognition tasks including image classification, object detection, and scene label- ing, due to their large learning capacity and resistance to overfit.
Multi-Task Zero-Shot Action Recognition with Prioritised Data Augmentation
In this work, we improve the ability of ZSL to generalise across this domain shift in both model- and data-centric ways by formulating a visual-semantic mapping with better generalisation properties and a dynamic data re-weighting method to prioritise auxiliary data that are relevant to the target classes.
Ranked #7 on
Zero-Shot Action Recognition
on Olympics
Fully Convolutional Measurement Network for Compressive Sensing Image Reconstruction
Recently, deep learning methods have made a significant improvement in compressive sensing image reconstruction task.
Motion Segmentation by Exploiting Complementary Geometric Models
Many real-world sequences cannot be conveniently categorized as general or degenerate; in such cases, imposing a false dichotomy in using the fundamental matrix or homography model for motion segmentation would lead to difficulty.
Ranked #1 on
Motion Segmentation
on KT3DMoSeg
Image Ordinal Classification and Understanding: Grid Dropout with Masking Label
Finally we demonstrate the effectiveness of both approaches by visualizing the Class Activation Map (CAM) and discover that grid dropout is more aware of the whole facial areas and more robust than neuron dropout for small training dataset.
Learning for Multi-Model and Multi-Type Fitting
Multi-model fitting has been extensively studied from the random sampling and clustering perspectives.
Robust Video Background Identification by Dominant Rigid Motion Estimation
In this paper, we propose an efficient local-to-global method to identify background, based on the assumption that as long as there is sufficient camera motion, the cumulative background features will have the largest amount of trajectories.
Learning for Multi-Type Subspace Clustering
Subspace clustering has been extensively studied from the hypothesis-and-test, algebraic, and spectral clustering based perspectives.
C3AE: Exploring the Limits of Compact Model for Age Estimation
Recently, MobileNets and ShuffleNets have been proposed to reduce the number of parameters, yielding lightweight models.
Ranked #3 on
Age Estimation
on FGNET
Zero-Shot Crowd Behavior Recognition
To that end, we relax the common assumption that each individual crowd video instance is only associated with a single crowd attribute.
3D Rigid Motion Segmentation with Mixed and Unknown Number of Models
Many real-world video sequences cannot be conveniently categorized as general or degenerate; in such cases, imposing a false dichotomy in using the fundamental matrix or homography model for motion segmentation on video sequences would lead to difficulty.
Weakly Supervised Semantic Point Cloud Segmentation:Towards 10X Fewer Labels
Point cloud analysis has received much attention recently; and segmentation is one of the most important tasks.
Weakly Supervised Semantic Point Cloud Segmentation: Towards 10x Fewer Labels
Point cloud analysis has received much attention recently; and segmentation is one of the most important tasks.
Learning Category-level Shape Saliency via Deep Implicit Surface Networks
Given the large shape variations among different instances of a same category, we are formally interested in developing a quantity defined for individual points on a continuous object surface; the quantity specifies how individual surface points contribute to the formation of the shape as the category.
ARMOURED: Adversarially Robust MOdels using Unlabeled data by REgularizing Diversity
In this paper, we propose ARMOURED, an adversarially robust training method based on semi-supervised learning that consists of two components.
Label-Efficient Point Cloud Semantic Segmentation: An Active Learning Approach
Deep learning models are the state-of-the-art methods for semantic point cloud segmentation, the success of which relies on the availability of large-scale annotated datasets.
Multi-scale GCN-assisted two-stage network for joint segmentation of retinal layers and disc in peripapillary OCT images
An accurate and automated tissue segmentation algorithm for retinal optical coherence tomography (OCT) images is crucial for the diagnosis of glaucoma.
Medical Image Segmentation
Retinal OCT Layer Segmentation
+1
Sequential Learning on Liver Tumor Boundary Semantics and Prognostic Biomarker Mining
(2) The sampled deep vertex features with positional embedding are mapped into a sequential space and decoded by a multilayer perceptron (MLP) for semantic classification.
3D AffordanceNet: A Benchmark for Visual Object Affordance Understanding
The ability to understand the ways to interact with objects from visual cues, a. k. a.
Ranked #1 on
Affordance Detection
on 3D AffordanceNet
Revisiting Superpixels for Active Learning in Semantic Segmentation With Realistic Annotation Costs
Our results strongly argue for the use of superpixel-based AL for semantic segmentation and highlight the importance of using realistic annotation costs in evaluating such methods.
Diverse and Consistent Multi-view Networks for Semi-supervised Regression
Label collection is costly in many applications, which poses the need for label-efficient learning.
On Automatic Data Augmentation for 3D Point Cloud Classification
Data augmentation is an important technique to reduce overfitting and improve learning performance, but existing works on data augmentation for 3D point cloud data are based on heuristics.
Ranked #1 on
3D Point Cloud Data Augmentation
on ModelNet40
Open-Set Semi-Supervised Learning for 3D Point Cloud Understanding
We also demonstrate the feasibility of a more efficient training strategy.
Weakly Supervised 3D Point Cloud Segmentation via Multi-Prototype Learning
Addressing the annotation challenge in 3D Point Cloud segmentation has inspired research into weakly supervised learning.
Revisiting Pretraining for Semi-Supervised Learning in the Low-Label Regime
Recent studies combined finetuning (FT) from pretrained weights with SSL to mitigate the challenges and claimed superior results in the low-label regime.
Exploring Diversity-based Active Learning for 3D Object Detection in Autonomous Driving
3D object detection has recently received much attention due to its great potential in autonomous vehicle (AV).
SemiCurv: Semi-Supervised Curvilinear Structure Segmentation
In this work, we propose SemiCurv, a semi-supervised learning (SSL) framework for curvilinear structure segmentation that is able to utilize such unlabelled data to reduce the labelling burden.
Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering
Test-time training (TTT) emerges as a solution to this adaptation under a realistic scenario where access to full source domain data is not available and instant inference on target domain is required.
Deep Negative Correlation Classification
Ensemble learning serves as a straightforward way to improve the performance of almost any machine learning algorithm.
Transformation-Invariant Network for Few-Shot Object Detection in Remote Sensing Images
Object detection in remote sensing images relies on a large amount of labeled data for training.
Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering Regularized Self-Training
Test-time training (TTT) emerges as a solution to this adaptation under a realistic scenario where access to full source domain data is not available, and instant inference on the target domain is required.
STFAR: Improving Object Detection Robustness at Test-Time by Self-Training with Feature Alignment Regularization
This motivates us to explore adapting an object detection model at test-time, a. k. a.
On the Robustness of Open-World Test-Time Training: Self-Training with Dynamic Prototype Expansion
Existing approaches often focus on improving test-time training performance under well-curated target domain data.
Towards Real-World Test-Time Adaptation: Tri-Net Self-Training with Balanced Normalization
Test-Time Adaptation aims to adapt source domain model to testing data at inference stage with success demonstrated in adapting to unseen corruptions.
Semi-Supervised Object Detection with Uncurated Unlabeled Data for Remote Sensing Images
Semi-supervised object detection (SSOD) methods tackle this issue by generating pseudo-labels for the unlabeled data, assuming that all classes found in the unlabeled dataset are also represented in the labeled data.
Improving the Generalization of Segmentation Foundation Model under Distribution Shift via Weakly Supervised Adaptation
The success of large language models has inspired the computer vision community to explore image segmentation foundation model that is able to zero/few-shot generalize through prompt engineering.
CLIP-guided Source-free Object Detection in Aerial Images
Domain adaptation is crucial in aerial imagery, as the visual representation of these images can significantly vary based on factors such as geographic location, time, and weather conditions.
