421 citations · 640 across the 30 of their papers we have counts for
30 papers
Probabilistically Aligned View-unaligned Clustering with Adaptive Template Selection
Wenhua Dong, Xiao-Jun Wu, Zhenhua Feng +3
In most existing multi-view modeling scenarios, cross-view correspondence (CVC) between instances of the same target from different views, like paired image-text data, is a crucial…
C2C: Component-to-Composition Learning for Zero-Shot Compositional Action Recognition
Rongchang Li, Zhenhua Feng, Tianyang Xu +5
Compositional actions consist of dynamic (verbs) and static (objects) concepts. Humans can easily recognize unseen compositions using the learned concepts. For machines, solving su…
Investigating Self-Supervised Methods for Label-Efficient Learning
Srinivasa Rao Nandam, Sara Atito, Zhenhua Feng +2
Vision transformers combined with self-supervised learning have enabled the development of models which scale across large datasets for several downstream tasks like classification…
Pseudo Labelling for Enhanced Masked Autoencoders
Srinivasa Rao Nandam, Sara Atito, Zhenhua Feng +2
Masked Image Modeling (MIM)-based models, such as SdAE, CAE, GreenMIM, and MixAE, have explored different strategies to enhance the performance of Masked Autoencoders (MAE) by modi…
DailyMAE: Towards Pretraining Masked Autoencoders in One Day
Jiantao Wu, Shentong Mo, Sara Atito +3
Recently, masked image modeling (MIM), an important self-supervised learning (SSL) method, has drawn attention for its effectiveness in learning data representation from unlabeled…
Beyond Accuracy: Statistical Measures and Benchmark for Evaluation of Representation from Self-Supervised Learning
Jiantao Wu, Shentong Mo, Sara Atito +3
Recently, self-supervised metric learning has raised attention for the potential to learn a generic distance function. It overcomes the limitations of conventional supervised one,…
SCD-Net: Spatiotemporal Clues Disentanglement Network for Self-supervised Skeleton-based Action Recognition
Cong Wu, Xiao-Jun Wu, Josef Kittler +4
Contrastive learning has achieved great success in skeleton-based action recognition. However, most existing approaches encode the skeleton sequences as entangled spatiotemporal re…
Masked Momentum Contrastive Learning for Zero-shot Semantic Understanding
Jiantao Wu, Shentong Mo, Muhammad Awais +3
Self-supervised pretraining (SSP) has emerged as a popular technique in machine learning, enabling the extraction of meaningful feature representations without labelled data. In th…
LabelPrompt: Effective Prompt-based Learning for Relation Classification
Wenjie Zhang, Xiaoning Song, Zhenhua Feng +2
Recently, prompt-based learning has gained popularity across many natural language processing (NLP) tasks by reformulating them into a cloze-style format to better align pre-traine…
NFLAT: Non-Flat-Lattice Transformer for Chinese Named Entity Recognition
Shuang Wu, Xiaoning Song, Zhenhua Feng +1
Recently, Flat-LAttice Transformer (FLAT) has achieved great success in Chinese Named Entity Recognition (NER). FLAT performs lexical enhancement by constructing flat lattices, whi…
Vision-Based UAV Self-Positioning in Low-Altitude Urban Environments
Ming Dai, Enhui Zheng, Zhenhua Feng +2
Unmanned Aerial Vehicles (UAVs) rely on satellite systems for stable positioning. However, due to limited satellite coverage or communication disruptions, UAVs may lose signals fro…
MC-SSL0.0: Towards Multi-Concept Self-Supervised Learning
Sara Atito, Muhammad Awais, Ammarah Farooq +2
Self-supervised pretraining is the method of choice for natural language processing models and is rapidly gaining popularity in many vision tasks. Recently, self-supervised pretrai…
NPT-Loss: A Metric Loss with Implicit Mining for Face Recognition
Syed Safwan Khalid, Muhammad Awais, Chi-Ho Chan +4
Face recognition (FR) using deep convolutional neural networks (DCNNs) has seen remarkable success in recent years. One key ingredient of DCNN-based FR is the appropriate design of…
Separable Batch Normalization for Robust Facial Landmark Localization with Cross-protocol Network Training
Shuangping Jin, Zhenhua Feng, Wankou Yang +1
A big, diverse and balanced training data is the key to the success of deep neural network training. However, existing publicly available datasets used in facial landmark localizat…
A Flatter Loss for Bias Mitigation in Cross-dataset Facial Age Estimation
Ali Akbari, Muhammad Awais, Zhen-Hua Feng +2
The most existing studies in the facial age estimation assume training and test images are captured under similar shooting conditions. However, this is rarely valid in real-world a…
DD-CNN: Depthwise Disout Convolutional Neural Network for Low-complexity Acoustic Scene Classification
Jingqiao Zhao, Zhen-Hua Feng, Qiuqiang Kong +2
This paper presents a Depthwise Disout Convolutional Neural Network (DD-CNN) for the detection and classification of urban acoustic scenes. Specifically, we use log-mel as feature…
Affine Non-negative Collaborative Representation Based Pattern Classification
He-Feng Yin, Xiao-Jun Wu, Zhen-Hua Feng +1
During the past decade, representation-based classification methods have received considerable attention in pattern recognition. In particular, the recently proposed non-negative r…
AFAT: Adaptive Failure-Aware Tracker for Robust Visual Object Tracking
Tianyang Xu, Zhen-Hua Feng, Xiao-Jun Wu +1
Siamese approaches have achieved promising performance in visual object tracking recently. The key to the success of Siamese trackers is to learn appearance-invariant feature embed…
An Accelerated Correlation Filter Tracker
Tianyang Xu, Zhen-Hua Feng, Xiao-Jun Wu +1
Recent visual object tracking methods have witnessed a continuous improvement in the state-of-the-art with the development of efficient discriminative correlation filters (DCF) and…
Learning a Representation with the Block-Diagonal Structure for Pattern Classification
He-Feng Yin, Xiao-Jun Wu, Josef Kittler +1
Sparse-representation-based classification (SRC) has been widely studied and developed for various practical signal classification applications. However, the performance of a SRC-b…
Dual Encoder-Decoder based Generative Adversarial Networks for Disentangled Facial Representation Learning
Cong Hu, Zhen-Hua Feng, Xiao-Jun Wu +1
To learn disentangled representations of facial images, we present a Dual Encoder-Decoder based Generative Adversarial Network (DED-GAN). In the proposed method, both the generator…
Joint Group Feature Selection and Discriminative Filter Learning for Robust Visual Object Tracking
Tianyang Xu, Zhen-Hua Feng, Xiao-Jun Wu +1
We propose a new Group Feature Selection method for Discriminative Correlation Filters (GFS-DCF) based visual object tracking. The key innovation of the proposed method is to perfo…
Learning Adaptive Discriminative Correlation Filters via Temporal Consistency Preserving Spatial Feature Selection for Robust Visual Tracking
Tianyang Xu, Zhen-Hua Feng, Xiao-Jun Wu +1
With efficient appearance learning models, Discriminative Correlation Filter (DCF) has been proven to be very successful in recent video object tracking benchmarks and competitions…
Evaluation of Dense 3D Reconstruction from 2D Face Images in the Wild
Zhen-Hua Feng, Patrik Huber, Josef Kittler +5
This paper investigates the evaluation of dense 3D face reconstruction from a single 2D image in the wild. To this end, we organise a competition that provides a new benchmark data…