Search Results for author:
Found 62 papers, 27 papers with code
On Diverse Asynchronous Activity Anticipation
We investigate the joint anticipation of long-term activity labels and their corresponding times with the aim of improving both the naturalness and diversity of predictions.
A Label-Aware Autoregressive Framework for Cross-Domain NER
In doing so, label information contained in the embedding vectors can be effectively transferred to the target domain, and Bi-LSTM can further model the label relationship among different domains by pre-train and then fine-tune setting.
Cross-Domain Named Entity Recognition
named-entity-recognition
+2
Extracting Clean and Balanced Subset for Noisy Long-tailed Classification
To solve the joint issue of long-tailed distribution and label noise, most previous works usually aim to design a noise detector to distinguish the noisy and clean samples.
Selective, Interpretable, and Motion Consistent Privacy Attribute Obfuscation for Action Recognition
Global obfuscation hides privacy sensitive regions, but also contextual regions important for action recognition.
Optimal Transport for Structure Learning Under Missing Data
Merely filling in missing values with existing imputation methods and subsequently applying structure learning on the complete data is empirical shown to be sub-optimal.
Pretext Training Algorithms for Event Sequence Data
Pretext training followed by task-specific fine-tuning has been a successful approach in vision and language domains.
Bayesian Factorised Granger-Causal Graphs For Multivariate Time-series Data
We study the problem of automatically discovering Granger causal relations from observational multivariate time-series data.
Variational DAG Estimation via State Augmentation With Stochastic Permutations
Estimating the structure of a Bayesian network, in the form of a directed acyclic graph (DAG), from observational data is a statistically and computationally hard problem with essential applications in areas such as causal discovery.
A Class-aware Optimal Transport Approach with Higher-Order Moment Matching for Unsupervised Domain Adaptation
Additionally, we propose minimizing class-aware Higher-order Moment Matching (HMM) to align the corresponding class regions on the source and target domains.
HGAttack: Transferable Heterogeneous Graph Adversarial Attack
Heterogeneous Graph Neural Networks (HGNNs) are increasingly recognized for their performance in areas like the web and e-commerce, where resilience against adversarial attacks is crucial.
Audio Deepfake Detection with Self-Supervised WavLM and Multi-Fusion Attentive Classifier
In this paper, we report our efforts to combine the self-supervised WavLM model and Multi-Fusion Attentive classifier for audio deepfake detection.
Dual Conditioned Diffusion Models for Out-Of-Distribution Detection: Application to Fetal Ultrasound Videos
To detect OOD samples in this context, the resulting model should generalise to the intra-anatomy variations while rejecting similar OOD samples.
Cross-adversarial local distribution regularization for semi-supervised medical image segmentation
Medical semi-supervised segmentation is a technique where a model is trained to segment objects of interest in medical images with limited annotated data.
Towards Generalising Neural Topical Representations
To do so, we propose to enhance NTMs by narrowing the semantical distance between similar documents, with the underlying assumption that documents from different corpora may share similar semantics.
Multiscale Memory Comparator Transformer for Few-Shot Video Segmentation
We present a meta-learned Multiscale Memory Comparator (MMC) for few-shot video segmentation that combines information across scales within a transformer decoder.
Learning Directed Graphical Models with Optimal Transport
Estimating the parameters of a probabilistic directed graphical model from incomplete data remains a long-standing challenge.
Generating Adversarial Examples with Task Oriented Multi-Objective Optimization
The key factor for the success of adversarial training is the capability to generate qualified and divergent adversarial examples which satisfy some objectives/goals (e. g., finding adversarial examples that maximize the model losses for simultaneously attacking multiple models).
A Unified Multiscale Encoder-Decoder Transformer for Video Segmentation
In this paper, we present an end-to-end trainable unified multiscale encoder-decoder transformer that is focused on dense prediction tasks in video.
Transformed Distribution Matching for Missing Value Imputation
The key to missing value imputation is to capture the data distribution with incomplete samples and impute the missing values accordingly.
Vector Quantized Wasserstein Auto-Encoder
Learning deep discrete latent presentations offers a promise of better symbolic and summarized abstractions that are more useful to subsequent downstream tasks.
Adaptive Distribution Calibration for Few-Shot Learning with Hierarchical Optimal Transport
A recent solution to this problem is calibrating the distribution of these few sample classes by transferring statistics from the base classes with sufficient examples, where how to decide the transfer weights from base classes to novel classes is the key.
Uncertainty Estimation for Multi-view Data: The Power of Seeing the Whole Picture
Uncertainty estimation is essential to make neural networks trustworthy in real-world applications.
Feature-based Learning for Diverse and Privacy-Preserving Counterfactual Explanations
Interpretable machine learning seeks to understand the reasoning process of complex black-box systems that are long notorious for lack of explainability.
Sports Video Analysis on Large-Scale Data
In this paper, we propose a novel large-scale NBA dataset for Sports Video Analysis (NSVA) with a focus on captioning, to address the above challenges.
Learning to Re-weight Examples with Optimal Transport for Imbalanced Classification
Specifically, we view the training set as an imbalanced distribution over its samples, which is transported by OT to a balanced distribution obtained from the meta set.
P3IV: Probabilistic Procedure Planning from Instructional Videos with Weak Supervision
Our model is based on a transformer equipped with a memory module, which maps the start and goal observations to a sequence of plausible actions.
Representing Mixtures of Word Embeddings with Mixtures of Topic Embeddings
This paper introduces a new topic-modeling framework where each document is viewed as a set of word embedding vectors and each topic is modeled as an embedding vector in the same embedding space.
A Unified Wasserstein Distributional Robustness Framework for Adversarial Training
We introduce a new Wasserstein cost function and a new series of risk functions, with which we show that standard AT methods are special cases of their counterparts in our framework.
Neural Attention-Aware Hierarchical Topic Model
Neural topic models (NTMs) apply deep neural networks to topic modelling.
Contrastively Enforcing Distinctiveness for Multi-Label Classification
Recently, as an effective way of learning latent representations, contrastive learning has been increasingly popular and successful in various domains.
Interpretable Deep Feature Propagation for Early Action Recognition
Early action recognition (action prediction) from limited preliminary observations plays a critical role for streaming vision systems that demand real-time inference, as video actions often possess elongated temporal spans which cause undesired latency.
Review of Video Predictive Understanding: Early Action Recognition and Future Action Prediction
Action prediction is a major sub-area of video predictive understanding and is the focus of this review.
MOST: Multi-Source Domain Adaptation via Optimal Transport for Student-Teacher Learning
To this end, we propose in this paper a novel model for multi-source DA using the theory of optimal transport and imitation learning.
Imitation Learning
Multi-Source Unsupervised Domain Adaptation
+1
Improved and Efficient Text Adversarial Attacks using Target Information
There has been recently a growing interest in studying adversarial examples on natural language models in the black-box setting.
Cascade of correlated electron states in a kagome superconductor CsV3Sb5
At a temperature far above the superconducting transition Tc ~ 2. 5 K, we reveal a tri-directional charge order with a 2a0 period that breaks the translation symmetry of the lattice.
Superconductivity Strongly Correlated Electrons
Topic Modelling Meets Deep Neural Networks: A Survey
Topic modelling has been a successful technique for text analysis for almost twenty years.
Nanoscale decoupling of electronic nematicity and structural anisotropy in FeSe thin films
In this work, we discover that electronic nematicity can be locally decoupled from the underlying structural anisotropy in strain-engineered iron-selenide (FeSe) thin films.
Strongly Correlated Electrons Materials Science Superconductivity
Understanding and Achieving Efficient Robustness with Adversarial Supervised Contrastive Learning
Central to this approach is the selection of positive (similar) and negative (dissimilar) sets to provide the model the opportunity to `contrast' between data and class representation in the latent space.
Where Are You Heading? Dynamic Trajectory Prediction With Expert Goal Examples
Goal-conditioned approaches recently have been found very useful to human trajectory prediction, when adequate goal estimates are provided.
Ranked #5 on
Trajectory Prediction
on ETH
OTLDA: A Geometry-aware Optimal Transport Approach for Topic Modeling
We present an optimal transport framework for learning topics from textual data.
Explain2Attack: Text Adversarial Attacks via Cross-Domain Interpretability
Training robust deep learning models for down-stream tasks is a critical challenge.
Learning to Attack with Fewer Pixels: A Probabilistic Post-hoc Framework for Refining Arbitrary Dense Adversarial Attacks
Deep neural network image classifiers are reported to be susceptible to adversarial evasion attacks, which use carefully crafted images created to mislead a classifier.
Improving Ensemble Robustness by Collaboratively Promoting and Demoting Adversarial Robustness
An important technique of this approach is to control the transferability of adversarial examples among ensemble members.
Neural Topic Model via Optimal Transport
Recently, Neural Topic Models (NTMs) inspired by variational autoencoders have obtained increasingly research interest due to their promising results on text analysis.
Ranked #5 on
Topic Models
on 20NewsGroups
MED-TEX: Transferring and Explaining Knowledge with Less Data from Pretrained Medical Imaging Models
To interpret the teacher model and assist the learning of the student, an explainer module is introduced to highlight the regions of an input that are important for the predictions of the teacher model.
SummPip: Unsupervised Multi-Document Summarization with Sentence Graph Compression
Obtaining training data for multi-document summarization (MDS) is time consuming and resource-intensive, so recent neural models can only be trained for limited domains.
Improving Adversarial Robustness by Enforcing Local and Global Compactness
The fact that deep neural networks are susceptible to crafted perturbations severely impacts the use of deep learning in certain domains of application.
SpanMlt: A Span-based Multi-Task Learning Framework for Pair-wise Aspect and Opinion Terms Extraction
To this end, this paper proposes an end-to-end method to solve the task of Pair-wise Aspect and Opinion Terms Extraction (PAOTE).
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+3
RDCFace: Radial Distortion Correction for Face Recognition
The effects of radial lens distortion often appear in wide-angle cameras of surveillance and safeguard systems, which may severely degrade performances of previous face recognition algorithms.
Leveraging Cross Feedback of User and Item Embeddings with Attention for Variational Autoencoder based Collaborative Filtering
Based on the ELBOs, we propose a VAE-based Bayesian MF framework.
A Context-based Framework for Modeling the Role and Function of On-line Resource Citations in Scientific Literature
We introduce a new task of modeling the role and function for on-line resource citations in scientific literature.
Perturbations are not Enough: Generating Adversarial Examples with Spatial Distortions
Deep neural network image classifiers are reported to be susceptible to adversarial evasion attacks, which use carefully crafted images created to mislead a classifier.
Spatiotemporal Feature Residual Propagation for Action Prediction
Recognizing actions from limited preliminary video observations has seen considerable recent progress.
daBNN: A Super Fast Inference Framework for Binary Neural Networks on ARM devices
It is always well believed that Binary Neural Networks (BNNs) could drastically accelerate the inference efficiency by replacing the arithmetic operations in float-valued Deep Neural Networks (DNNs) with bit-wise operations.
Leveraging Meta Information in Short Text Aggregation
Short texts such as tweets often contain insufficient word co-occurrence information for training conventional topic models.
Variational Autoencoders for Sparse and Overdispersed Discrete Data
Many applications, such as text modelling, high-throughput sequencing, and recommender systems, require analysing sparse, high-dimensional, and overdispersed discrete (count-valued or binary) data.
Foreground-aware Pyramid Reconstruction for Alignment-free Occluded Person Re-identification
FPR uses the error from robust reconstruction over spatial pyramid features to measure similarities between two persons.
Dirichlet belief networks for topic structure learning
Recently, considerable research effort has been devoted to developing deep architectures for topic models to learn topic structures.
Inter and Intra Topic Structure Learning with Word Embeddings
One important task of topic modeling for text analysis is interpretability.
MetaLDA: a Topic Model that Efficiently Incorporates Meta information
Besides the text content, documents and their associated words usually come with rich sets of meta informa- tion, such as categories of documents and semantic/syntactic features of words, like those encoded in word embeddings.
Leveraging Node Attributes for Incomplete Relational Data
Relational data are usually highly incomplete in practice, which inspires us to leverage side information to improve the performance of community detection and link prediction.
Synthesizing Filamentary Structured Images with GANs
This paper aims at synthesizing filamentary structured images such as retinal fundus images and neuronal images, as follows: Given a ground-truth, to generate multiple realistic looking phantoms.
