Search Results for author:
Found 61 papers, 25 papers with code
Unsupervised Search for Ethnic Minorities' Medical Segmentation Training Set
This article investigates the critical issue of dataset bias in medical imaging, with a particular emphasis on racial disparities caused by uneven population distribution in dataset collection.
Labels Generated by Large Language Model Helps Measuring People's Empathy in Vitro
In this paper, we evaluate this approach in the emerging field of empathy computing -- automating the prediction of psychological questionnaire outcomes from inputs like text sequences.
Ranked from Within: Ranking Large Multimodal Models for Visual Question Answering Without Labels
As large multimodal models (LMMs) are increasingly deployed across diverse applications, the need for adaptable, real-world model ranking has become paramount.
When Spatial meets Temporal in Action Recognition
Capturing the rich temporal evolution of video frames, while preserving their spatial details, is crucial for improving accuracy.
Visual Prompting in LLMs for Enhancing Emotion Recognition
Vision Large Language Models (VLLMs) are transforming the intersection of computer vision and natural language processing.
LEGO: Learnable Expansion of Graph Operators for Multi-Modal Feature Fusion
In computer vision tasks, features often come from diverse representations, domains, and modalities, such as text, images, and videos.
Toward a Holistic Evaluation of Robustness in CLIP Models
For instance, the architecture of the visual encoder in CLIP plays a significant role in their robustness against 3D corruption.
TrackNetV4: Enhancing Fast Sports Object Tracking with Motion Attention Maps
We refer to our lightweight, plug-and-play solution, built on top of the existing TrackNet, as TrackNetV4.
MRAC Track 1: 2nd Workshop on Multimodal, Generative and Responsible Affective Computing
With the rapid advancements in multimodal generative technology, Affective Computing research has provoked discussion about the potential consequences of AI systems equipped with emotional intelligence.
MIP-GAF: A MLLM-annotated Benchmark for Most Important Person Localization and Group Context Understanding
Estimating the Most Important Person (MIP) in any social event setup is a challenging problem mainly due to contextual complexity and scarcity of labeled data.
MADE-for-ASD: A Multi-Atlas Deep Ensemble Network for Diagnosing Autism Spectrum Disorder
We experiment with the well-known publicly available ABIDE (Autism Brain Imaging Data Exchange) I dataset, consisting of resting state fMRI data from 17 different laboratories around the globe.
Ranked #1 on
Autism detection
on ABIDE I CPAC (NYU Subset)
Motion meets Attention: Video Motion Prompts
We formalize this process as a motion prompt layer and incorporate the regularization term into the loss function to learn better motion prompts.
What Does Softmax Probability Tell Us about Classifiers Ranking Across Diverse Test Conditions?
This work aims to develop a measure that can accurately rank the performance of various classifiers when they are tested on unlabeled data from out-of-distribution (OOD) distributions.
FunnelNet: An End-to-End Deep Learning Framework to Monitor Digital Heart Murmur in Real-Time
Conclusion: The proposed model offers a deep learning framework for real-time accurate heart murmur detection within limited resources.
Authentic Emotion Mapping: Benchmarking Facial Expressions in Real News
In this paper, we present a novel benchmark for Emotion Recognition using facial landmarks extracted from realistic news videos.
DiabetesNet: A Deep Learning Approach to Diabetes Diagnosis
Diabetes, resulting from inadequate insulin production or utilization, causes extensive harm to the body.
An Empirical Study Into What Matters for Calibrating Vision-Language Models
Vision-Language Models (VLMs) have emerged as the dominant approach for zero-shot recognition, adept at handling diverse scenarios and significant distribution changes.
A Closer Look at the Robustness of Contrastive Language-Image Pre-Training (CLIP)
Driven by the above, this work comprehensively investigates the safety objectives of CLIP models, specifically focusing on three key properties: resilience to visual factor variations, calibrated uncertainty estimations, and the ability to detect anomalous inputs.
Meet JEANIE: a Similarity Measure for 3D Skeleton Sequences via Temporal-Viewpoint Alignment
For a support sequence, we match it with view-simulated query sequences, as in the popular Dynamic Time Warping (DTW).
Advancing Video Anomaly Detection: A Concise Review and a New Dataset
Our review identifies practical issues, including the absence of comprehensive datasets with diverse scenarios.
Taylor Videos for Action Recognition
Effectively extracting motions from video is a critical and long-standing problem for action recognition.
Optimizing Camera Configurations for Multi-View Pedestrian Detection
Jointly considering multiple camera views (multi-view) is very effective for pedestrian detection under occlusion.
AV-Deepfake1M: A Large-Scale LLM-Driven Audio-Visual Deepfake Dataset
The comprehensive benchmark of the proposed dataset utilizing state-of-the-art deepfake detection and localization methods indicates a significant drop in performance compared to previous datasets.
Empathy Detection from Text, Audiovisual, Audio or Physiological Signals: A Systematic Review of Task Formulations and Machine Learning Methods
Empathy indicates an individual's ability to understand others.
Adaptive Multi-head Contrastive Learning
In contrastive learning, two views of an original image, generated by different augmentations, are considered a positive pair, and their similarity is required to be high.
Training with Product Digital Twins for AutoRetail Checkout
Because the digital twins individually mimic user bias, the resulting DT training set better reflects the characteristics of the target scenario and allows us to train more effective product detection and tracking models.
Pavlok-Nudge: A Feedback Mechanism for Atomic Behaviour Modification with Snoring Usecase
This paper proposes a feedback mechanism to change behavioural patterns using the Pavlok device.
Glitch in the Matrix: A Large Scale Benchmark for Content Driven Audio-Visual Forgery Detection and Localization
The proposed baseline method, Boundary Aware Temporal Forgery Detection (BA-TFD), is a 3D Convolutional Neural Network-based architecture which effectively captures multimodal manipulations.
Ranked #1 on
Temporal Forgery Localization
on ForgeryNet
Large-scale Training Data Search for Object Re-identification
We consider a scenario where we have access to the target domain, but cannot afford on-the-fly training data annotation, and instead would like to construct an alternative training set from a large-scale data pool such that a competitive model can be obtained.
A Bag-of-Prototypes Representation for Dataset-Level Applications
The former measures how suitable a training set is for a target domain, while the latter studies how challenging a test set is for a learned model.
AMF: Adaptable Weighting Fusion with Multiple Fine-tuning for Image Classification
Fine-tuning is widely applied in image classification tasks as a transfer learning approach.
Strengthening Skeletal Action Recognizers via Leveraging Temporal Patterns
Skeleton sequences are compact and lightweight.
Deep transfer learning for image classification: a survey
We show that under this new taxonomy, many of the applications where transfer learning has been shown to be ineffective or even hinder performance are to be expected when taking into account the source and target datasets and the techniques used.
ANUBIS: Skeleton Action Recognition Dataset, Review, and Benchmark
To this end, we present a review in the form of a taxonomy on existing works of skeleton-based action recognition.
Attribute Descent: Simulating Object-Centric Datasets on the Content Level and Beyond
This article aims to use graphic engines to simulate a large number of training data that have free annotations and possibly strongly resemble to real-world data.
How to Synthesize a Large-Scale and Trainable Micro-Expression Dataset?
To this end, we develop a protocol to automatically synthesize large scale MiE training data that allow us to train improved recognition models for real-world test data.
Resolving Anomalies in the Behaviour of a Modularity Inducing Problem Domain with Distributional Fitness Evaluation
This dynamicity is imposed on top of an already complex fitness landscape.
Feature Selection on Thermal-stress Dataset
These findings are likely to improve the accuracy of current stress recognition systems.
Exploring Biases and Prejudice of Facial Synthesis via Semantic Latent Space
Varying the proportions of male and female faces in the training data can have a substantial effect on behavior on the test data: we found that the seemingly obvious choice of 50:50 proportions was not the best for this dataset to reduce biased behavior on female faces, which was 71% unbiased as compared to our top unbiased rate of 84%.
Non-binary deep transfer learning for image classification
A model is either pre-trained or not pre-trained.
Ranked #2 on
Image Classification
on Caltech-256
(using extra training data)
Neural Network Classifier as Mutual Information Evaluator
We give a new view of neural network classifiers with softmax and cross-entropy as mutual information evaluators.
Position-Sensing Graph Neural Networks: Proactively Learning Nodes Relative Positions
Such GNNs are incapable of learning relative positions between graph nodes within a graph.
Disentangling Noise from Images: A Flow-Based Image Denoising Neural Network
The prevalent convolutional neural network (CNN) based image denoising methods extract features of images to restore the clean ground truth, achieving high denoising accuracy.
Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition
Recent skeleton-based action recognition methods extract features from 3D joint coordinates as spatial-temporal cues, using these representations in a graph neural network for feature fusion to boost recognition performance.
Ranked #27 on
Skeleton Based Action Recognition
on NTU RGB+D 120
Invertible Denoising Network: A Light Solution for Real Noise Removal
InvDN transforms the noisy input into a low-resolution clean image and a latent representation containing noise.
S2FGAN: Semantically Aware Interactive Sketch-to-Face Translation
Instead of constraining the translation process by using a reference image, the users can command the model to retouch the generated images by involving the semantic information in the generation process.
Disguising Personal Identity Information in EEG Signals
The personal identity information in original EEGs are transformed into disguised ones with a CycleGANbased EEG disguising model.
Analogical and Relational Reasoning with Spiking Neural Networks
To illustrate this, we first investigate the performance of our networks with supervised learning, then with unsupervised learning.
RealSmileNet: A Deep End-To-End Network for Spontaneous and Posed Smile Recognition
Smiles play a vital role in the understanding of social interactions within different communities, and reveal the physical state of mind of people in both real and deceptive ways.
A Token-wise CNN-based Method for Sentence Compression
Sentence compression is a Natural Language Processing (NLP) task aimed at shortening original sentences and preserving their key information.
Pairwise-GAN: Pose-based View Synthesis through Pair-Wise Training
This inspired our research which explores the performance of two models from pixel transformation in frontal facial synthesis, Pix2Pix and CycleGAN.
Are Deep Neural Architectures Losing Information? Invertibility Is Indispensable
Identifying the information lossless condition for deep neural architectures is important, because tasks such as image restoration require keep the detailed information of the input data as much as possible.
A Genetic Feature Selection Based Two-stream Neural Network for Anger Veracity Recognition
For example, acted anger can be expressed when stimuli is not genuinely angry with an aim to manipulate the observer.
Simulating Content Consistent Vehicle Datasets with Attribute Descent
Between synthetic and real data, there is a two-level domain gap, i. e., content level and appearance level.
Rethinking Softmax with Cross-Entropy: Neural Network Classifier as Mutual Information Estimator
We show that optimising the parameters of classification neural networks with softmax cross-entropy is equivalent to maximising the mutual information between inputs and labels under the balanced data assumption.
Predicting Group Cohesiveness in Images
We study the factors that influence the perception of group-level cohesion and propose methods for estimating the human-perceived cohesion on the group cohesiveness scale.
Your Eyes Say You're Lying: An Eye Movement Pattern Analysis for Face Familiarity and Deceptive Cognition
Eye movement patterns reflect human latent internal cognitive activities.
Human-Computer Interaction
EmotiW 2018: Audio-Video, Student Engagement and Group-Level Affect Prediction
This paper details the sixth Emotion Recognition in the Wild (EmotiW) challenge.
Why don't the modules dominate - Investigating the Structure of a Well-Known Modularity-Inducing Problem Domain
Wagner's modularity inducing problem domain is a key contribution to the study of the evolution of modularity, including both evolutionary theory and evolutionary computation.
EPUTION at SemEval-2018 Task 2: Emoji Prediction with User Adaption
This paper describes our approach, called EPUTION, for the open trial of the SemEval- 2018 Task 2, Multilingual Emoji Prediction.
