Search Results for author:
Found 33 papers, 11 papers with code
A Heterogeneous Multimodal Graph Learning Framework for Recognizing User Emotions in Social Networks
Our work highlights the significance of exploiting advanced deep learning techniques for less-explored problems in Affective Computing.
S2S2: Semantic Stacking for Robust Semantic Segmentation in Medical Imaging
Robustness and generalizability in medical image segmentation are often hindered by scarcity and limited diversity of training data, which stands in contrast to the variability encountered during inference.
Incorporating simulated spatial context information improves the effectiveness of contrastive learning models
The historical spatial context of the agent provides a similarity signal for self-supervised contrastive learning.
AI-SAM: Automatic and Interactive Segment Anything Model
Interactive approaches, exemplified by the Segment Anything Model (SAM), have shown promise as pre-trained models.
Unlocking the Emotional World of Visual Media: An Overview of the Science, Research, and Impact of Understanding Emotion
The emergence of artificial emotional intelligence technology is revolutionizing the fields of computers and robotics, allowing for a new level of communication and understanding of human behavior that was once thought impossible.
Learning Emotion Representations from Verbal and Nonverbal Communication
We present EmotionCLIP, the first pre-training paradigm to extract visual emotion representations from verbal and nonverbal communication using only uncurated data.
Ranked #2 on
Emotion Recognition in Context
on BoLD
Bodily expressed emotion understanding through integrating Laban movement analysis
Body movements carry important information about a person's emotions or mental state and are essential in daily communication.
Learning to Adapt to Online Streams with Distribution Shifts
Test-time adaptation (TTA) is a technique used to reduce distribution gaps between the training and testing sets by leveraging unlabeled test data during inference.
Asymmetry Disentanglement Network for Interpretable Acute Ischemic Stroke Infarct Segmentation in Non-Contrast CT Scans
In this paper, we propose a novel Asymmetry Disentanglement Network (ADN) to automatically separate pathological asymmetries and intrinsic anatomical asymmetries in NCCTs for more effective and interpretable AIS segmentation.
HICEM: A High-Coverage Emotion Model for Artificial Emotional Intelligence
Unlike theory of emotion, which has been the historical focus in psychology, emotion models are a descriptive tools.
Patcher: Patch Transformers with Mixture of Experts for Precise Medical Image Segmentation
We also propose a new mixture-of-experts (MoE) based decoder, which treats the feature maps from the encoder as experts and selects a suitable set of expert features to predict the label for each pixel.
Forget Less, Count Better: A Domain-Incremental Self-Distillation Learning Benchmark for Lifelong Crowd Counting
Crowd counting has important applications in public safety and pandemic control.
Surface Defect Detection and Evaluation for Marine Vessels using Multi-Stage Deep Learning
Detecting and evaluating surface coating defects is important for marine vessel maintenance.
A Machine Learning Paradigm for Studying Pictorial Realism: Are Constable's Clouds More Real than His Contemporaries?
The British landscape painter John Constable is considered foundational for the Realist movement in 19th-century European painting.
Using Navigational Information to Learn Visual Representations
Children learn to build a visual representation of the world from unsupervised exploration and we hypothesize that a key part of this learning ability is the use of self-generated navigational information as a similarity label to drive a learning objective for self-supervised learning.
Deep Rank-Consistent Pyramid Model for Enhanced Crowd Counting
Specifically, we propose a Deep Rank-consistEnt pyrAmid Model (DREAM), which makes full use of rank consistency across coarse-to-fine pyramid features in latent spaces for enhanced crowd counting with massive unlabeled images.
DeepStroke: An Efficient Stroke Screening Framework for Emergency Rooms with Multimodal Adversarial Deep Learning
In an emergency room (ER) setting, stroke triage or screening is a common challenge.
LambdaUNet: 2.5D Stroke Lesion Segmentation of Diffusion-weighted MR Images
Thus, it is not ideal to apply most existing segmentation methods as they are designed for either 2D or 3D images.
Pareto Efficient Fairness in Supervised Learning: From Extraction to Tracing
The proposed PEF notion is definition-agnostic, meaning that any well-defined notion of fairness can be reduced to the PEF notion.
Targeted Data-driven Regularization for Out-of-Distribution Generalization
The proposed framework, named targeted data-driven regularization (TDR), is model- and dataset-agnostic and employs a target dataset that resembles the desired nature of test data in order to guide the learning process in a coupled manner.
CAPTAIN: Comprehensive Composition Assistance for Photo Taking
A user study demonstrates that the work is useful to those taking photos.
PaDNet: Pan-Density Crowd Counting
We propose a novel framework, the Pan-Density Network (PaDNet), for pan-density crowd counting.
ARBEE: Towards Automated Recognition of Bodily Expression of Emotion In the Wild
A system to model the emotional expressions based on bodily movements, named ARBEE (Automated Recognition of Bodily Expression of Emotion), has also been developed and evaluated.
Facial Aging and Rejuvenation by Conditional Multi-Adversarial Autoencoder with Ordinal Regression
The latent vector preserves personalized face features and the age controls facial aging and rejuvenation.
Ranked #1 on
Age Estimation
on MORPH
Detecting Comma-shaped Clouds for Severe Weather Forecasting using Shape and Motion
Meteorologists use shapes and movements of clouds in satellite images as indicators of several major types of severe storms.
Rethinking the Smaller-Norm-Less-Informative Assumption in Channel Pruning of Convolution Layers
Model pruning has become a useful technique that improves the computational efficiency of deep learning, making it possible to deploy solutions in resource-limited scenarios.
Determining Gains Acquired from Word Embedding Quantitatively Using Discrete Distribution Clustering
The new clustering method is easy to use and consistently outperforms other methods on a variety of data sets.
Probabilistic Multigraph Modeling for Improving the Quality of Crowdsourced Affective Data
We proposed a probabilistic approach to joint modeling of participants' reliability and humans' regularity in crowdsourced affective studies.
Detecting Dominant Vanishing Points in Natural Scenes with Application to Composition-Sensitive Image Retrieval
To overcome this difficulty, we propose a novel vanishing point detection method that exploits global structures in the scene via contour detection.
Modeling Photographic Composition via Triangles
The capacity of automatically modeling photographic composition is valuable for many real-world machine vision applications such as digital photography, image retrieval, image understanding, and image aesthetics assessment.
Storm Detection by Visual Learning Using Satellite Images
In our system, we extract and summarize important visual storm evidence from satellite image sequences in the way that meteorologists interpret the images.
Deep Multi-Patch Aggregation Network for Image Style, Aesthetics, and Quality Estimation
We propose a deep multi-patch aggregation network training approach, which allows us to train models using multiple patches generated from one image.
Ranked #8 on
Aesthetics Quality Assessment
on AVA
Fast Discrete Distribution Clustering Using Wasserstein Barycenter with Sparse Support
In a variety of research areas, the weighted bag of vectors and the histogram are widely used descriptors for complex objects.
