Search Results for author:
Found 33 papers, 14 papers with code
DiffFake: Exposing Deepfakes using Differential Anomaly Detection
Traditional deepfake detectors have dealt with the detection problem as a binary classification task.
From Age Estimation to Age-Invariant Face Recognition: Generalized Age Feature Extraction Using Order-Enhanced Contrastive Learning
Generalized age feature extraction is crucial for age-related facial analysis tasks, such as age estimation and age-invariant face recognition (AIFR).
Interact with me: Joint Egocentric Forecasting of Intent to Interact, Attitude and Social Actions
For efficient human-agent interaction, an agent should proactively recognize their target user and prepare for upcoming interactions.
Enhanced Prototypical Part Network (EPPNet) For Explainable Image Classification Via Prototypes
We also introduce a faithfulness score to evaluate the explainability of the results based on the discovered prototypes.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
+1
LLplace: The 3D Indoor Scene Layout Generation and Editing via Large Language Model
In this paper, we introduce LLplace, a novel 3D indoor scene layout designer based on lightweight fine-tuned open-source LLM Llama3.
Beyond Isolated Frames: Enhancing Sensor-Based Human Activity Recognition through Intra- and Inter-Frame Attention
Human Activity Recognition (HAR) has become increasingly popular with ubiquitous computing, driven by the popularity of wearable sensors in fields like healthcare and sports.
WorkBench: a Benchmark Dataset for Agents in a Realistic Workplace Setting
We evaluate five existing ReAct agents on WorkBench, finding they successfully complete as few as 3% of tasks (Llama2-70B), and just 43% for the best-performing (GPT-4).
CLIP-EBC: CLIP Can Count Accurately through Enhanced Blockwise Classification
Within our backbone-agnostic EBC framework, we then introduce CLIP-EBC to fully leverage CLIP's recognition capabilities for this task.
Ranked #1 on
Crowd Counting
on NWPU-Crowd (Val)
Detecting Face Synthesis Using a Concealed Fusion Model
In this paper, we propose a fusion-based strategy to detect face image synthesis while providing resiliency to several attacks.
Data-Agnostic Face Image Synthesis Detection Using Bayesian CNNs
Face image synthesis detection is considerably gaining attention because of the potential negative impact on society that this type of synthetic data brings.
Cross-Age Contrastive Learning for Age-Invariant Face Recognition
Cross-age facial images are typically challenging and expensive to collect, making noise-free age-oriented datasets relatively small compared to widely-used large-scale facial datasets.
Robust Multiview Multimodal Driver Monitoring System Using Masked Multi-Head Self-Attention
Driver Monitoring Systems (DMSs) are crucial for safe hand-over actions in Level-2+ self-driving vehicles.
Real-Time Driver Monitoring Systems through Modality and View Analysis
Driver distractions are known to be the dominant cause of road accidents.
Look at Adjacent Frames: Video Anomaly Detection without Offline Training
Based on the information shifts between adjacent frames, an incremental learner is used to update parameters of the multilayer perceptron after observing each frame, thus allowing to detect anomalous events along the video stream.
Visually-aware Acoustic Event Detection using Heterogeneous Graphs
In contrast, we employ heterogeneous graphs to explicitly capture the spatial and temporal relationships between the modalities and represent detailed information about the underlying signal.
Video Anomaly Detection via Prediction Network with Enhanced Spatio-Temporal Memory Exchange
Video anomaly detection is a challenging task because most anomalies are scarce and non-deterministic.
FusionCount: Efficient Crowd Counting via Multiscale Feature Fusion
Then, to account for perspective distortion, the highest-level feature map is fed to extra components to extract multiscale features, which are the input to the decoder to generate crowd densities.
Ranked #11 on
Crowd Counting
on ShanghaiTech B
Spectral-PQ: A Novel Spectral Sensitivity-Orientated Perceptual Compression Technique for RGB 4:4:4 Video Data
With application for RGB 4:4:4 video data, Spectral-PQ exploits HVS spectral sensitivity-related color masking in addition to spatial masking and temporal masking; the proposed method operates at the Coding Block (CB) level and the Prediction Unit (PU) level in the HEVC standard.
Improving Face-Based Age Estimation with Attention-Based Dynamic Patch Fusion
Since the proposed RMHHA mechanism ranks the discovered patches based on their importance, the length of the learning path of each patch in the FusionNet is proportional to the amount of information it carries (the longer, the more important).
Joint Learning Architecture for Multiple Object Tracking and Trajectory Forecasting
We propose to jointly train a tracking and trajectory forecasting model and use the predicted trajectory forecasts for short-term motion estimates in lieu of linear motion prediction methods such as the Kalman filter.
Multi-Camera Trajectory Forecasting with Trajectory Tensors
We introduce the problem of multi-camera trajectory forecasting (MCTF), which involves predicting the trajectory of a moving object across a network of cameras.
On the detection-to-track association for online multi-object tracking
Driven by recent advances in object detection with deep neural networks, the tracking-by-detection paradigm has gained increasing prevalence in the research community of multi-object tracking (MOT).
Deep Learning for Predictive Analytics in Reversible Steganography
Given that reversibility is governed independently by the coding module, we narrow our focus to the incorporation of neural networks into the analytics module, which serves the purpose of predicting pixel intensities and a pivotal role in determining capacity and imperceptibility.
Video Anomaly Detection by Estimating Likelihood of Representations
Video anomaly detection is a challenging task not only because it involves solving many sub-tasks such as motion representation, object localization and action recognition, but also because it is commonly considered as an unsupervised learning problem that involves detecting outliers.
Age-Oriented Face Synthesis with Conditional Discriminator Pool and Adversarial Triplet Loss
In this paper, we propose a method for the age-oriented face synthesis task that achieves a high synthesis accuracy with strong identity permanence capabilities.
Ensemble Network for Ranking Images Based on Visual Appeal
The ranking is expected to correspond with human perception of overall appeal of the images.
HVS-Based Perceptual Color Compression of Image Data
In the evaluations, we compare the proposed PCC technique with a set of reference methods including Versatile Video Coding (VVC) and High Efficiency Video Coding (HEVC) in addition to two other recently proposed algorithms.
Multi-Camera Trajectory Forecasting: Pedestrian Trajectory Prediction in a Network of Cameras
To facilitate research in this new area, we release the Warwick-NTU Multi-camera Forecasting Database (WNMF), a unique dataset of multi-camera pedestrian trajectories from a network of 15 synchronized cameras.
Multiple Object Forecasting: Predicting Future Object Locations in Diverse Environments
In contrast to existing works on object trajectory forecasting which primarily consider the problem from a birds-eye perspective, we formulate the problem from an object-level perspective and call for the prediction of full object bounding boxes, rather than trajectories alone.
Ranked #1 on
Multiple Object Forecasting
on Citywalks
Forecasting Pedestrian Trajectory with Machine-Annotated Training Data
In this work, we present a deep learning approach for pedestrian trajectory forecasting using a single vehicle-mounted camera.
Fusion Network for Face-based Age Estimation
Convolutional Neural Networks (CNN) have been applied to age-related research as the core framework.
The Predictive Context Tree: Predicting Contexts and Interactions
The Predictive Context Tree (PCT) is constructed as a hierarchical classifier, capable of predicting both the future locations that a user will visit and the contexts that a user will be immersed within.
Context Trees: Augmenting Geospatial Trajectories with Context
Summarising user contexts into a single data structure gives easy access to information that would otherwise remain latent, providing the basis for better understanding and predicting the actions and behaviours of individuals and groups.
