Search Results for author:
Found 41 papers, 12 papers with code
Who Brings the Frisbee: Probing Hidden Hallucination Factors in Large Vision-Language Model via Causality Analysis
We hypothesize that hidden factors, such as objects, contexts, and semantic foreground-background structures, induce hallucination.
LLaVA-MR: Large Language-and-Vision Assistant for Video Moment Retrieval
However, long video processing and precise moment retrieval remain challenging due to LLMs' limited context size and coarse frame extraction.
UU-Mamba: Uncertainty-aware U-Mamba for Cardiovascular Segmentation
Building on the success of deep learning models in cardiovascular structure segmentation, increasing attention has been focused on improving generalization and robustness, particularly in small, annotated datasets.
Learning Multi-Manifold Embedding for Out-Of-Distribution Detection
Leveraging recent advances in representation learning and latent embeddings, Various scoring algorithms estimate distributions beyond the training data.
Learning with Instance-Dependent Noisy Labels by Anchor Hallucination and Hard Sample Label Correction
Traditional Noisy-Label Learning (NLL) methods categorize training data into clean and noisy sets based on the loss distribution of training samples.
UU-Mamba: Uncertainty-aware U-Mamba for Cardiac Image Segmentation
Biomedical image segmentation is critical for accurate identification and analysis of anatomical structures in medical imaging, particularly in cardiac MRI.
The 8th AI City Challenge
The eighth AI City Challenge highlighted the convergence of computer vision and artificial intelligence in areas like retail, warehouse settings, and Intelligent Traffic Systems (ITS), presenting significant research opportunities.
Addressing Long-Tail Noisy Label Learning Problems: a Two-Stage Solution with Label Refurbishment Considering Label Rarity
In the second stage, our label refurbishment method is applied to obtain soft labels for multi-expert ensemble learning, providing a principled solution to the long-tail noisy label problem.
A Comprehensive Review of Machine Learning Advances on Data Change: A Cross-Field Perspective
In this review, we regroup domain shift and concept drift into a single research problem, namely the data change problem, with a systematic overview of state-of-the-art methods in the two research fields.
Improving Limited Supervised Foot Ulcer Segmentation Using Cross-Domain Augmentation
Existing segmentation models relying on extensive annotations are impractical in real-world scenarios with limited annotated data.
Scale-Aware Crowd Count Network with Annotation Error Correction
Furthermore, the use of a fixed Gaussian kernel fails to account for the varying pixel distribution with respect to the camera distance.
A New Benchmark and Model for Challenging Image Manipulation Detection
Existing Image Manipulation Detection (IMD) methods are mainly based on detecting anomalous features arisen from image editing or double compression artifacts.
MixNet: Toward Accurate Detection of Challenging Scene Text in the Wild
Detecting small scene text instances in the wild is particularly challenging, where the influence of irregular positions and nonideal lighting often leads to detection errors.
Ranked #1 on
Scene Text Detection
on SCUT-CTW1500
FishEye8K: A Benchmark and Dataset for Fisheye Camera Object Detection
With the advance of AI, road object detection has been a prominent topic in computer vision, mostly using perspective cameras.
Ranked #1 on
2D Object Detection
on FishEye8K
The 7th AI City Challenge
The AI City Challenge's seventh edition emphasizes two domains at the intersection of computer vision and artificial intelligence - retail business and Intelligent Traffic Systems (ITS) - that have considerable untapped potential.
SMILEtrack: SiMIlarity LEarning for Occlusion-Aware Multiple Object Tracking
Second, we develop a Similarity Matching Cascade (SMC) module with a novel GATE function for robust object matching across consecutive video frames, further enhancing MOT performance.
Ranked #6 on
Multi-Object Tracking
on MOT20
(using extra training data)
Scale-Aware Crowd Counting Using a Joint Likelihood Density Map and Synthetic Fusion Pyramid Network
We then approximate the joint distribution of crowd density maps with the full covariance of multiple scales and derive a low-rank approximation for tractability and efficient implementation.
NAS-based Recursive Stage Partial Network (RSPNet) for Light-Weight Semantic Segmentation
The first architecture search determines the inner cell structure, and the second architecture search considers exponentially growing paths to finalize the outer structure of the network.
Mitigating Data Absence in Federated Learning Using Privacy-Controllable Data Digests
The absence of training data and their distribution changes in federated learning (FL) can significantly undermine model performance, especially in cross-silo scenarios.
Class-Specific Channel Attention for Few-Shot Learning
Few-Shot Learning (FSL) has attracted growing attention in computer vision due to its capability in model training without the need for excessive data.
Few-Shot Classification and Segmentation
Few-Shot Image Classification
+3
Open-Eye: An Open Platform to Study Human Performance on Identifying AI-Synthesized Faces
In this work, we develop an online platform called Open-eye to study the human performance of AI-synthesized face detection.
The 6th AI City Challenge
The four challenge tracks of the 2022 AI City Challenge received participation requests from 254 teams across 27 countries.
PseudoProp: Robust Pseudo-Label Generation for Semi-Supervised Object Detection in Autonomous Driving Systems
Semi-supervised object detection methods are widely used in autonomous driving systems, where only a fraction of objects are labeled.
GAN-generated Faces Detection: A Survey and New Perspectives
Generative Adversarial Networks (GAN) have led to the generation of very realistic face images, which have been used in fake social media accounts and other disinformation matters that can generate profound impacts.
VocBench: A Neural Vocoder Benchmark for Speech Synthesis
We perform a subjective and objective evaluation to compare the performance of each vocoder along a different axis.
Learnable Discrete Wavelet Pooling (LDW-Pooling) For Convolutional Networks
We introduce the Learning Discrete Wavelet Pooling (LDW-Pooling) that can be applied universally to replace standard pooling operations to better extract features with improved accuracy and efficiency.
Robust Attentive Deep Neural Network for Exposing GAN-generated Faces
However, images from existing public datasets do not represent real-world scenarios well enough in terms of view variations and data distributions (where real faces largely outnumber synthetic faces).
Eyes Tell All: Irregular Pupil Shapes Reveal GAN-generated Faces
Generative adversary network (GAN) generated high-realistic human faces have been used as profile images for fake social media accounts and are visually challenging to discern from real ones.
MS-DARTS: Mean-Shift Based Differentiable Architecture Search
Our approach can improve bot the stability and accuracy of DARTS, by smoothing the loss landscape and sampling architecture parameters within a suitable bandwidth.
Parallel Residual Bi-Fusion Feature Pyramid Network for Accurate Single-Shot Object Detection
Feature Pyramid (FP) is widely used in recent visual detection, however the top-down pathway of FP cannot preserve accurate localization due to pooling shifting.
Ranked #1 on
Object Detection
on UAVDT
MagGAN: High-Resolution Face Attribute Editing with Mask-Guided Generative Adversarial Network
We present Mask-guided Generative Adversarial Network (MagGAN) for high-resolution face attribute editing, in which semantic facial masks from a pre-trained face parser are used to guide the fine-grained image editing process.
Robust Adversarial Perturbation on Deep Proposal-based Models
Adversarial noises are useful tools to probe the weakness of deep learning based computer vision algorithms.
Exploring the Vulnerability of Single Shot Module in Object Detectors via Imperceptible Background Patches
In this paper, we focus on exploring the vulnerability of the Single Shot Module (SSM) commonly used in recent object detectors, by adding small perturbations to patches in the background outside the object.
Multi-Scale Supervised Network for Human Pose Estimation
Human pose estimation is an important topic in computer vision with many applications including gesture and activity recognition.
Who did What at Where and When: Simultaneous Multi-Person Tracking and Activity Recognition
We present a bootstrapping framework to simultaneously improve multi-person tracking and activity recognition at individual, interaction and social group activity levels.
In Ictu Oculi: Exposing AI Generated Fake Face Videos by Detecting Eye Blinking
The new developments in deep generative networks have significantly improve the quality and efficiency in generating realistically-looking fake face videos.
Multi-Scale Structure-Aware Network for Human Pose Estimation
We develop a robust multi-scale structure-aware neural network for human pose estimation.
Ranked #13 on
Pose Estimation
on MPII Human Pose
Adaptive RNN Tree for Large-Scale Human Action Recognition
The RNNs in RNN-T are co-trained with the action category hierarchy, which determines the structure of RNN-T.
Ranked #119 on
Skeleton Based Action Recognition
on NTU RGB+D
UA-DETRAC: A New Benchmark and Protocol for Multi-Object Detection and Tracking
In this work, we perform a comprehensive quantitative study on the effects of object detection accuracy to the overall MOT performance, using the new large-scale University at Albany DETection and tRACking (UA-DETRAC) benchmark dataset.
