Search Results for author:
Found 39 papers, 16 papers with code
Open-Vocabulary Affordance Detection in 3D Point Clouds
Affordance detection is a challenging problem with a wide variety of robotic applications.
DRG-Net: Interactive Joint Learning of Multi-lesion Segmentation and Classification for Diabetic Retinopathy Grading
Diabetic Retinopathy (DR) is a leading cause of vision loss in the world, and early DR detection is necessary to prevent vision loss and support an appropriate treatment.
Contextual Explainable Video Representation: Human Perception-based Understanding
We choose video paragraph captioning and temporal action detection to illustrate the effectiveness of human perception based-contextual representation in video understanding.
CLIP-TSA: CLIP-Assisted Temporal Self-Attention for Weakly-Supervised Video Anomaly Detection
Video anomaly detection (VAD) -- commonly formulated as a multiple-instance learning problem in a weakly-supervised manner due to its labor-intensive nature -- is a challenging problem in video surveillance where the frames of anomaly need to be localized in an untrimmed video.
VLTinT: Visual-Linguistic Transformer-in-Transformer for Coherent Video Paragraph Captioning
Video paragraph captioning aims to generate a multi-sentence description of an untrimmed video with several temporal event locations in coherent storytelling.
Ranked #2 on
Video Captioning
on ActivityNet Captions
Multi-Camera Multi-Object Tracking on the Move via Single-Stage Global Association Approach
The development of autonomous vehicles generates a tremendous demand for a low-cost solution with a complete set of camera sensors capturing the environment around the car.
AISFormer: Amodal Instance Segmentation with Transformer
AISFormer explicitly models the complex coherence between occluder, visible, amodal, and invisible masks within an object's regions of interest by treating them as learnable queries.
EmbryosFormer: Deformable Transformer and Collaborative Encoding-Decoding for Embryos Stage Development Classification
The transformer expanding path models the temporal coherency between embryo images to ensure monotonic non-decreasing constraint and is optimized by a segmentation head.
AOE-Net: Entities Interactions Modeling with Adaptive Attention Mechanism for Temporal Action Proposals Generation
PMR module represents each video snippet by a visual-linguistic feature, in which main actors and surrounding environment are represented by visual information, whereas relevant objects are depicted by linguistic features through an image-text model.
Multimodality Multi-Lead ECG Arrhythmia Classification using Self-Supervised Learning
Electrocardiogram (ECG) signal is one of the most effective sources of information mainly employed for the diagnosis and prediction of cardiovascular diseases (CVDs) connected with the abnormalities in heart rhythm.
Vec2Face-v2: Unveil Human Faces from their Blackbox Features via Attention-based Network in Face Recognition
We therefore introduce a new method named Attention-based Bijective Generative Adversarial Networks in a Distillation framework (DAB-GAN) to synthesize faces of a subject given his/her extracted face recognition features.
VLCap: Vision-Language with Contrastive Learning for Coherent Video Paragraph Captioning
In this paper, we leverage the human perceiving process, that involves vision and language interaction, to generate a coherent paragraph description of untrimmed videos.
Ranked #3 on
Video Captioning
on ActivityNet Captions
Self-supervised Domain Adaptation in Crowd Counting
Self-training crowd counting has not been attentively explored though it is one of the important challenges in computer vision.
OTAdapt: Optimal Transport-based Approach For Unsupervised Domain Adaptation
Unsupervised domain adaptation is one of the challenging problems in computer vision.
Multi-Camera Multiple 3D Object Tracking on the Move for Autonomous Vehicles
The experimental results on the nuScenes dataset demonstrate the benefits of the proposed method to produce SOTA performance on the existing vision-based tracking dataset.
CapsNet for Medical Image Segmentation
We then provide recent developments of CapsNet for the task of medical image segmentation.
ABN: Agent-Aware Boundary Networks for Temporal Action Proposal Generation
Temporal action proposal generation (TAPG) aims to estimate temporal intervals of actions in untrimmed videos, which is a challenging yet plays an important role in many tasks of video analysis and understanding.
Point-Unet: A Context-aware Point-based Neural Network for Volumetric Segmentation
In this paper, we propose Point-Unet, a novel method that incorporates the efficiency of deep learning with 3D point clouds into volumetric segmentation.
3D-UCaps: 3D Capsules Unet for Volumetric Image Segmentation
Medical image segmentation has been so far achieving promising results with Convolutional Neural Networks (CNNs).
Meta-Learning of NAS for Few-shot Learning in Medical Image Applications
To address such limitations, meta-learning has been adopted in the scenarios of few-shot learning and multiple tasks.
SS-3DCapsNet: Self-supervised 3D Capsule Networks for Medical Segmentation on Less Labeled Data
Capsule network is a recent new deep network architecture that has been applied successfully for medical image segmentation tasks.
AEI: Actors-Environment Interaction with Adaptive Attention for Temporal Action Proposals Generation
In this paper, we make an attempt to simulate that ability of a human by proposing Actor Environment Interaction (AEI) network to improve the video representation for temporal action proposals generation.
Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey
In this work, we provide a detailed review of recent and state-of-the-art research advances of deep reinforcement learning in computer vision.
BiMaL: Bijective Maximum Likelihood Approach to Domain Adaptation in Semantic Scene Segmentation
Semantic segmentation aims to predict pixel-level labels.
The Right to Talk: An Audio-Visual Transformer Approach
Therefore, this work introduces a new Audio-Visual Transformer approach to the problem of localization and highlighting the main speaker in both audio and visual channels of a multi-speaker conversation video in the wild.
Multi-module Recurrent Convolutional Neural Network with Transformer Encoder for ECG Arrhythmia Classification
The automatic classification of electrocardiogram (ECG) signals has played an important role in cardiovascular diseases diagnosis and prediction.
Agent-Environment Network for Temporal Action Proposal Generation
Temporal action proposal generation is an essential and challenging task that aims at localizing temporal intervals containing human actions in untrimmed videos.
Offset Curves Loss for Imbalanced Problem in Medical Segmentation
Our proposed Offset Curves (OsC) loss consists of three main fitting terms.
Flow-based Deformation Guidance for Unpaired Multi-Contrast MRI Image-to-Image Translation
To capture temporal structures in the medical images, we explore the displacement between the consecutive slices using a deformation field.
A Multi-task Contextual Atrous Residual Network for Brain Tumor Detection & Segmentation
The first objective is performed by our proposed contextual brain tumor detection network, which plays a role of an attention gate and focuses on the region around brain tumor only while ignoring the far neighbor background which is less correlated to the tumor.
LIAAD: Lightweight Attentive Angular Distillation for Large-scale Age-Invariant Face Recognition
This work presents a novel Lightweight Attentive Angular Distillation (LIAAD) approach to Large-scale Lightweight AiFR that overcomes these limitations.
Domain Generalization via Universal Non-volume Preserving Models
However, it has been largely overlooked in the problem of recognition in new unseen domains.
Image Alignment in Unseen Domains via Domain Deep Generalization
This paper presents a novel deep learning based approach to tackle the problem of across unseen modalities.
ShrinkTeaNet: Million-scale Lightweight Face Recognition via Shrinking Teacher-Student Networks
In addition, this work introduces a novel Angular Distillation Loss for distilling the feature direction and the sample distributions of the teacher's hypersphere to its student.
Fast Flow Reconstruction via Robust Invertible nxn Convolution
The experiments on CIFAR-10, ImageNet and Celeb-HQ datasets, have shown that our invertible $n \times n$ convolution helps to improve the performance of generative models significantly.
Non-Volume Preserving-based Fusion to Group-Level Emotion Recognition on Crowd Videos
To demonstrate the robustness and effectiveness of each component in the proposed approach, three experiments were conducted: (i) evaluation on AffectNet database to benchmark the proposed EmoNet for recognizing facial expression; (ii) evaluation on EmotiW2018 to benchmark the proposed deep feature level fusion mechanism NVPF; and, (iii) examine the proposed TNVPF on an innovative Group-level Emotion on Crowd Videos (GECV) dataset composed of 627 videos collected from publicly available sources.
MobiFace: A Lightweight Deep Learning Face Recognition on Mobile Devices
Deep neural networks have been widely used in numerous computer vision applications, particularly in face recognition.
Automatic Face Aging in Videos via Deep Reinforcement Learning
This paper presents a novel approach to synthesize automatically age-progressed facial images in video sequences using Deep Reinforcement Learning.
Reformulating Level Sets as Deep Recurrent Neural Network Approach to Semantic Segmentation
To address these issues and boost the classic variational LS methods to a new level of the learnable deep learning approaches, we propose a novel definition of contour evolution named Recurrent Level Set (RLS)} to employ Gated Recurrent Unit under the energy minimization of a variational LS functional.
