26 citations · 170 across the 41 of their papers we have counts for
34 papers · 1 filter
AerialFormer: Multi-resolution Transformer for Aerial Image Segmentation
Kashu Yamazaki, Taisei Hanyu, Minh Tran +7
Aerial Image Segmentation is a top-down perspective semantic segmentation and has several challenging characteristics such as strong imbalance in the foreground-background distribu…
Z-GMOT: Zero-shot Generic Multiple Object Tracking
Kim Hoang Tran, Anh Duy Le Dinh, Tien Phat Nguyen +6
Despite recent significant progress, Multi-Object Tracking (MOT) faces limitations such as reliance on prior knowledge and predefined categories and struggles with unseen objects.…
FREDOM: Fairness Domain Adaptation Approach to Semantic Scene Understanding
Thanh-Dat Truong, Ngan Le, Bhiksha Raj +2
Although Domain Adaptation in Semantic Scene Segmentation has shown impressive improvement in recent years, the fairness concerns in the domain adaptation have yet to be well defin…
DRG-Net: Interactive Joint Learning of Multi-lesion Segmentation and Classification for Diabetic Retinopathy Grading
Hasan Md Tusfiqur, Duy M. H. Nguyen, Mai T. N. Truong +8
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. In this w…
Contextual Explainable Video Representation: Human Perception-based Understanding
Khoa Vo, Kashu Yamazaki, Phong X. Nguyen +3
Video understanding is a growing field and a subject of intense research, which includes many interesting tasks to understanding both spatial and temporal information, e.g., action…
CLIP-TSA: CLIP-Assisted Temporal Self-Attention for Weakly-Supervised Video Anomaly Detection
Hyekang Kevin Joo, Khoa Vo, Kashu Yamazaki +1
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 pro…
Multi-Camera Multi-Object Tracking on the Move via Single-Stage Global Association Approach
Pha Nguyen, Kha Gia Quach, Chi Nhan Duong +3
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. It is e…
VLTinT: Visual-Linguistic Transformer-in-Transformer for Coherent Video Paragraph Captioning
Kashu Yamazaki, Khoa Vo, Sang Truong +2
Video paragraph captioning aims to generate a multi-sentence description of an untrimmed video with several temporal event locations in coherent storytelling. Following the human p…
EmbryosFormer: Deformable Transformer and Collaborative Encoding-Decoding for Embryos Stage Development Classification
Tien-Phat Nguyen, Trong-Thang Pham, Tri Nguyen +7
The timing of cell divisions in early embryos during the In-Vitro Fertilization (IVF) process is a key predictor of embryo viability. However, observing cell divisions in Time-Laps…
AOE-Net: Entities Interactions Modeling with Adaptive Attention Mechanism for Temporal Action Proposals Generation
Khoa Vo, Sang Truong, Kashu Yamazaki +3
Temporal action proposal generation (TAPG) is a challenging task, which requires localizing action intervals in an untrimmed video. Intuitively, we as humans, perceive an action th…
AISFormer: Amodal Instance Segmentation with Transformer
Minh Tran, Khoa Vo, Kashu Yamazaki +3
Amodal Instance Segmentation (AIS) aims to segment the region of both visible and possible occluded parts of an object instance. While Mask R-CNN-based AIS approaches have shown pr…
Vec2Face-v2: Unveil Human Faces from their Blackbox Features via Attention-based Network in Face Recognition
Thanh-Dat Truong, Chi Nhan Duong, Ngan Le +2
In this work, we investigate the problem of face reconstruction given a facial feature representation extracted from a blackbox face recognition engine. Indeed, it is a very challe…
Self-supervised Domain Adaptation in Crowd Counting
Pha Nguyen, Thanh-Dat Truong, Miaoqing Huang +3
Self-training crowd counting has not been attentively explored though it is one of the important challenges in computer vision. In practice, the fully supervised methods usually re…
3DConvCaps: 3DUnet with Convolutional Capsule Encoder for Medical Image Segmentation
Minh Tran, Viet-Khoa Vo-Ho, Ngan T. H. Le
Convolutional Neural Networks (CNNs) have achieved promising results in medical image segmentation. However, CNNs require lots of training data and are incapable of handling pose a…
VLCap: Vision-Language with Contrastive Learning for Coherent Video Paragraph Captioning
Kashu Yamazaki, Sang Truong, Khoa Vo +4
In this paper, we leverage the human perceiving process, that involves vision and language interaction, to generate a coherent paragraph description of untrimmed videos. We propose…
OTAdapt: Optimal Transport-based Approach For Unsupervised Domain Adaptation
Thanh-Dat Truong, Naga Venkata Sai Raviteja Chappa, Xuan Bac Nguyen +3
Unsupervised domain adaptation is one of the challenging problems in computer vision. This paper presents a novel approach to unsupervised domain adaptations based on the optimal t…
Multi-Camera Multiple 3D Object Tracking on the Move for Autonomous Vehicles
Pha Nguyen, Kha Gia Quach, Chi Nhan Duong +3
The development of autonomous vehicles provides an opportunity to have a complete set of camera sensors capturing the environment around the car. Thus, it is important for object d…
ABN: Agent-Aware Boundary Networks for Temporal Action Proposal Generation
Khoa Vo, Kashu Yamazaki, Sang Truong +3
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 v…
Point-Unet: A Context-aware Point-based Neural Network for Volumetric Segmentation
Ngoc-Vuong Ho, Tan Nguyen, Gia-Han Diep +2
Medical image analysis using deep learning has recently been prevalent, showing great performance for various downstream tasks including medical image segmentation and its sibling,…
AEI: Actors-Environment Interaction with Adaptive Attention for Temporal Action Proposals Generation
Khoa Vo, Hyekang Joo, Kashu Yamazaki +4
Humans typically perceive the establishment of an action in a video through the interaction between an actor and the surrounding environment. An action only starts when the main ac…
Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey
Ngan Le, Vidhiwar Singh Rathour, Kashu Yamazaki +2
Deep reinforcement learning augments the reinforcement learning framework and utilizes the powerful representation of deep neural networks. Recent works have demonstrated the remar…
BiMaL: Bijective Maximum Likelihood Approach to Domain Adaptation in Semantic Scene Segmentation
Thanh-Dat Truong, Chi Nhan Duong, Ngan Le +3
Semantic segmentation aims to predict pixel-level labels. It has become a popular task in various computer vision applications. While fully supervised segmentation methods have ach…
The Right to Talk: An Audio-Visual Transformer Approach
Thanh-Dat Truong, Chi Nhan Duong, The De Vu +4
Turn-taking has played an essential role in structuring the regulation of a conversation. The task of identifying the main speaker (who is properly taking his/her turn of speaking)…
Agent-Environment Network for Temporal Action Proposal Generation
Viet-Khoa Vo-Ho, Ngan Le, Kashu Yamazaki +2
Temporal action proposal generation is an essential and challenging task that aims at localizing temporal intervals containing human actions in untrimmed videos. Most of existing a…