Search Results for author: Vuong Le

Found 21 papers, 7 papers with code

Persistent-Transient Duality: A Multi-mechanism Approach for Modeling Human-Object Interaction

no code implementations ICCV 2023 Hung Tran, Vuong Le, Svetha Venkatesh, Truyen Tran

To bridge that gap, this work proposes to model two concurrent mechanisms that jointly control human motion: the Persistent process that runs continually on the global scale, and the Transient sub-processes that operate intermittently on the local context of the human while interacting with objects.

Graph Attention Human-Object Interaction Detection +1

Video Dialog as Conversation about Objects Living in Space-Time

1 code implementation8 Jul 2022 Hoang-Anh Pham, Thao Minh Le, Vuong Le, Tu Minh Phuong, Truyen Tran

To tackle these challenges we present a new object-centric framework for video dialog that supports neural reasoning dubbed COST - which stands for Conversation about Objects in Space-Time.

Object Relational Reasoning +3

Guiding Visual Question Answering with Attention Priors

no code implementations25 May 2022 Thao Minh Le, Vuong Le, Sunil Gupta, Svetha Venkatesh, Truyen Tran

This grounding guides the attention mechanism inside VQA models through a duality of mechanisms: pre-training attention weight calculation and directly guiding the weights at inference time on a case-by-case basis.

Question Answering Visual Grounding +2

Persistent-Transient Duality in Human Behavior Modeling

no code implementations21 Apr 2022 Hung Tran, Vuong Le, Svetha Venkatesh, Truyen Tran

We propose to model the persistent-transient duality in human behavior using a parent-child multi-channel neural network, which features a parent persistent channel that manages the global dynamics and children transient channels that are initiated and terminated on-demand to handle detailed interactive actions.

Human-Object Interaction Detection motion prediction

Neural Latent Traversal with Semantic Constraints

no code implementations29 Sep 2021 Majid Abdolshah, Hung Le, Thommen Karimpanal George, Vuong Le, Sunil Gupta, Santu Rana, Svetha Venkatesh

Whilst Generative Adversarial Networks (GANs) generate visually appealing high resolution images, the latent representations (or codes) of these models do not allow controllable changes on the semantic attributes of the generated images.

Hierarchical Object-oriented Spatio-Temporal Reasoning for Video Question Answering

no code implementations25 Jun 2021 Long Hoang Dang, Thao Minh Le, Vuong Le, Truyen Tran

Toward reaching this goal we propose an object-oriented reasoning approach in that video is abstracted as a dynamic stream of interacting objects.

Object Question Answering +1

A Spatio-temporal Attention-based Model for Infant Movement Assessment from Videos

1 code implementation20 May 2021 Binh Nguyen-Thai, Vuong Le, Catherine Morgan, Nadia Badawi, Truyen Tran, Svetha Venkatesh

The absence or abnormality of fidgety movements of joints or limbs is strongly indicative of cerebral palsy in infants.

Video Classification

Object-Centric Representation Learning for Video Question Answering

no code implementations12 Apr 2021 Long Hoang Dang, Thao Minh Le, Vuong Le, Truyen Tran

Video question answering (Video QA) presents a powerful testbed for human-like intelligent behaviors.

Object Question Answering +3

Learning Asynchronous and Sparse Human-Object Interaction in Videos

no code implementations CVPR 2021 Romero Morais, Vuong Le, Svetha Venkatesh, Truyen Tran

Their interactions are sparse in time hence more faithful to the true underlying nature and more robust in inference and learning.

Human-Object Interaction Detection Object

The Three Ghosts of Medical AI: Can the Black-Box Present Deliver?

no code implementations10 Dec 2020 Thomas P. Quinn, Stephan Jacobs, Manisha Senadeera, Vuong Le, Simon Coghlan

Our title alludes to the three Christmas ghosts encountered by Ebenezer Scrooge in \textit{A Christmas Carol}, who guide Ebenezer through the past, present, and future of Christmas holiday events.

Goal-driven Long-Term Trajectory Prediction

no code implementations5 Nov 2020 Hung Tran, Vuong Le, Truyen Tran

We design Goal-driven Trajectory Prediction model - a dual-channel neural network that realizes such intuition.

Trajectory Prediction

Learning to Abstract and Predict Human Actions

1 code implementation20 Aug 2020 Romero Morais, Vuong Le, Truyen Tran, Svetha Venkatesh

We propose Hierarchical Encoder-Refresher-Anticipator, a multi-level neural machine that can learn the structure of human activities by observing a partial hierarchy of events and roll-out such structure into a future prediction in multiple levels of abstraction.

Activity Prediction Future prediction

Trust and Medical AI: The challenges we face and the expertise needed to overcome them

no code implementations18 Aug 2020 Thomas P. Quinn, Manisha Senadeera, Stephan Jacobs, Simon Coghlan, Vuong Le

These consequences could erode public trust in AI, which could in turn undermine trust in our healthcare institutions.

Scalable Backdoor Detection in Neural Networks

no code implementations10 Jun 2020 Haripriya Harikumar, Vuong Le, Santu Rana, Sourangshu Bhattacharya, Sunil Gupta, Svetha Venkatesh

Recently, it has been shown that deep learning models are vulnerable to Trojan attacks, where an attacker can install a backdoor during training time to make the resultant model misidentify samples contaminated with a small trigger patch.

Dynamic Language Binding in Relational Visual Reasoning

1 code implementation30 Apr 2020 Thao Minh Le, Vuong Le, Svetha Venkatesh, Truyen Tran

We present Language-binding Object Graph Network, the first neural reasoning method with dynamic relational structures across both visual and textual domains with applications in visual question answering.

Object Question Answering +2

Hierarchical Conditional Relation Networks for Video Question Answering

1 code implementation CVPR 2020 Thao Minh Le, Vuong Le, Svetha Venkatesh, Truyen Tran

Video question answering (VideoQA) is challenging as it requires modeling capacity to distill dynamic visual artifacts and distant relations and to associate them with linguistic concepts.

Audio-Visual Question Answering (AVQA) Question Answering +4

Neural Reasoning, Fast and Slow, for Video Question Answering

no code implementations10 Jul 2019 Thao Minh Le, Vuong Le, Svetha Venkatesh, Truyen Tran

While recent advances in lingual and visual question answering have enabled sophisticated representations and neural reasoning mechanisms, major challenges in Video QA remain on dynamic grounding of concepts, relations and actions to support the reasoning process.

Natural Questions Question Answering +2

Cannot find the paper you are looking for? You can Submit a new open access paper.