Basura Fernando

research

∙ 05/04/2023

Modelling Spatio-Temporal Interactions for Compositional Action Recognition

Humans have the natural ability to recognize actions even if the objects...

0 Ramanathan Rajendiran, et al. ∙

research

∙ 11/26/2022

Who are you referring to? Weakly supervised coreference resolution with multimodal grounding

Coreference resolution aims at identifying words and phrases which refer...

0 Arushi Goel, et al. ∙

research

∙ 11/25/2022

Interaction Visual Transformer for Egocentric Action Anticipation

Human-object interaction is one of the most important visual cues that h...

0 Debaditya Roy, et al. ∙

research

∙ 10/24/2022

Abductive Action Inference

Abductive reasoning aims to make the most likely inference for a given s...

0 Clement Tan, et al. ∙

research

∙ 09/12/2022

Predicting the Next Action by Modeling the Abstract Goal

The problem of anticipating human actions is an inherently uncertain one...

0 Debaditya Roy, et al. ∙

research

∙ 08/23/2022

Consistency Regularization for Domain Adaptation

Collection of real world annotations for training semantic segmentation ...

0 Kian Boon Koh, et al. ∙

research

∙ 03/31/2022

3D Equivariant Graph Implicit Functions

In recent years, neural implicit representations have made remarkable pr...

6 Yunlu Chen, et al. ∙

research

∙ 12/19/2021

LocFormer: Enabling Transformers to Perform Temporal Moment Localization on Long Untrimmed Videos With a Feature Sampling Approach

We propose LocFormer, a Transformer-based model for video grounding whic...

0 Cristian Rodriguez Opazo, et al. ∙

research

∙ 11/26/2021

Not All Relations are Equal: Mining Informative Labels for Scene Graph Generation

Scene graph generation (SGG) aims to capture a wide variety of interacti...

0 Arushi Goel, et al. ∙

research

∙ 11/26/2021

TDAN: Top-Down Attention Networks for Enhanced Feature Selectivity in CNNs

Attention modules for Convolutional Neural Networks (CNNs) are an effect...

0 Shantanu Jaiswal, et al. ∙

research

∙ 07/19/2021

Action Forecasting with Feature-wise Self-Attention

We present a new architecture for human action forecasting from videos. ...

0 Yan Bin Ng, et al. ∙

research

∙ 05/26/2021

Anticipating human actions by correlating past with the future with Jaccard similarity measures

We propose a framework for early action recognition and anticipation by ...

0 Basura Fernando, et al. ∙

research

∙ 12/11/2020

A Log-likelihood Regularized KL Divergence for Video Prediction with A 3D Convolutional Variational Recurrent Network

The use of latent variable models has shown to be a powerful tool for mo...

0 Haziq Razali, et al. ∙

research

∙ 11/08/2020

FlowCaps: Optical Flow Estimation with Capsule Networks For Action Recognition

Capsule networks (CapsNets) have recently shown promise to excel in most...

0 Vinoj Jayasundara, et al. ∙

research

∙ 10/13/2020

DORi: Discovering Object Relationship for Moment Localization of a Natural-Language Query in Video

This paper studies the task of temporal moment localization in a long un...

0 Cristian Rodriguez Opazo, et al. ∙

research

∙ 04/28/2020

Inferring Temporal Compositions of Actions Using Probabilistic Automata

This paper presents a framework to recognize temporal compositions of at...

6 Rodrigo Santa Cruz, et al. ∙

research

∙ 12/10/2019

Forecasting Future Sequence of Actions to Complete an Activity

Future human action forecasting from partial observations of activities ...

0 Yan Bin Ng, et al. ∙

research

∙ 11/22/2019

Learning to Caption Images with Two-Stream Attention and Sentence Auto-Encoder

Automatically generating natural language descriptions from an image is ...

0 Arushi Goel, et al. ∙

research

∙ 11/18/2019

Action Anticipation with RBF Kernelized Feature Mapping RNN

We introduce a novel Recurrent Neural Network-based algorithm for future...

16 Yuge Shi, et al. ∙

research

∙ 11/18/2019

Action Anticipation with RBF KernelizedFeature Mapping RNN

We introduce a novel Recurrent Neural Network-based algorithm for future...

13 Yuge Shi, et al. ∙

research

∙ 10/07/2019

Human Action Sequence Classification

This paper classifies human action sequences from videos using a machine...

8 Yan Bin Ng, et al. ∙

research

∙ 04/16/2019

Weakly Supervised Gaussian Networks for Action Detection

Detecting temporal extents of human actions in videos is a challenging c...

0 Basura Fernando, et al. ∙

research

∙ 10/22/2018

VIENA2: A Driving Anticipation Dataset

Action anticipation is critical in scenarios where one needs to react be...

4 Mohammad Sadegh Aliakbarian, et al. ∙

research

∙ 08/01/2018

Action Anticipation By Predicting Future Dynamic Images

Human action-anticipation methods predict what is the future action by o...

0 Cristian Rodriguez, et al. ∙

research

∙ 01/26/2018

Neural Algebra of Classifiers

The world is fundamentally compositional, so it is natural to think of v...

0 Rodrigo Santa Cruz, et al. ∙

research

∙ 05/30/2017

Discriminatively Learned Hierarchical Rank Pooling Networks

In this work, we present novel temporal encoding methods for action and ...

0 Basura Fernando, et al. ∙

research

∙ 04/10/2017

DeepPermNet: Visual Permutation Learning

We present a principled approach to uncover the structure of visual data...

0 Rodrigo Santa Cruz, et al. ∙

research

∙ 04/07/2017

Generalized Rank Pooling for Activity Recognition

Most popular deep models for action recognition split video sequences in...

0 Anoop Cherian, et al. ∙

research

∙ 03/21/2017

Encouraging LSTMs to Anticipate Actions Very Early

In contrast to the widely studied problem of recognizing an action given...

0 Mohammad Sadegh Aliakbarian, et al. ∙

research

∙ 03/07/2017

Deep Learning for Automated Quality Assessment of Color Fundus Images in Diabetic Retinopathy Screening

Purpose To develop a computer based method for the automated assessment ...

0 Sajib Kumar Saha, et al. ∙

research

∙ 12/02/2016

Action Recognition with Dynamic Image Networks

We introduce the concept of "dynamic image", a novel compact representat...

0 Hakan Bilen, et al. ∙

research

∙ 12/02/2016

Guided Open Vocabulary Image Captioning with Constrained Beam Search

Existing image captioning models do not generalize well to out-of-domain...

0 Peter Anderson, et al. ∙

research

∙ 12/02/2016

Unsupervised Human Action Detection by Action Matching

We propose a new task of unsupervised action detection by action matchin...

0 Basura Fernando, et al. ∙

research

∙ 11/21/2016

Self-Supervised Video Representation Learning With Odd-One-Out Networks

We propose a new self-supervised CNN pre-training technique based on a n...

0 Basura Fernando, et al. ∙

research

∙ 11/17/2016

Generalized BackPropagation, Étude De Cas: Orthogonality

This paper introduces an extension of the backpropagation algorithm that...

0 Mehrtash Harandi, et al. ∙

research

∙ 11/17/2016

Deep Action- and Context-Aware Sequence Learning for Activity Recognition and Anticipation

Action recognition and anticipation are key to the success of many compu...

0 Mohammad Sadegh Aliakbarian, et al. ∙

research

∙ 07/29/2016

SPICE: Semantic Propositional Image Caption Evaluation

There is considerable interest in the task of automatically generating i...

0 Peter Anderson, et al. ∙

research

∙ 12/06/2015

Rank Pooling for Action Recognition

We propose a function-based temporal pooling method that captures the la...

0 Basura Fernando, et al. ∙

research

∙ 11/29/2015

MidRank: Learning to rank based on subsequences

We present a supervised learning to rank algorithm that effectively orde...

0 Basura Fernando, et al. ∙

research

∙ 09/16/2015

Guiding Long-Short Term Memory for Image Caption Generation

In this work we focus on the problem of image caption generation. We pro...

0 Xu Jia, et al. ∙

research

∙ 05/03/2015

Object Class Detection and Classification using Multi Scale Gradient and Corner Point based Shape Descriptors

This paper presents a novel multi scale gradient and a corner point base...

0 Basura Fernando, et al. ∙

research

∙ 11/17/2014

Joint cross-domain classification and subspace learning for unsupervised adaptation

Domain adaptation aims at adapting the knowledge acquired on a source do...

0 Basura Fernando, et al. ∙

research

∙ 09/26/2014

Location Recognition Over Large Time Lags

Would it be possible to automatically associate ancient pictures to mode...

0 Basura Fernando, et al. ∙

research

∙ 09/18/2014

Subspace Alignment For Domain Adaptation

In this paper, we introduce a new domain adaptation (DA) algorithm where...

0 Basura Fernando, et al. ∙

Basura Fernando

Featured Co-authors