Search Results for author: Mohan Kankanhalli

Found 45 papers, 18 papers with code

Identifying Worry in Twitter: Beyond Emotion Analysis

no code implementations EMNLP (NLP+CSS) 2020 Reyha Verma, Christian von der Weth, Jithin Vachery, Mohan Kankanhalli

Identifying the worries of individuals and societies plays a crucial role in providing social support and enhancing policy decision-making.

Decision Making Emotion Recognition

Inferring DQN structure for high-dimensional continuous control

no code implementations ICML 2020 Andrey Sakryukin, Chedy Raissi, Mohan Kankanhalli

We propose a novel approach to infer the network structure for DQN models operating with high-dimensional continuous actions.

Continuous Control

Disentangled Multimodal Representation Learning for Recommendation

no code implementations10 Mar 2022 Fan Liu, Zhiyong Cheng, Huilin Chen, AnAn Liu, Liqiang Nie, Mohan Kankanhalli

In particular, we adopt a disentangled representation technique to ensure the features of different factors in each modality are independent to each other.

Recommendation Systems Representation Learning

Joint Answering and Explanation for Visual Commonsense Reasoning

1 code implementation25 Feb 2022 Zhenyang Li, Yangyang Guo, Kejie Wang, Yinwei Wei, Liqiang Nie, Mohan Kankanhalli

Given that our framework is model-agnostic, we apply it to the existing popular baselines and validate its effectiveness on the benchmark dataset.

Knowledge Distillation Question Answering +3

On Modality Bias Recognition and Reduction

no code implementations25 Feb 2022 Yangyang Guo, Liqiang Nie, Harry Cheng, Zhiyong Cheng, Mohan Kankanhalli, Alberto del Bimbo

From the results on four datasets regarding the above three tasks, our method yields remarkable performance improvements compared with the baselines, demonstrating its superiority on reducing the modality bias problem.

Action Recognition Question Answering +1

Adversarial Attacks and Defense for Non-Parametric Two-Sample Tests

no code implementations7 Feb 2022 Xilie Xu, Jingfeng Zhang, Feng Liu, Masashi Sugiyama, Mohan Kankanhalli

First, we theoretically show that an adversary can upper-bound the distributional shift which guarantees the attack's invisibility.

Learning to Predict Gradients for Semi-Supervised Continual Learning

1 code implementation23 Jan 2022 Yan Luo, Yongkang Wong, Mohan Kankanhalli, Qi Zhao

To explore these issues, we formulate a new semi-supervised continual learning method, which can be generically applied to existing continual learning models.

Continual Learning

Zero-Shot Machine Unlearning

no code implementations14 Jan 2022 Vikram S Chundawat, Ayush K Tarun, Murari Mandal, Mohan Kankanhalli

This necessitates deletion of data not only from storage archives but also from ML model.

Transfer Learning

Fast Yet Effective Machine Unlearning

no code implementations17 Nov 2021 Ayush K Tarun, Vikram S Chundawat, Murari Mandal, Mohan Kankanhalli

In the impair step, the noise matrix along with a very high learning rate is used to induce sharp unlearning in the model.

Unsupervised Abstract Reasoning for Raven's Problem Matrices

1 code implementation21 Sep 2021 Tao Zhuo, Qiang Huang, Mohan Kankanhalli

Raven's Progressive Matrices (RPM) is highly correlated with human intelligence, and it has been widely used to measure the abstract reasoning ability of humans.

Fair Representation: Guaranteeing Approximate Multiple Group Fairness for Unknown Tasks

1 code implementation1 Sep 2021 Xudong Shen, Yongkang Wong, Mohan Kankanhalli

Motivated by scenarios where data is used for diverse prediction tasks, we study whether fair representation can be used to guarantee fairness for unknown tasks and for multiple fairness notions simultaneously.


Relation-aware Compositional Zero-shot Learning for Attribute-Object Pair Recognition

1 code implementation10 Aug 2021 Ziwei Xu, Guangzhi Wang, Yongkang Wong, Mohan Kankanhalli

The concept module generates semantically meaningful features for primitive concepts, whereas the visual module extracts visual features for attributes and objects from input images.

Compositional Zero-Shot Learning

Understanding the Interaction of Adversarial Training with Noisy Labels

no code implementations6 Feb 2021 Jianing Zhu, Jingfeng Zhang, Bo Han, Tongliang Liu, Gang Niu, Hongxia Yang, Mohan Kankanhalli, Masashi Sugiyama

A recent adversarial training (AT) study showed that the number of projected gradient descent (PGD) steps to successfully attack a point (i. e., find an adversarial example in its proximity) is an effective measure of the robustness of this point.

PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences

no code implementations ICLR 2021 Hehe Fan, Xin Yu, Yuhang Ding, Yi Yang, Mohan Kankanhalli

Then, a spatial convolution is employed to capture the local structure of points in the 3D space, and a temporal convolution is used to model the dynamics of the spatial regions along the time dimension.

3D Action Recognition Semantic Segmentation

Learning Causal Representation for Training Cross-Domain Pose Estimator via Generative Interventions

no code implementations ICCV 2021 Xiheng Zhang, Yongkang Wong, Xiaofei Wu, Juwei Lu, Mohan Kankanhalli, Xiangdong Li, Weidong Geng

In this work, we take a step towards training robust models for cross-domain pose estimation task, which brings together ideas from causal representation learning and generative adversarial networks.

3D Pose Estimation Domain Generalization +2

Unsupervised Spatial-spectral Network Learning for Hyperspectral Compressive Snapshot Reconstruction

no code implementations18 Dec 2020 Yubao Sun, Ying Yang, Qingshan Liu, Mohan Kankanhalli

Hyperspectral compressive imaging takes advantage of compressive sensing theory to achieve coded aperture snapshot measurement without temporal scanning, and the entire three-dimensional spatial-spectral data is captured by a two-dimensional projection during a single integration period.

Compressive Sensing

Geometry-aware Instance-reweighted Adversarial Training

1 code implementation ICLR 2021 Jingfeng Zhang, Jianing Zhu, Gang Niu, Bo Han, Masashi Sugiyama, Mohan Kankanhalli

The belief was challenged by recent studies where we can maintain the robustness and improve the accuracy.

My Health Sensor, my Classifier: Adapting a Trained Classifier to Unlabeled End-User Data

no code implementations22 Sep 2020 Konstantinos Nikolaidis, Stein Kristiansen, Thomas Plagemann, Vera Goebel, Knut Liestøl, Mohan Kankanhalli, Gunn Marit Traaen, Britt Øverland, Harriet Akre, Lars Aakerøy, Sigurd Steinshamn

In this work, we present an approach for unsupervised domain adaptation (DA) with the constraint, that the labeled source data are not directly available, and instead only access to a classifier trained on the source data is provided.

Sleep apnea detection Unsupervised Domain Adaptation

Learning Realistic Patterns from Unrealistic Stimuli: Generalization and Data Anonymization

1 code implementation21 Sep 2020 Konstantinos Nikolaidis, Stein Kristiansen, Thomas Plagemann, Vera Goebel, Knut Liestøl, Mohan Kankanhalli, Gunn Marit Traaen, Britt Øverland, Harriet Akre, Lars Aakerøy, Sigurd Steinshamn

We use sleep monitoring data from both an open and a large closed clinical study and evaluate whether (1) end-users can create and successfully use customized classification models for sleep apnea detection, and (2) the identity of participants in the study is protected.

Sleep apnea detection

Robust Federated Recommendation System

no code implementations15 Jun 2020 Chen Chen, Jingfeng Zhang, Anthony K. H. Tung, Mohan Kankanhalli, Gang Chen

We argue that the key to Byzantine detection is monitoring of gradients of the model parameters of clients.

Recommendation Systems

Hierarchically Fair Federated Learning

no code implementations22 Apr 2020 Jingfeng Zhang, Cheng Li, Antonio Robles-Kelly, Mohan Kankanhalli

When the federated learning is adopted among competitive agents with siloed datasets, agents are self-interested and participate only if they are fairly rewarded.

Fairness Federated Learning

Adversarial Learning for Personalized Tag Recommendation

1 code implementation1 Apr 2020 Erik Quintanilla, Yogesh Rawat, Andrey Sakryukin, Mubarak Shah, Mohan Kankanhalli

We demonstrate the effectiveness of the proposed model on two different large-scale and publicly available datasets, YFCC100M and NUS-WIDE.

General Classification Image Classification +2

Evaluating Salient Object Detection in Natural Images with Multiple Objects having Multi-level Saliency

1 code implementation19 Mar 2020 Gökhan Yildirim, Debashis Sen, Mohan Kankanhalli, Sabine Süsstrunk

In this paper, we corroborate based on three subjective experiments on a novel image dataset that objects in natural images are inherently perceived to have varying levels of importance.

RGB Salient Object Detection Saliency Detection +1

GradMix: Multi-source Transfer across Domains and Tasks

no code implementations9 Feb 2020 Junnan Li, Ziwei Xu, Yongkang Wong, Qi Zhao, Mohan Kankanhalli

Therefore, it is important to develop algorithms that can leverage off-the-shelf labeled dataset to learn useful knowledge for the target task.

Action Recognition Meta-Learning +1

Weakly-Supervised Multi-Person Action Recognition in 360$^{\circ}$ Videos

no code implementations9 Feb 2020 Junnan Li, Jianquan Liu, Yongkang Wong, Shoji Nishimura, Mohan Kankanhalli

To enable research in this direction, we introduce 360Action, the first omnidirectional video dataset for multi-person action recognition.

Action Localization Action Recognition +1

Solving Raven's Progressive Matrices with Neural Networks

1 code implementation5 Feb 2020 Tao Zhuo, Mohan Kankanhalli

Based on the design of the pseudo target, MCPT converts the unsupervised learning problem to a supervised task.

Fast Video Object Segmentation via Mask Transfer Network

no code implementations28 Aug 2019 Tao Zhuo, Zhiyong Cheng, Mohan Kankanhalli

To overcome this limitation, we propose a novel mask transfer network (MTN), which can greatly boost the processing speed of VOS and also achieve a reasonable accuracy.

Frame Semantic Segmentation +2

Explainable Video Action Reasoning via Prior Knowledge and State Transitions

1 code implementation28 Aug 2019 Tao Zhuo, Zhiyong Cheng, Peng Zhang, Yongkang Wong, Mohan Kankanhalli

Finally, by sequentially examining each state transition in the video graph, our method can detect and explain how those actions are executed with prior knowledge, just like the logical manner of thinking by humans.

Action Analysis

User Diverse Preference Modeling by Multimodal Attentive Metric Learning

1 code implementation21 Aug 2019 Fan Liu, Zhiyong Cheng, Changchang Sun, Yinglong Wang, Liqiang Nie, Mohan Kankanhalli

To tackle this problem, in this paper, we propose a novel Multimodal Attentive Metric Learning (MAML) method to model user diverse preferences for various items.

Metric Learning Recommendation Systems

Quantifying and Alleviating the Language Prior Problem in Visual Question Answering

1 code implementation13 May 2019 Yangyang Guo, Zhiyong Cheng, Liqiang Nie, Yibing Liu, Yinglong Wang, Mohan Kankanhalli

Benefiting from the advancement of computer vision, natural language processing and information retrieval techniques, visual question answering (VQA), which aims to answer questions about an image or a video, has received lots of attentions over the past few years.

Information Retrieval Question Answering +2

$\mathcal{G}$-softmax: Improving Intra-class Compactness and Inter-class Separability of Features

1 code implementation8 Apr 2019 Yan Luo, Yongkang Wong, Mohan Kankanhalli, Qi Zhao

In addition, analysis of the intra-class compactness and inter-class separability demonstrates the advantages of the proposed function over the softmax function, which is consistent with the performance improvement.

General Classification Multi-Label Classification

Towards Robust ResNet: A Small Step but A Giant Leap

no code implementations28 Feb 2019 Jingfeng Zhang, Bo Han, Laura Wynter, Kian Hsiang Low, Mohan Kankanhalli

Our analytical studies reveal that the step factor h in the Euler method is able to control the robustness of ResNet in both its training and generalization.

Learning to Learn from Noisy Labeled Data

1 code implementation CVPR 2019 Junnan Li, Yongkang Wong, Qi Zhao, Mohan Kankanhalli

Despite the success of deep neural networks (DNNs) in image classification tasks, the human-level performance relies on massive training data with high-quality manual annotations, which are expensive and time-consuming to collect.

Ranked #14 on Image Classification on Clothing1M (using extra training data)

Learning with noisy labels Meta-Learning

MMALFM: Explainable Recommendation by Leveraging Reviews and Images

no code implementations12 Nov 2018 Zhiyong Cheng, Xiaojun Chang, Lei Zhu, Rose C. Kanjirathinkal, Mohan Kankanhalli

Then the aspect importance is integrated into a novel aspect-aware latent factor model (ALFM), which learns user's and item's latent factors based on ratings.

Looking Beyond a Clever Narrative: Visual Context and Attention are Primary Drivers of Affect in Video Advertisements

no code implementations14 Aug 2018 Abhinav Shukla, Harish Katti, Mohan Kankanhalli, Ramanathan Subramanian

Contrary to the popular notion that ad affect hinges on the narrative and the clever use of linguistic and social cues, we find that actively attended objects and the coarse scene structure better encode affective information as compared to individual scene objects or conspicuous background elements.

Attention Transfer from Web Images for Video Recognition

no code implementations3 Aug 2017 Junnan Li, Yongkang Wong, Qi Zhao, Mohan Kankanhalli

However, due to the domain shift problem, the performance of Web images trained deep classifiers tend to degrade when directly deployed to videos.

Action Recognition Video Recognition

Multi-Camera Action Dataset for Cross-Camera Action Recognition Benchmarking

no code implementations21 Jul 2016 Wenhui Li, Yongkang Wong, An-An Liu, Yang Li, Yu-Ting Su, Mohan Kankanhalli

To enable the study of this problem, there exist a vast number of action datasets, which are recorded under controlled laboratory settings, real-world surveillance environments, or crawled from the Internet.

Action Recognition

Near-Optimal Active Learning of Multi-Output Gaussian Processes

1 code implementation21 Nov 2015 Yehong Zhang, Trong Nghia Hoang, Kian Hsiang Low, Mohan Kankanhalli

This paper addresses the problem of active learning of a multi-output Gaussian process (MOGP) model representing multiple types of coexisting correlated environmental phenomena.

Active Learning Gaussian Processes

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