Search Results for author: Amit K. Roy-Chowdhury

Found 62 papers, 14 papers with code

A-ACT: Action Anticipation through Cycle Transformations

no code implementations2 Apr 2022 Akash Gupta, Jingen Liu, Liefeng Bo, Amit K. Roy-Chowdhury, Tao Mei

To incorporate this ability in intelligent systems a question worth pondering upon is how exactly do we anticipate?

Action Anticipation

Controllable Dynamic Multi-Task Architectures

no code implementations28 Mar 2022 Dripta S. Raychaudhuri, Yumin Suh, Samuel Schulter, Xiang Yu, Masoud Faraki, Amit K. Roy-Chowdhury, Manmohan Chandraker

In contrast to the existing dynamic multi-task approaches that adjust only the weights within a fixed architecture, our approach affords the flexibility to dynamically control the total computational cost and match the user-preferred task importance better.

Multi-Task Learning

ADC: Adversarial attacks against object Detection that evade Context consistency checks

no code implementations24 Oct 2021 Mingjun Yin, Shasha Li, Chengyu Song, M. Salman Asif, Amit K. Roy-Chowdhury, Srikanth V. Krishnamurthy

A very recent defense strategy for detecting adversarial examples, that has been shown to be robust to current attacks, is to check for intrinsic context consistencies in the input data, where context refers to various relationships (e. g., object-to-object co-occurrence relationships) in images.

Object Detection

Ada-VSR: Adaptive Video Super-Resolution with Meta-Learning

no code implementations5 Aug 2021 Akash Gupta, Padmaja Jonnalagedda, Bir Bhanu, Amit K. Roy-Chowdhury

Specifically, meta-learning is employed to obtain adaptive parameters, using a large-scale external dataset, that can adapt quickly to the novel condition (degradation model) of the given test video during the internal learning task, thereby exploiting external and internal information of a video for super-resolution.

Frame Meta-Learning +2

Learning Few-shot Open-set Classifiers using Exemplar Reconstruction

no code implementations31 Jul 2021 Sayak Nag, Dripta S. Raychaudhuri, Sujoy Paul, Amit K. Roy-Chowdhury

We study the problem of how to identify samples from unseen categories (open-set classification) when there are only a few samples given from the seen categories (few-shot setting).

Classification Meta-Learning +1

Deep Quantized Representation for Enhanced Reconstruction

1 code implementation29 Jul 2021 Akash Gupta, Abhishek Aich, Kevin Rodriguez, G. Venugopala Reddy, Amit K. Roy-Chowdhury

In this paper, we propose a data-driven Deep Quantized Latent Representation (DQLR) methodology for high-quality image reconstruction in the Shoot Apical Meristem (SAM) of Arabidopsis thaliana.

Image Reconstruction

Spatio-Temporal Representation Factorization for Video-based Person Re-Identification

no code implementations ICCV 2021 Abhishek Aich, Meng Zheng, Srikrishna Karanam, Terrence Chen, Amit K. Roy-Chowdhury, Ziyan Wu

To alleviate these problems, we propose Spatio-Temporal Representation Factorization (STRF), a flexible new computational unit that can be used in conjunction with most existing 3D convolutional neural network architectures for re-ID.

Video-Based Person Re-Identification

Cross-domain Imitation from Observations

no code implementations20 May 2021 Dripta S. Raychaudhuri, Sujoy Paul, Jeroen van Baar, Amit K. Roy-Chowdhury

Once this correspondence is found, we can directly transfer the demonstrations on one domain to the other and use it for imitation.

Imitation Learning

Unsupervised Multi-source Domain Adaptation Without Access to Source Data

1 code implementation CVPR 2021 Sk Miraj Ahmed, Dripta S. Raychaudhuri, Sujoy Paul, Samet Oymak, Amit K. Roy-Chowdhury

A recent line of work addressed this problem and proposed an algorithm that transfers knowledge to the unlabeled target domain from a single source model without requiring access to the source data.

Unsupervised Domain Adaptation

Detection and Localization of Facial Expression Manipulations

no code implementations15 Mar 2021 Ghazal Mazaheri, Amit K. Roy-Chowdhury

Thus, it is important to develop methods that can detect manipulations in facial expressions, and localize the manipulated regions.

Facial Expression Recognition Image Manipulation

Learning to identify image manipulations in scientific publications

no code implementations3 Feb 2021 Ghazal Mazaheri, Kevin Urrutia Avila, Amit K. Roy-Chowdhury

We show that our method leads to a 90% accuracy rate of detecting duplicated images, a ~ 13% improvement in detection accuracy in comparison to other manipulation detection methods.

Exploiting Context for Robustness to Label Noise in Active Learning

no code implementations18 Oct 2020 Sudipta Paul, Shivkumar Chandrasekaran, B. S. Manjunath, Amit K. Roy-Chowdhury

Several works in computer vision have demonstrated the effectiveness of active learning for adapting the recognition model when new unlabeled data becomes available.

Active Learning Document Classification +2

ALANET: Adaptive Latent Attention Network forJoint Video Deblurring and Interpolation

no code implementations31 Aug 2020 Akash Gupta, Abhishek Aich, Amit K. Roy-Chowdhury

Different from these works, we address a more realistic problem of high frame-rate sharp video synthesis with no prior assumption that input is always blurry.

Deblurring Frame

Measurement-driven Security Analysis of Imperceptible Impersonation Attacks

no code implementations26 Aug 2020 Shasha Li, Karim Khalil, Rameswar Panda, Chengyu Song, Srikanth V. Krishnamurthy, Amit K. Roy-Chowdhury, Ananthram Swami

The emergence of Internet of Things (IoT) brings about new security challenges at the intersection of cyber and physical spaces.

Face Recognition

Text-based Localization of Moments in a Video Corpus

no code implementations20 Aug 2020 Sudipta Paul, Niluthpol Chowdhury Mithun, Amit K. Roy-Chowdhury

This task poses a unique challenge as the system is required to perform: (i) retrieval of the relevant video where only a segment of the video corresponds with the queried sentence, and (ii) temporal localization of moment in the relevant video based on sentence query.

Moment Retrieval Temporal Localization

Adversarial Knowledge Transfer from Unlabeled Data

1 code implementation13 Aug 2020 Akash Gupta, Rameswar Panda, Sujoy Paul, Jianming Zhang, Amit K. Roy-Chowdhury

While machine learning approaches to visual recognition offer great promise, most of the existing methods rely heavily on the availability of large quantities of labeled training data.

Transfer Learning

Distributed Multi-agent Video Fast-forwarding

1 code implementation10 Aug 2020 Shuyue Lan, Zhilu Wang, Amit K. Roy-Chowdhury, Ermin Wei, Qi Zhu

In many intelligent systems, a network of agents collaboratively perceives the environment for better and more efficient situation awareness.

Exploiting Temporal Coherence for Self-Supervised One-shot Video Re-identification

no code implementations ECCV 2020 Dripta S. Raychaudhuri, Amit K. Roy-Chowdhury

While supervised techniques in re-identification are extremely effective, the need for large amounts of annotations makes them impractical for large camera networks.

One-Shot Learning

Non-Adversarial Video Synthesis with Learned Priors

1 code implementation CVPR 2020 Abhishek Aich, Akash Gupta, Rameswar Panda, Rakib Hyder, M. Salman Asif, Amit K. Roy-Chowdhury

Different from these methods, we focus on the problem of generating videos from latent noise vectors, without any reference input frames.


Learning from Trajectories via Subgoal Discovery

1 code implementation NeurIPS 2019 Sujoy Paul, Jeroen van Baar, Amit K. Roy-Chowdhury

Learning to solve complex goal-oriented tasks with sparse terminal-only rewards often requires an enormous number of samples.

Imitation Learning

Exploiting Global Camera Network Constraints for Unsupervised Video Person Re-identification

no code implementations27 Aug 2019 Xueping Wang, Rameswar Panda, Min Liu, Yaonan Wang, Amit K. Roy-Chowdhury

Additionally, a cross-view matching strategy followed by global camera network constraints is proposed to explore the matching relationships across the entire camera network.

Graph Matching Metric Learning +2

Prediction and Description of Near-Future Activities in Video

no code implementations2 Aug 2019 Tahmida Mahmud, Mohammad Billah, Mahmudul Hasan, Amit K. Roy-Chowdhury

Most of the existing works on human activity analysis focus on recognition or early recognition of the activity labels from complete or partial observations.

Video Captioning Video Description

A Skip Connection Architecture for Localization of Image Manipulations

no code implementations IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops 2019 Ghazal Mazaheri, Niluthpol Chowdhury Mithun, Jawadul H. Bappy, Amit K. Roy-Chowdhury

In order to exploit these traces in localizing the tampered regions, we propose an encoder-decoder based network where we fuse representations from early layers in the encoder (which are richer in low-level spatial cues, like edges) by skip pooling with representations of the last layer of the decoder and use for manipulation detection.

Image Manipulation Image Manipulation Detection

Context-Aware Query Selection for Active Learning in Event Recognition

no code implementations9 Apr 2019 Mahmudul Hasan, Sujoy Paul, Anastasios I. Mourikis, Amit K. Roy-Chowdhury

We formulate a conditional random field model that encodes the context and devise an information-theoretic approach that utilizes entropy and mutual information of the nodes to compute the set of most informative queries, which are labeled by a human.

Active Learning Activity Recognition +1

Weakly Supervised Video Moment Retrieval From Text Queries

1 code implementation CVPR 2019 Niluthpol Chowdhury Mithun, Sujoy Paul, Amit K. Roy-Chowdhury

The weak nature of the supervision is because, during training, we only have access to the video-text pairs rather than the temporal extent of the video to which different text descriptions relate.

Moment Retrieval

Detecting GAN generated Fake Images using Co-occurrence Matrices

no code implementations15 Mar 2019 Lakshmanan Nataraj, Tajuddin Manhar Mohammed, Shivkumar Chandrasekaran, Arjuna Flenner, Jawadul H. Bappy, Amit K. Roy-Chowdhury, B. S. Manjunath

The advent of Generative Adversarial Networks (GANs) has brought about completely novel ways of transforming and manipulating pixels in digital images.

Hybrid LSTM and Encoder-Decoder Architecture for Detection of Image Forgeries

1 code implementation6 Mar 2019 Jawadul H. Bappy, Cody Simons, Lakshmanan Nataraj, B. S. Manjunath, Amit K. Roy-Chowdhury

This paper proposes a high-confidence manipulation localization architecture which utilizes resampling features, Long-Short Term Memory (LSTM) cells, and encoder-decoder network to segment out manipulated regions from non-manipulated ones.

Webly Supervised Joint Embedding for Cross-Modal lmage-Text Retrieval

no code implementations Proceedings of the 26th ACM international conference on Multimedia·October 2018 2018 Niluthpol Chowdhury Mithun, Rameswar Panda, Vagelis Papalexakis, Amit K. Roy-Chowdhury

Inspired by the recent success of web-supervised learning in deep neural networks, we capitalize on readily-available web images with noisy annotations to learn robust image-text joint representation.

Cross-Modal Retrieval

Multi-View Frame Reconstruction with Conditional GAN

no code implementations27 Sep 2018 Tahmida Mahmud, Mohammad Billah, Amit K. Roy-Chowdhury

Multi-view frame reconstruction is an important problem particularly when multiple frames are missing and past and future frames within the camera are far apart from the missing ones.


Webly Supervised Joint Embedding for Cross-Modal Image-Text Retrieval

no code implementations23 Aug 2018 Niluthpol Chowdhury Mithun, Rameswar Panda, Evangelos E. Papalexakis, Amit K. Roy-Chowdhury

Inspired by the recent success of webly supervised learning in deep neural networks, we capitalize on readily-available web images with noisy annotations to learn robust image-text joint representation.

Cross-Modal Retrieval

Contemplating Visual Emotions: Understanding and Overcoming Dataset Bias

no code implementations ECCV 2018 Rameswar Panda, Jianming Zhang, Haoxiang Li, Joon-Young Lee, Xin Lu, Amit K. Roy-Chowdhury

While machine learning approaches to visual emotion recognition offer great promise, current methods consider training and testing models on small scale datasets covering limited visual emotion concepts.

Emotion Recognition

Incorporating Scalability in Unsupervised Spatio-Temporal Feature Learning

no code implementations6 Aug 2018 Sujoy Paul, Sourya Roy, Amit K. Roy-Chowdhury

This necessitates learning of visual features from videos in an unsupervised setting.

Learning Joint Embedding with Multimodal Cues for Cross-Modal Video-Text Retrieval

1 code implementation ICMR 2018 Niluthpol Chowdhury Mithun, Juncheng Li, Florian Metze, Amit K. Roy-Chowdhury

Constructing a joint representation invariant across different modalities (e. g., video, language) is of significant importance in many multimedia applications.

Video-Text Retrieval

Exploiting Transitivity for Learning Person Re-Identification Models on a Budget

no code implementations CVPR 2018 Sourya Roy, Sujoy Paul, Neal E. Young, Amit K. Roy-Chowdhury

Minimization of labeling effort for person re-identification in camera networks is an important problem as most of the existing popular methods are supervised and they require large amount of manual annotations, acquiring which is a tedious job.

Person Re-Identification

FFNet: Video Fast-Forwarding via Reinforcement Learning

1 code implementation CVPR 2018 Shuyue Lan, Rameswar Panda, Qi Zhu, Amit K. Roy-Chowdhury

The first group is supported by video summarization techniques, which require processing of the entire video to select an important subset for showing to users.

reinforcement-learning Video Summarization

Weakly Supervised Summarization of Web Videos

no code implementations ICCV 2017 Rameswar Panda, Abir Das, Ziyan Wu, Jan Ernst, Amit K. Roy-Chowdhury

Casting the problem as a weakly supervised learning problem, we propose a flexible deep 3D CNN architecture to learn the notion of importance using only video-level annotation, and without any human-crafted training data.

Joint Prediction of Activity Labels and Starting Times in Untrimmed Videos

no code implementations ICCV 2017 Tahmida Mahmud, Mahmudul Hasan, Amit K. Roy-Chowdhury

We propose a network similar to a hybrid Siamese network with three branches to jointly learn both the future label and the starting time.

Exploiting Spatial Structure for Localizing Manipulated Image Regions

no code implementations ICCV 2017 Jawadul H. Bappy, Amit K. Roy-Chowdhury, Jason Bunk, Lakshmanan Nataraj, B. S. Manjunath

In order to formulate the framework, we employ a hybrid CNN-LSTM model to capture discriminative features between manipulated and non-manipulated regions.

Image Manipulation Semantic Segmentation

The Impact of Typicality for Informative Representative Selection

no code implementations CVPR 2017 Jawadul H. Bappy, Sujoy Paul, Ertem Tuncel, Amit K. Roy-Chowdhury

In computer vision, selection of the most informative samples from a huge pool of training data in order to learn a good recognition model is an active research problem.

Active Learning Data Compression

Multi-View Surveillance Video Summarization via Joint Embedding and Sparse Optimization

no code implementations9 Jun 2017 Rameswar Panda, Amit K. Roy-Chowdhury

In this paper, with the aim of summarizing multi-view videos, we introduce a novel unsupervised framework via joint embedding and sparse representative selection.

Video Summarization

Collaborative Summarization of Topic-Related Videos

no code implementations CVPR 2017 Rameswar Panda, Amit K. Roy-Chowdhury

Large collections of videos are grouped into clusters by a topic keyword, such as Eiffel Tower or Surfing, with many important visual concepts repeating across them.

Information Retrieval

Diversity-aware Multi-Video Summarization

no code implementations9 Jun 2017 Rameswar Panda, Niluthpol Chowdhury Mithun, Amit K. Roy-Chowdhury

Most video summarization approaches have focused on extracting a summary from a single video; we propose an unsupervised framework for summarizing a collection of videos.

Video Summarization

Unsupervised Adaptive Re-identification in Open World Dynamic Camera Networks

no code implementations CVPR 2017 Rameswar Panda, Amran Bhuiyan, Vittorio Murino, Amit K. Roy-Chowdhury

Most approaches have neglected the dynamic and open world nature of the re-identification problem, where a new camera may be temporarily inserted into an existing system to get additional information.

Person Re-Identification

Video Summarization in a Multi-View Camera Network

no code implementations1 Aug 2016 Rameswar Panda, Abir Das, Amit K. Roy-Chowdhury

While most existing video summarization approaches aim to extract an informative summary of a single video, we propose a novel framework for summarizing multi-view videos by exploiting both intra- and inter-view content correlations in a joint embedding space.

Video Summarization

Continuous Adaptation of Multi-Camera Person Identification Models through Sparse Non-redundant Representative Selection

no code implementations1 Jul 2016 Abir Das, Rameswar Panda, Amit K. Roy-Chowdhury

We demonstrate the effectiveness of our approach on multi-camera person re-identification datasets, to demonstrate the feasibility of learning online classification models in multi-camera big data applications.

Person Identification Person Re-Identification

Learning Temporal Regularity in Video Sequences

2 code implementations CVPR 2016 Mahmudul Hasan, Jonghyun Choi, Jan Neumann, Amit K. Roy-Chowdhury, Larry S. Davis

Perceiving meaningful activities in a long video sequence is a challenging problem due to ambiguous definition of 'meaningfulness' as well as clutters in the scene.

Semi-supervised Anomaly Detection

Context Aware Active Learning of Activity Recognition Models

no code implementations ICCV 2015 Mahmudul Hasan, Amit K. Roy-Chowdhury

We formulate a conditional random field (CRF) model that encodes the context and devise an information theoretic approach that utilizes entropy and mutual information of the nodes to compute the set of most informative query instances, which need to be labeled by a human.

Active Learning Activity Recognition +1

Incremental Activity Modeling and Recognition in Streaming Videos

no code implementations CVPR 2014 Mahmudul Hasan, Amit K. Roy-Chowdhury

Most of the state-of-the-art approaches to human activity recognition in video need an intensive training stage and assume that all of the training examples are labeled and available beforehand.

Active Learning Activity Recognition

Context-Aware Modeling and Recognition of Activities in Video

no code implementations CVPR 2013 Yingying Zhu, Nandita M. Nayak, Amit K. Roy-Chowdhury

This is motivated from the observations that the activities related in space and time rarely occur independently and can serve as the context for each other.

Motion Segmentation

Information Consensus for Distributed Multi-target Tracking

no code implementations CVPR 2013 Ahmed T. Kamal, Jay A. Farrell, Amit K. Roy-Chowdhury

The estimation errors in tracking and data association, as well as the effect of naivety, are jointly addressed leading to the development of an informationweighted consensus algorithm, which we term as the Multitarget Information Consensus (MTIC) algorithm.

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