no code implementations • 10 Apr 2024 • Aakash Kumar, Chen Chen, Ajmal Mian, Neils Lobo, Mubarak Shah
Our method requires only a small number of 3D points, that can be obtained from a low-cost, low-resolution sensor.
no code implementations • 3 Apr 2024 • Jordan Vice, Naveed Akhtar, Richard Hartley, Ajmal Mian
Charting the susceptibility of T2I models to such manipulation, we first expose the new possibility of a dynamic and computationally efficient exploitation of model bias by targeting the embedded language models.
1 code implementation • 28 Mar 2024 • Bo Miao, Mohammed Bennamoun, Yongsheng Gao, Mubarak Shah, Ajmal Mian
Referring Video Object Segmentation (R-VOS) methods face challenges in maintaining consistent object segmentation due to temporal context variability and the presence of other visually similar objects.
Ranked #3 on Referring Video Object Segmentation on Refer-YouTube-VOS (using extra training data)
no code implementations • 21 Mar 2024 • Haoran Hou, Mingtao Feng, Zijie Wu, Weisheng Dong, Qing Zhu, Yaonan Wang, Ajmal Mian
In this work, we focus on the distributional properties of point clouds and formulate the voting process as generating new points in the high-density region of the distribution of object centers.
no code implementations • 21 Mar 2024 • Zijie Wu, Mingtao Feng, Yaonan Wang, He Xie, Weisheng Dong, Bo Miao, Ajmal Mian
Generating realistic 3D scenes is challenging due to the complexity of room layouts and object geometries. We propose a sketch based knowledge enhanced diffusion architecture (SEK) for generating customized, diverse, and plausible 3D scenes.
no code implementations • 21 Mar 2024 • Yong He, Hongshan Yu, Muhammad Ibrahim, Xiaoyan Liu, Tongjia Chen, Anwaar Ulhaq, Ajmal Mian
This strategy allows various transformer blocks to share the same position information over the same resolution points, thereby reducing network parameters and training time without compromising accuracy. Experimental comparisons with existing methods on multiple datasets demonstrate the efficacy of SMTransformer and skip-attention-based up-sampling for point cloud processing tasks, including semantic segmentation and classification.
no code implementations • 20 Mar 2024 • Qitong Yang, Mingtao Feng, Zijie Wu, ShiJie Sun, Weisheng Dong, Yaonan Wang, Ajmal Mian
To address this, we propose a novel framework that generates coherent 4D sequences with animation of 3D shapes under given conditions with dynamic evolution of shape and color over time through integrative latent mapping.
no code implementations • 28 Jan 2024 • Shuai Yuan, Hanlin Qin, Xiang Yan, Naveed Akhtar, Ajmal Mian
In the proposed SCTBs, the outputs of all encoders are interacted with cross transformer to generate mixed features, which are redistributed to all decoders to effectively reinforce semantic differences between the target and clutter at full scales.
no code implementations • 20 Dec 2023 • Jordan Vice, Naveed Akhtar, Richard Hartley, Ajmal Mian
Bias in text-to-image (T2I) models can propagate unfair social representations and may be used to aggressively market ideas or push controversial agendas.
no code implementations • 26 Sep 2023 • Yunzhuo Chen, Nur Al Hasan Haldar, Naveed Akhtar, Ajmal Mian
To curb their exploitation for Deepfakes, it is imperative to first explore the extent to which diffusion models can be used to generate realistic content that is controllable with convenient prompts.
no code implementations • 26 Sep 2023 • Yunzhuo Chen, Naveed Akhtar, Nur Al Hasan Haldar, Ajmal Mian
Recent advances in diffusion models have led to a quantum leap in the quality of generative visual content.
no code implementations • 20 Sep 2023 • Rahul Ambati, Naveed Akhtar, Ajmal Mian, Yogesh Singh Rawat
Inspired by this, we introduce a novel problem of PRofiling Adversarial aTtacks (PRAT).
no code implementations • 18 Sep 2023 • James Beetham, Navid Kardan, Ajmal Mian, Mubarak Shah
To this end, the two main challenges are estimating gradients of the target model without access to its parameters, and generating a diverse set of training samples that thoroughly explores the input space.
no code implementations • 22 Aug 2023 • Larry Huynh, Jin Hong, Ajmal Mian, Hajime Suzuki, Yanqiu Wu, Seyit Camtepe
Quantum-inspired Machine Learning (QiML) is a burgeoning field, receiving global attention from researchers for its potential to leverage principles of quantum mechanics within classical computational frameworks.
no code implementations • ICCV 2023 • Zijie Wu, Yaonan Wang, Mingtao Feng, He Xie, Ajmal Mian
In this paper, we propose a sketch and text guided probabilistic diffusion model for colored point cloud generation that conditions the denoising process jointly with a hand drawn sketch of the object and its textual description.
1 code implementation • 31 Jul 2023 • Jordan Vice, Naveed Akhtar, Richard Hartley, Ajmal Mian
Based on the penetration level, BAGM takes the form of a suite of attacks that are referred to as surface, shallow and deep attacks in this article.
1 code implementation • ICCV 2023 • Bo Miao, Mohammed Bennamoun, Yongsheng Gao, Ajmal Mian
To address the drift problem, we propose a Spectrum-guided Multi-granularity (SgMg) approach, which performs direct segmentation on the encoded features and employs visual details to further optimize the masks.
Ranked #1 on Referring Expression Segmentation on J-HMDB (using extra training data)
1 code implementation • 12 Jul 2023 • Humza Naveed, Asad Ullah Khan, Shi Qiu, Muhammad Saqib, Saeed Anwar, Muhammad Usman, Naveed Akhtar, Nick Barnes, Ajmal Mian
Large Language Models (LLMs) have recently demonstrated remarkable capabilities in natural language processing tasks and beyond.
no code implementations • 3 Jul 2023 • Muhammad Ibrahim, Naveed Akhtar, Saeed Anwar, Ajmal Mian
The results ascertain the efficacy of our technique.
no code implementations • 17 Apr 2023 • Sania Zahan, Zulqarnain Gilani, Ghulam Mubashar Hassan, Ajmal Mian
Autism diagnosis presents a major challenge due to the vast heterogeneity of the condition and the elusive nature of early detection.
no code implementations • 8 Mar 2023 • Yong He, Hongshan Yu, Zhengeng Yang, Wei Sun, Mingtao Feng, Ajmal Mian
Local features and contextual dependencies are crucial for 3D point cloud analysis.
no code implementations • 8 Mar 2023 • Yong He, Hongshan Yu, Zhengeng Yang, Xiaoyan Liu, Wei Sun, Ajmal Mian
In particular, we achieve state-of-the-art semantic segmentation results of 76% mIoU on S3DIS 6-fold and 72. 2% on S3DIS Area5.
no code implementations • 26 Feb 2023 • Cris Cunha, Wei Liu, Tim French, Ajmal Mian
We present Q-Cogni, an algorithmically integrated causal reinforcement learning framework that redesigns Q-Learning with an autonomous causal structure discovery method to improve the learning process with causal inference.
no code implementations • 21 Jan 2023 • Muhammad Ibrahim, Naveed Akhtar, Saeed Anwar, Michael Wise, Ajmal Mian
We present a self-supervised learning method that employs Transformers for the first time for the task of outdoor localization using LiDAR data.
no code implementations • 15 Jan 2023 • Sania Zahan, Ghulam Mubashar Hassan, Ajmal Mian
Athlete performance measurement in sports videos requires modeling long sequences since the entire spatio-temporal progression contributes dominantly to the performance.
no code implementations • CVPR 2023 • Mingtao Feng, Haoran Hou, Liang Zhang, Zijie Wu, Yulan Guo, Ajmal Mian
In-depth understanding of a 3D scene not only involves locating/recognizing individual objects, but also requires to infer the relationships and interactions among them.
1 code implementation • 8 Dec 2022 • Jiantong Jiang, Zeyi Wen, Ajmal Mian
The mainstream BN structure learning methods require performing a large number of conditional independence (CI) tests.
1 code implementation • 8 Dec 2022 • Jiantong Jiang, Zeyi Wen, Atif Mansoor, Ajmal Mian
Bayesian networks (BNs) are attractive, because they are graphical and interpretable machine learning models.
no code implementations • 23 Nov 2022 • Rohit Gupta, Naveed Akhtar, Gaurav Kumar Nayak, Ajmal Mian, Mubarak Shah
By using a nearly disjoint dataset to train the substitute model, our method removes the requirement that the substitute model be trained using the same dataset as the target model, and leverages queries to the target model to retain the fooling rate benefits provided by query-based methods.
no code implementations • 1 Nov 2022 • Jyoti Kini, Ajmal Mian, Mubarak Shah
We propose a method for joint detection and tracking of multiple objects in 3D point clouds, a task conventionally treated as a two-step process comprising object detection followed by data association.
no code implementations • 6 Oct 2022 • Zainy M. Malakan, Ghulam Mubashar Hassan, Ajmal Mian
Visual Story-Telling is the process of forming a multi-sentence story from a set of images.
Ranked #25 on Visual Storytelling on VIST
no code implementations • 13 Sep 2022 • Anwaar Ulhaq, Naveed Akhtar, Ganna Pogrebna, Ajmal Mian
Finally, it provides a discussion on the challenges, outlook, and future avenues for this research direction.
no code implementations • 12 Aug 2022 • Zhengeng Yang, Hongshan Yu, Wei Sun, Li-Cheng, Ajmal Mian
In this paper, we present an easy-to-train framework that learns domain-invariant prototypes for domain adaptive semantic segmentation.
no code implementations • 22 Jul 2022 • Rohit Gupta, Naveed Akhtar, Ajmal Mian, Mubarak Shah
We establish that this is a result of the presence of false negative pairs in the training process, which increases model sensitivity to input perturbations.
no code implementations • 21 Jul 2022 • Bo Miao, Mohammed Bennamoun, Yongsheng Gao, Ajmal Mian
Current semi-supervised video object segmentation (VOS) methods usually leverage the entire features of one frame to predict object masks and update memory.
Ranked #16 on Semi-Supervised Video Object Segmentation on DAVIS 2017 (val) (using extra training data)
1 code implementation • 28 Apr 2022 • Mingtao Feng, Kendong Liu, Liang Zhang, Hongshan Yu, Yaonan Wang, Ajmal Mian
Saliency detection with light field images is becoming attractive given the abundant cues available, however, this comes at the expense of large-scale pixel level annotated data which is expensive to generate.
no code implementations • 16 Apr 2022 • Mohammed Hassanin, Saeed Anwar, Ibrahim Radwan, Fahad S Khan, Ajmal Mian
Inspired by the human cognitive system, attention is a mechanism that imitates the human cognitive awareness about specific information, amplifying critical details to focus more on the essential aspects of data.
1 code implementation • CVPR 2022 • Nazmul Karim, Mamshad Nayeem Rizve, Nazanin Rahnavard, Ajmal Mian, Mubarak Shah
To combat label noise, recent state-of-the-art methods employ some sort of sample selection mechanism to select a possibly clean subset of data.
1 code implementation • 15 Feb 2022 • Jiachen Zhong, Junying Chen, Ajmal Mian
We also test DualConv for image detection on YOLO-V3.
no code implementations • 22 Jan 2022 • XiangYu Song, JianXin Li, Qi Lei, Wei Zhao, Yunliang Chen, Ajmal Mian
The goal of Knowledge Tracing (KT) is to estimate how well students have mastered a concept based on their historical learning of related exercises.
1 code implementation • CVPR 2022 • Mingtao Feng, Kendong Liu, Liang Zhang, Hongshan Yu, Yaonan Wang, Ajmal Mian
Saliency detection with light field images is becoming attractive given the abundant cues available, however, this comes at the expense of large-scale pixel level annotated data which is expensive to generate.
2 code implementations • 3 Dec 2021 • Huan Lei, Naveed Akhtar, Mubarak Shah, Ajmal Mian
In this paper, we propose a series of modular operations for effective geometric feature learning from 3D triangle meshes.
no code implementations • 1 Aug 2021 • Naveed Akhtar, Ajmal Mian, Navid Kardan, Mubarak Shah
In [2], we reviewed the contributions made by the computer vision community in adversarial attacks on deep learning (and their defenses) until the advent of year 2018.
1 code implementation • 1 Aug 2021 • Bo Miao, Liguang Zhou, Ajmal Mian, Tin Lun Lam, Yangsheng Xu
The final results in this work show that OTS successfully extracts object features and learns object relations from the segmentation network.
1 code implementation • 27 Jul 2021 • Bo Miao, Mohammed Bennamoun, Yongsheng Gao, Ajmal Mian
We propose a self-supervised spatio-temporal matching method, coined Motion-Aware Mask Propagation (MAMP), for video object segmentation.
no code implementations • 7 Jul 2021 • Nayyer Aafaq, Naveed Akhtar, Wei Liu, Mubarak Shah, Ajmal Mian
In contrast, we propose a GAN-based algorithm for crafting adversarial examples for neural image captioning that mimics the internal representation of the CNN such that the resulting deep features of the input image enable a controlled incorrect caption generation through the recurrent network.
1 code implementation • CVPR 2021 • Mohammad A. A. K. Jalwana, Naveed Akhtar, Mohammed Bennamoun, Ajmal Mian
Backpropagation image saliency aims at explaining model predictions by estimating model-centric importance of individual pixels in the input.
no code implementations • 20 Jun 2021 • Naveed Akhtar, Muhammad A. A. K. Jalwana, Mohammed Bennamoun, Ajmal Mian
Exploring this phenomenon further, we alter the `adversarial' objective of our attack to use it as a tool to `explain' deep visual representation.
1 code implementation • 13 Jun 2021 • Humza Naveed, Saeed Anwar, Munawar Hayat, Kashif Javed, Ajmal Mian
One such method is augmentation which introduces different types of corruption in the data to prevent the model from overfitting and to memorize patterns present in the data.
no code implementations • 3 Jun 2021 • Aakash Kumar, Jyoti Kini, Mubarak Shah, Ajmal Mian
In recent times, the scope of LIDAR (Light Detection and Ranging) sensor-based technology has spread across numerous fields.
no code implementations • 3 May 2021 • Camilo Pestana, Wei Liu, David Glance, Robyn Owens, Ajmal Mian
We discuss how we can exploit these insights to re-think, or avoid, some patterns that might contribute to, or degrade, the detectability of objects in the real-world.
1 code implementation • ICCV 2021 • Mingtao Feng, Zhen Li, Qi Li, Liang Zhang, Xiangdong Zhang, Guangming Zhu, HUI ZHANG, Yaonan Wang, Ajmal Mian
There are three main challenges in 3D object grounding: to find the main focus in the complex and diverse description; to understand the point cloud scene; and to locate the target object.
2 code implementations • CVPR 2021 • Huan Lei, Naveed Akhtar, Ajmal Mian
We present Picasso, a CUDA-based library comprising novel modules for deep learning over complex real-world 3D meshes.
no code implementations • 19 Mar 2021 • Ashkan Esmaeili, Marzieh Edraki, Nazanin Rahnavard, Mubarak Shah, Ajmal Mian
It is set forth that the proposed sparse perturbation is the most aligned sparse perturbation with the shortest path from the input sample to the decision boundary for some initial adversarial sample (the best sparse approximation of shortest path, likely to fool the model).
no code implementations • 9 Mar 2021 • Yong He, Hongshan Yu, Xiaoyan Liu, Zhengeng Yang, Wei Sun, Ajmal Mian
This paper fills the gap and provides a comprehensive survey of the recent progress made in deep learning based 3D segmentation.
no code implementations • 18 Dec 2020 • Zhengeng Yang, Hongshan Yu, Yong He, Zhi-Hong Mao, Ajmal Mian
By learning to solve a Jigsaw Puzzle problem with 25 patches and transferring the learned features to semantic segmentation task on Cityscapes dataset, we achieve a 5. 8 percentage point improvement over the baseline model that initialized from random values.
1 code implementation • 5 Nov 2020 • Camilo Pestana, Wei Liu, David Glance, Ajmal Mian
We propose three metrics to determine the proportion of robust images in a dataset and provide scoring to determine the dataset bias.
1 code implementation • 25 Aug 2020 • Saeed Anwar, Muhammad Tahir, Chongyi Li, Ajmal Mian, Fahad Shahbaz Khan, Abdul Wahab Muzaffar
Image colorization is the process of estimating RGB colors for grayscale images or video frames to improve their aesthetic and perceptual quality.
no code implementations • 22 Aug 2020 • Qiang Fu, Hongshan Yu, Xiaolong Wang, Zhengeng Yang, Hong Zhang, Ajmal Mian
ORB-SLAM2 \cite{orbslam2} is a benchmark method in this domain, however, it consumes significant time for computing descriptors that never get reused unless a frame is selected as a keyframe.
Robotics Computational Geometry I.4.0; I.4.9
3 code implementations • ECCV 2020 • Shi-Jie Sun, Naveed Akhtar, Xiang-Yu Song, HuanSheng Song, Ajmal Mian, Mubarak Shah
Deep learning-based Multiple Object Tracking (MOT) currently relies on off-the-shelf detectors for tracking-by-detection. This results in deep models that are detector biased and evaluations that are detector influenced.
no code implementations • 28 Jul 2020 • Xiao-Yu Zhang, Ajmal Mian, Rohit Gupta, Nazanin Rahnavard, Mubarak Shah
We also propose an anomaly detection method to identify the target class in a Trojaned network.
Ranked #1 on Adversarial Defense on TrojAI Round 1
1 code implementation • 16 Jul 2020 • Marzieh Edraki, Nazmul Karim, Nazanin Rahnavard, Ajmal Mian, Mubarak Shah
We propose a detector that is based on the analysis of the intrinsic DNN properties; that are affected due to the Trojaning process.
no code implementations • 26 Jun 2020 • Mohammad A. A. K. Jalwana, Naveed Akhtar, Mohammed Bennamoun, Ajmal Mian
On the other, deep learning has also been found vulnerable to adversarial attacks, which calls for new techniques to defend deep models against these attacks.
no code implementations • 11 Jun 2020 • Zijie Wu, Yaonan Wang, Qing Zhu, Jianxu Mao, Haotian Wu, Mingtao Feng, Ajmal Mian
Different from the most existing point set registration methods which usually extract the descriptors to find correspondences between point sets, our proposed MPE alignment method is able to handle large scale raw data offset without depending on traditional descriptors extraction, whether for the local or global registration methods.
1 code implementation • 25 Feb 2020 • Camilo Pestana, Naveed Akhtar, Wei Liu, David Glance, Ajmal Mian
Our results show that our approach achieves the best balance between defence against adversarial attacks such as FGSM, PGD and DDN and maintaining the original accuracies of VGG-16, ResNet50 and DenseNet121 on clean images.
no code implementations • 30 Nov 2019 • Mingtao Feng, Syed Zulqarnain Gilani, Yaonan Wang, Liang Zhang, Ajmal Mian
Convolutional Neural Networks (CNNs) have emerged as a powerful strategy for most object detection tasks on 2D images.
no code implementations • 21 Nov 2019 • Nayyer Aafaq, Naveed Akhtar, Wei Liu, Ajmal Mian
We perform extensive experiments by varying the constituent components of the video captioning framework, and quantify the performance gains that are possible by mere component selection.
1 code implementation • 9 Oct 2019 • Muhammad Tahir, Saeed Anwar, Ajmal Mian, Abdul Wahab Muzaffar
This study highlights the importance of deep learning for the analysis of fluorescence microscopy protein imagery.
no code implementations • 27 Sep 2019 • Mingtao Feng, Liang Zhang, Xuefei Lin, Syed Zulqarnain Gilani, Ajmal Mian
We propose a point attention network that learns rich local shape features and their contextual correlations for 3D point cloud semantic segmentation.
3 code implementations • 20 Sep 2019 • Huan Lei, Naveed Akhtar, Ajmal Mian
We propose a spherical kernel for efficient graph convolution of 3D point clouds.
Ranked #5 on 3D Object Classification on ModelNet40
no code implementations • 14 Sep 2019 • Jian Liu, Naveed Akhtar, Ajmal Mian
We also explore the possibility of semantically imperceptible localized attacks with CIASA, and succeed in fooling the state-of-the-art skeleton action recognition models with high confidence.
no code implementations • 1 Jun 2019 • Jian Liu, Naveed Akhtar, Ajmal Mian
A major challenge in this regard is the lack of appropriately annotated video data for learning the desired deep models.
1 code implementation • 27 May 2019 • Naveed Akhtar, Mohammad A. A. K. Jalwana, Mohammed Bennamoun, Ajmal Mian
We introduce Label Universal Targeted Attack (LUTA) that makes a deep model predict a label of attacker's choice for `any' sample of a given source class with high probability.
no code implementations • 17 Apr 2019 • Zohaib Khan, Faisal Shafait, Ajmal Mian
We propose the construction of a prototype scanner designed to capture multispectral images of documents.
no code implementations • 18 Mar 2019 • William R. Johnson, Ajmal Mian, Mark A. Robinson, Jasper Verheul, David G. Lloyd, Jacqueline A. Alderson
Competing convolutional neural network (CNN) deep learning models were trained using laboratory-derived stance phase GRF/M data and simulated sensor accelerations for running and sidestepping maneuvers derived from nearly half a million legacy motion trials.
no code implementations • CVPR 2019 • Huan Lei, Naveed Akhtar, Ajmal Mian
We propose an octree guided neural network architecture and spherical convolutional kernel for machine learning from arbitrary 3D point clouds.
Ranked #10 on 3D Part Segmentation on ShapeNet-Part
no code implementations • CVPR 2019 • Nayyer Aafaq, Naveed Akhtar, Wei Liu, Syed Zulqarnain Gilani, Ajmal Mian
The final representation is projected to a compact space and fed to a language model.
1 code implementation • 28 Oct 2018 • Shi-Jie Sun, Naveed Akhtar, HuanSheng Song, Ajmal Mian, Mubarak Shah
In this paper, we harness the power of deep learning for data association in tracking by jointly modelling object appearances and their affinities between different frames in an end-to-end fashion.
no code implementations • 21 Sep 2018 • William R. Johnson, Ajmal Mian, David G. Lloyd, Jacqueline A. Alderson
In sports analytics, an understanding of accurate on-field 3D knee joint moments (KJM) could provide an early warning system for athlete workload exposure and knee injury risk.
no code implementations • 19 Jun 2018 • Xiang Yan, Syed Zulqarnain Gilani, Hanlin Qin, Ajmal Mian
Convolutional neural networks have recently been used for multi-focus image fusion.
no code implementations • 1 Jun 2018 • Nayyer Aafaq, Ajmal Mian, Wei Liu, Syed Zulqarnain Gilani, Mubarak Shah
Video description is the automatic generation of natural language sentences that describe the contents of a given video.
no code implementations • 21 May 2018 • Huan Lei, Naveed Akhtar, Ajmal Mian
We propose a neural network for 3D point cloud processing that exploits `spherical' convolution kernels and octree partitioning of space.
no code implementations • 26 Apr 2018 • Xiang Yan, Syed Zulqarnain Gilani, Hanlin Qin, Mingtao Feng, Liang Zhang, Ajmal Mian
Detecting representative frames in videos based on human actions is quite challenging because of the combined factors of human pose in action and the background.
1 code implementation • 12 Apr 2018 • Shi-Jie Sun, Naveed Akhtar, HuanSheng Song, Chaoyang Zhang, Jian-Xin Li, Ajmal Mian
A thorough evaluation on PCDS demonstrates that our technique is able to count people in cluttered scenes with high accuracy at 45 fps on a 1. 7 GHz processor, and hence it can be deployed for effective real-time people counting for intelligent transportation systems.
no code implementations • 15 Jan 2018 • Naveed Akhtar, Ajmal Mian
We propose to recover spectral details from RGB images of known spectral quantization by modeling natural spectra under Gaussian Processes and combining them with the RGB images.
3 code implementations • 2 Jan 2018 • Naveed Akhtar, Ajmal Mian
This article presents the first comprehensive survey on adversarial attacks on deep learning in Computer Vision.
no code implementations • CVPR 2018 • Naveed Akhtar, Jian Liu, Ajmal Mian
A rigorous evaluation shows that our framework can defend the network classifiers against unseen adversarial perturbations in the real-world scenarios with up to 97. 5% success rate.
no code implementations • ECCV 2018 • Mingtao Feng, Syed Zulqarnain Gilani, Yaonan Wang, Ajmal Mian
Reconstructing 3D facial geometry from a single RGB image has recently instigated wide research interest.
no code implementations • 16 Nov 2017 • Jian Liu, Naveed Akhtar, Ajmal Mian
The proposed action recognition exploits the representation in a hierarchical manner by first capturing the micro-temporal relations between the skeleton joints with the Skepxels and then exploiting their macro-temporal relations by computing the Fourier Temporal Pyramids over the CNN features of the skeletal images.
1 code implementation • CVPR 2018 • Syed Zulqarnain Gilani, Ajmal Mian
Unlike 2D photographs, 3D facial scans cannot be sourced from the web causing a bottleneck in the development of deep 3D face recognition networks and datasets.
no code implementations • 15 Sep 2017 • Jian Liu, Naveed Akhtar, Ajmal Mian
The proposed technique capitalizes on the spatio-temporal information available in the two data streams to the extract action features that are largely insensitive to the viewpoint variations.
no code implementations • 4 Jul 2017 • Jian Liu, Naveed Akhtar, Ajmal Mian
We propose Human Pose Models that represent RGB and depth images of human poses independent of clothing textures, backgrounds, lighting conditions, body shapes and camera viewpoints.
Ranked #94 on Skeleton Based Action Recognition on NTU RGB+D
no code implementations • CVPR 2017 • Hasan F. M. Zaki, Faisal Shafait, Ajmal Mian
We compare our method to state-of-the-art first person and generic video recognition algorithms.
no code implementations • CVPR 2017 • Naveed Akhtar, Ajmal Mian, Fatih Porikli
To further encourage discrimination in the dictionary, our model uses separate (sets of) Bernoulli distributions to represent data from different classes.
no code implementations • CVPR 2016 • Hossein Rahmani, Ajmal Mian
We propose a human pose representation model that transfers human poses acquired from different unknown views to a view-invariant high-level space.
no code implementations • 2 Feb 2016 • Hossein Rahmani, Ajmal Mian, Mubarak Shah
The strength of our technique is that we learn a single R-NKTM for all actions and all viewpoints for knowledge transfer of any real human action video without the need for re-training or fine-tuning the model.
no code implementations • 29 Nov 2015 • Naveed Akhtar, Faisal Shafait, Ajmal Mian
Many classification approaches first represent a test sample using the training samples of all the classes.
no code implementations • CVPR 2015 • Hossein Rahmani, Ajmal Mian
We propose unsupervised learning of a non-linear model that transfers knowledge from multiple views to a canonical view.
no code implementations • CVPR 2015 • Syed Zulqarnain Gilani, Faisal Shafait, Ajmal Mian
Our approach does not use texture and is completely shape based in order to detect landmarks that are morphologically significant.
no code implementations • CVPR 2015 • Naveed Akhtar, Faisal Shafait, Ajmal Mian
We propose a hyperspectral image super resolution approach that fuses a high resolution image with the low resolution hyperspectral image using non-parametric Bayesian sparse representation.
no code implementations • 27 Mar 2015 • Naveed Akhtar, Faisal Shafait, Ajmal Mian
We propose a Bayesian approach to learn discriminative dictionaries for sparse representation of data.
no code implementations • 9 Mar 2015 • Muhammad Uzair, Faisal Shafait, Bernard Ghanem, Ajmal Mian
Efficient and accurate joint representation of a collection of images, that belong to the same class, is a major research challenge for practical image set classification.
no code implementations • 19 Oct 2014 • Syed Zulqarnain Gilani, Ajmal Mian, Faisal Shafait, Ian Reid
A deformable model (K3DM) is constructed from the dense corresponded faces and an algorithm is proposed for morphing the K3DM to fit unseen faces.
no code implementations • 24 Sep 2014 • Hossein Rahmani, Arif Mahmood, Du Huynh, Ajmal Mian
We propose the Histogram of Oriented Principal Components (HOPC) descriptor that is robust to noise, viewpoint, scale and action speed variations.
no code implementations • 17 Aug 2014 • Hossein Rahmani, Arif Mahmood, Du. Q. Huynh, Ajmal Mian
In contrast, we directly process the pointclouds and propose a new technique for action recognition which is more robust to noise, action speed and viewpoint variations.
no code implementations • 17 Aug 2014 • Hossein Rahmani, Arif Mahmood, Du Huynh, Ajmal Mian
We use the Histogram of Oriented Gradient (HOG3D) feature to encode the information in each cell.
no code implementations • 14 Jul 2014 • Arif Mahmood, Ajmal Mian, Robyn Owens
To this end we propose an Efficient Group Size (EGS) algorithm which minimizes the number of similarity computations for a particular search image.
no code implementations • CVPR 2014 • Arif Mahmood, Ajmal Mian, Robyn Owens
We present an image set classification algorithm based on unsupervised clustering of labeled training and unlabeled test data where labels are only used in the stopping criterion.
no code implementations • 6 Feb 2014 • Zohaib Khan, Faisal Shafait, Yiqun Hu, Ajmal Mian
Comprehensive experiments for both identification and verification scenarios are performed on two public datasets -- one captured with a contact-based sensor (PolyU dataset), and the other with a contact-free sensor (CASIA dataset).