Mubarak Shah

@conference{nokey,

title = {Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detection},

author = {Nicolae-Catalin Ristea and Neelu Madan and Radu Tudor Ionescu and Kamal Nasrollahi and Fahad Shahbaz Khan and Thomas B. Moeslund and Mubarak Shah},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/SSPCAB_camera-arxiv.pdf},

year  = {2022},

date = {2022-06-19},

urldate = {2022-06-19},

publisher = {IEEE Computer Vision and Pattern Recognition},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{nokey,

title = {TransGeo: Transformer Is All You Need for Cross-view Image Geo-localization},

author = {Sijie Zhu and Mubarak Shah and Chen Chen},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/11695.pdf

https://www.crcv.ucf.edu/wp-content/uploads/2018/11/11695-supp.pdf},

year  = {2022},

date = {2022-06-19},

urldate = {2022-06-19},

publisher = {IEEE Computer Vision and Pattern Recognition},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{nokey,

title = {PSTR: End-to-End One-Step Person Search With Transformers},

author = {Jiale Cao and Yenwai Pang and Rao Muhammad Anwer and Hisham Cholakkal and Jin Xie and Mubarak Shah and Fahad Shahbaz Khan},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/05237-2.pdf

https://github.com/JialeCao001/PSTR},

year  = {2022},

date = {2022-06-19},

urldate = {2022-06-19},

publisher = {IEEE Computer Vision and Pattern Recognition},

abstract = {We propose a novel one-step transformer-based person search framework, PSTR, that jointly performs person detection and re-identification (re-id) in a single architecture. PSTR comprises a person search-specialized (PSS) module that contains a detection encoder-decoder for person detection along with a discriminative re-id decoder for person re-id. The discriminative re-id decoder utilizes a multi-level supervision scheme with a shared decoder for

discriminative re-id feature learning and also comprises a part attention block to encode relationship between different parts of a person. We further introduce a simple multi-scale scheme to support re-id across person instances at different scales. PSTR jointly achieves the diverse objectives of object-level recognition (detection) and instance-level matching (re-id). To the best of our knowledge, we are the first to propose an end-to-end one-step

transformer-based person search framework. Experiments are performed on two popular benchmarks: CUHK-SYSU and PRW. Our extensive ablations reveal the merits of the proposed contributions. Further, the proposed PSTR sets a new state-of-the-art on both benchmarks. On the challenging

PRW benchmark, PSTR achieves a mean average precision (mAP) score of 56.5%. The source code is available at https://github.com/JialeCao001/PSTR.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{nokey,

title = {OW-DETR: Open-world Detection Transformer},

author = {Akshita Gupta and Sanath Narayan and K J Joseph and Salman Khan and Fahad Shahbaz Khan and Mubarak Shah},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/03815.pdf

https://www.crcv.ucf.edu/wp-content/uploads/2018/11/03815-supp.pdf

https://github.com/akshitac8/OW-DETR.},

year  = {2022},

date = {2022-06-19},

urldate = {2022-06-19},

publisher = {IEEE Computer Vision and Pattern Recognition},

abstract = {Open-world object detection (OWOD) is a challenging computer vision problem, where the task is to detect a known set of object categories while  simultaneously identifying unknown objects. Additionally, the model must incrementally learn new classes that become known in the next training episodes. Distinct from standard object detection, the OWOD setting poses significant challenges for generating quality candidate proposals on potentially unknown objects, separating the unknown objects from the background and detecting diverse unknown objects. Here, we introduce a novel end-to-end transformer-based framework, OW-DETR, for open-world object detection. The proposed OW-DETR comprises three dedicated components

namely, attention-driven pseudo-labeling, novelty classification and objectness scoring to explicitly address the aforementioned OWOD challenges. Our OW-DETR explicitly encodes multi-scale contextual information, possesses less inductive bias, enables knowledge transfer from known classes to the unknown class and can better discriminate between unknown objects and background. Comprehensive experiments are performed on two benchmarks: MS-COCO and PASCAL VOC. The extensive ablations reveal the merits of our proposed contributions. Further, our model outperforms the recently introduced OWOD approach, ORE, with absolute gains ranging from 1.8% to 3.3% in terms of unknown recall on MS-COCO. In the case of incremental

object detection, OW-DETR outperforms the state-of-the art for all settings on PASCAL VOC. Our code is available at https://github.com/akshitac8/OW-DETR.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{nokey,

title = {SPAct: Self-supervised Privacy Preservation for Action Recognition},

author = {Ishan Rajendrakumar Dave and Chen Chen and Mubarak Shah},

url = {https://arxiv.org/pdf/2203.15205.pdf

https://github.com/DAVEISHAN/SPAct},

year  = {2022},

date = {2022-06-19},

urldate = {2022-06-19},

publisher = {IEEE Computer Vision and Pattern Recognition},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{nokey,

title = {UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detection},

author = {Andra Acsintoae and Andrei Florescu and Mariana-Iuliana Georgescu and Tudor Mare and Paul Sumedrea and Radu Tudor Ionescu and Fahad Shahbaz Khan and Mubarak Shah},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/04315.pdf

https://github.com/lilygeorgescu/UBnormal},

year  = {2022},

date = {2022-06-19},

urldate = {2022-06-19},

publisher = {IEEE Computer Vision and Pattern Recognition},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{nokey,

title = {UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learning},

author = {Nazmul Karim and Mamshad Nayeem Rizve and Nazanin Rahnavard and Ajmal Mian and Mubarak Shah},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/07363.pdf

https://www.crcv.ucf.edu/wp-content/uploads/2018/11/07363-supp.pdf

https://github.com/nazmul-karim170/unicon-noisy-label},

year  = {2022},

date = {2022-06-19},

urldate = {2022-06-19},

publisher = {IEEE Computer Vision and Pattern Recognition},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Modi2022,

title = {Video Action Detection: Analysing Limitations and Challenges},

author = {Rajat Modi and Aayush Jung Rana and Akash Kumar and Praveen Tirupattur and Shruti Vyas and Yogesh Singh Rawat and Mubarak Shah},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/2204.07892.pdf},

year  = {2022},

date = {2022-04-17},

urldate = {2022-04-17},

publisher = {IEEE Computer Vision and Pattern Recognition},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Pestana2022,

title = {Transferable 3D Adversarial Textures using End-to-end Optimization},

author = {Camilo Pestana and Naveed Akhtar and Nazanin Rahnavard and Mubarak Shah and Ajmal Mian},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/WACV_2022_Deceptive_Textures-1.pdf},

doi = {10.1109/WACV51458.2022.00080},

year  = {2022},

date = {2022-02-15},

urldate = {2022-02-15},

pages = {727-736},

publisher = {IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},

abstract = {Deep visual models are known to be vulnerable to adversarial attacks. The last few years have seen numerous techniques to compute adversarial inputs for these models. However, there are still under-explored avenues in this critical research direction. Among those is the estimation of adversarial textures for 3D models in an end-to-end optimization scheme. In this paper, we propose such a scheme to generate adversarial textures for 3D models that are highly transferable and invariant to different camera views and lighting conditions. Our method makes use of neural rendering with explicit control over the model texture and background. We ensure transferability of the adversarial textures by employing an ensemble of robust and non-robust models. Our technique utilizes 3D models as a proxy to simulate closer to real-life conditions, in contrast to conventional use of 2D images for adversarial attacks. We show the efficacy of our method with extensive experiments.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Kardan2022,

title = {Self-Joint Supervised Learning},

author = {Navid Kardan and Mitchell Hill and Mubarak Shah},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/Self_joint_ICLR-002.pdf

https://github.com/ndkn/Self-joint-Learning},

year  = {2022},

date = {2022-01-20},

urldate = {2022-01-20},

publisher = {International Conference on Learning Representations (ICLR)},

abstract = {Supervised learning is a fundamental framework used to train machine learning systems. A supervised learning problem is often formulated using an i.i.d. as-sumption that restricts model attention to a single relevant signal at a time when predicting. This contrasts with the human ability to actively use related samples as reference when making decisions. We hypothesize that the restriction to a single signal for each prediction in the standard i.i.d. framework contributes to well-known drawbacks of supervised learning: making overconfident predictions and vulnerability to overfitting, adversarial attacks, and out-of-distribution data. To address these limitations, we propose a new supervised learning paradigm called self-joint learning that generalizes the standard approach by modeling the joint conditional distribution of two observed samples, where each sample is an im-age and its label. Rather than assuming samples are independent, our models explicitly learn the sample-to-sample relation of conditional independence. Our framework can naturally incorporate auxiliary unlabeled data to further improve the performance. Experiments on benchmark image datasets show our method offers significant improvement over standard supervised learning in terms of ac-curacy, robustness against adversarial attacks, out-of-distribution detection, and overconfidence mitigation. Code: github.com/ndkn/Self-joint-Learning},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Kerrigan2021,

title = {Reformulating Zero-shot Action Recognition for Multi-label Actions},

author = {Alec Kerrigan and Kevin Duarte and Yogesh Singh Rawat and Mubarak Shah},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/reformulating_zero_shot_action2.pdf

https://www.crcv.ucf.edu/wp-content/uploads/2018/11/ZSL-Supp.pdf

https://www.crcv.ucf.edu/wp-content/uploads/2018/11/Reformulating-Zero-shot-Action-Recognition-forMulti-label-Actions.pptx},

year  = {2021},

date = {2021-12-06},

urldate = {2021-12-06},

booktitle = {Thirty-fifth Conference on Neural Information Processing Systems},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Rajasegaran2020,

title = {Self-supervised Knowledge Distillation for Few-shot Learning},

author = {Jathushan Rajasegaran and Salman Khan and Munawar Hayat and Fahad Shahbaz Khan and Mubarak Shah},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2020/07/Publications_Self-supervised-Knowledge-Distillation-for-Few-shot-Learning.pdf

https://bmvc2021-virtualconference.com/conference/papers/paper_0820.html

https://github.com/brjathu/SKD},

year  = {2021},

date = {2021-11-22},

urldate = {2021-11-22},

booktitle = {British Machine Vision Conference, Nov 22-25},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Rajasegaran2021,

title = {Meta-learning the Learning Trends Shared Across Tasks},

author = {Jathushan Rajasegaran and Salman Khan and Munawar Hayat and Fahad Shahbaz Khan and Mubarak Shah},

url = {https://www.bmvc2021-virtualconference.com/conference/papers/paper_0874.html},

year  = {2021},

date = {2021-11-22},

urldate = {2021-11-22},

booktitle = {British Machine Vision Conference, Nov 22-25},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{NarayanICCV2021,

title = {Discriminative Region-based Multi-Label Zero-Shot Learning},

author = {Sanath Narayan and Akshita Gupta and Salman Khan and Fahad Shahbaz Khan and Ling Shao and Mubarak Shah},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/02617.pdf

https://www.crcv.ucf.edu/wp-content/uploads/2018/11/02617-supp.pdf},

year  = {2021},

date = {2021-10-11},

urldate = {2021-10-11},

booktitle = {International Conference on Computer Vision},

abstract = {Multi-label zero-shot learning (ZSL) is a more realistic counter-part of standard single-label ZSL since several objects can co-exist in a natural image.  However, the occurrence of multiple objects complicates the reasoning and re-quires region-specific processing of visual features to pre-serve their contextual cues.  We note that the best existing multi-label ZSL method takes a shared approach towards attending  to  region  features  with  a  common  set  of  attention  maps  for  all  the  classes.   Such  shared  maps  lead  to diffused attention, which does not discriminatively focus on relevant  locations  when  the  number  of  classes  are  large. Moreover, mapping spatially-pooled visual features to the class semantics leads to  inter-class  feature entanglement, thus  hampering  the  classification.   Here,  we  propose  an alternate approach towards region-based discriminability-preserving  multi-label  zero-shot  classification. Our  approach maintains the spatial resolution to preserve region-level characteristics and utilizes a bi-level attention module (BiAM) to enrich the features by incorporating both region and scene context information.   The enriched region-level features are then mapped to the class semantics and only their class predictions are spatially pooled to obtain image-level predictions,  thereby keeping the multi-class features

disentangled.  Our approach sets a new state of the art on two  large-scale  multi-label  zero-shot  benchmarks:   NUS-WIDE  and  Open  Images.   On  NUS-WIDE,  our  approach achieves an absolute gain of 6.9% mAP for ZSL, compared to the best published results.   Source code is available at https://github.com/akshitac8/BiAM.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{ZaeemzadehICCV2021,

title = {Face Image Retrieval with Attribute Manipulation},

author = {Alireza Zaeemzadeh and Shabnam Ghadar and Baldo Faieta and Zhe Lin and Nazanin Rahnavard and Mubarak Shah and Ratheesh Kalarot},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/06328.pdf

https://www.crcv.ucf.edu/wp-content/uploads/2018/11/06328-supp.pdf},

year  = {2021},

date = {2021-10-11},

urldate = {2021-10-11},

booktitle = {International Conference on Computer Vision},

abstract = {Current face image retrieval solutions are limited, since they treat different facial attributes the same and cannot incorporate

user’s preference for a subset of attributes in their search criteria. This paper introduces a new face image retrieval framework, where the input face query is augmented by both an adjustment vector that specifies the desired modifications

to the facial attributes, and a preference vector that assigns different levels of importance to different attributes. For example, a user can ask for retrieving images similar to a query image, but with a different hair color, and no preference for absence/presence of eyeglasses in the results. To achieve this, we propose to disentangle the semantics, corresponding to various attributes, by learning a set of sparse and orthogonal basis vectors in the latent space of StyleGAN. Such basis vectors are then employed to decompose the dissimilarity between face images in terms of dissimilarity between their attributes, assign preference to the attributes, and adjust the attributes in the query. Enforcing sparsity on the basis vectors helps us to disentangle the latent space and adjust each attribute independently from other attributes, while enforcing orthogonality facilitates preference assignment and the dissimilarity decomposition. The effectiveness of our approach is illustrated by achieving state-of-the-art results for the face image retrieval task. },

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{BhuniaICCV2021,

title = {Handwriting Transformers},

author = {Ankan Kumar Bhunia and Salman Khan and Hisham Cholakkal and Rao Muhammad Anwer and Fahad Shahbaz Khan and Mubarak Shah},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/Handwriting_Generation_ICCV21.pdf

https://www.crcv.ucf.edu/wp-content/uploads/2018/11/Handwriting_Generation_ICCV21_supp.pdf},

year  = {2021},

date = {2021-10-11},

urldate = {2021-10-11},

booktitle = {International Conference on Computer Vision},

abstract = {We propose a novel transformer-based styled handwritten text image generation approach, HWT, that strives to learn both style-content entanglement as well as global and local writing style patterns. The proposed HWT captures the long and short range relationships within the style examples through a self-attention mechanism, thereby encoding both global and local style patterns. Further, the proposed transformer-based HWT comprises an encoder-decoder attention that enables style-content entanglement by gathering the style representation of each query character. To the best of our knowledge, we are the first to introduce a transformer-based generative network for styled handwritten text generation.



Our proposed HWT generates realistic styled handwritten text images and significantly outperforms the state-of-the-art demonstrated through extensive qualitative, quantitative and human-based evaluations. The proposed HWT can handle arbitrary length of text and any desired writing style in a few-shot setting. Further, our HWT generalizes well to the challenging scenario where both words and writing style are unseen during training, generating realistic styled handwritten text images.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{RegmiICCV2021,

title = {Video Geo-Localization Employing Geo-Temporal Feature Learning and GPS Trajectory Smoothing},

author = {Krishna Regmi and Mubarak Shah},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/video_geolocalization_ICCV2021.pdf

https://github.com/kregmi/VTE},

year  = {2021},

date = {2021-10-11},

urldate = {2021-10-11},

booktitle = {International Conference on Computer Vision},

abstract = {In this paper, we address the problem of video geolocalization by proposing a Geo-Temporal Feature Learning (GTFL) Network to simultaneously learn the discriminative features for the query video frames and the gallery images for estimating the geo-spatial trajectory of a query video. Based on a transformer encoder architecture, our

GTFL model encodes query and gallery data separately, via two dedicated branches. The proposed GPS Loss and Clip Triplet Loss exploit the geographical and temporal proximity between the frames and the clips to jointly learn the query and the gallery features. We also propose a deep learning approach to trajectory smoothing by predicting the outliers in the estimated GPS positions and learning the offsets to smooth the trajectory. We build a large dataset from four different regions of USA; New York, San Francisco, Berkeley and Bay Area using BDD driving videos as query, and by collecting corresponding Google StreetView (GSV) Images for gallery. Extensive

evaluations of proposed method on this new dataset are provided. Code and dataset details is publicly available at

https://github.com/kregmi/VTE.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Shiraz2021,

title = {Novel View Video Prediction using Dual Representation},

author = {Sarah Shiraz and Krishna Regmi and Shruti Vyas and Yogesh Singh Rawat and Mubarak Shah

},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/Projects_Novel-View-Video-Prediction-using-dual-Representation.pdf

https://www.crcv.ucf.edu/research/projects/novel-view-video-prediction-using-dual-representation/},

year  = {2021},

date = {2021-09-19},

urldate = {2021-09-19},

booktitle = {IEEE International Conference on Image Processing},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Swetha2021,

title = {Unsupervised Discriminative Embedding for Sub-Action Learning in Complex Activities},

author = {Sirnam Swetha and Hilde Kuehne and Yogesh Singh Rawat and Mubarak Shah },

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/Unsupervised-Discriminative-Embedding-for-Sub-Action-Learning-in-Complex-Activities.pdf},

year  = {2021},

date = {2021-09-19},

urldate = {2021-09-19},

booktitle = {IEEE International Conference on Image Processing},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Tirupattur2021,

title = {Modeling Multi-Label Action Dependencies for Temporal Action Localization},

author = {Praveen Tirupattur and Kevin Duarte and Yogesh Singh Rawat and Mubarak Shah},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/Modeling-Multi-Label-Action-Dependencies-for-Temporal-Action-Localization.pdf

https://www.crcv.ucf.edu/wp-content/uploads/2018/11/Modeling-Multi-Label-Action-Dependencies-for-Temporal-Action-Localization_Supp.zip

https://www.crcv.ucf.edu/wp-content/uploads/2018/11/Modeling-Multi-Label-Action-Dependencies-for-Temporal-Action-Localization-CVPR-2021-ORAL.mp4},

year  = {2021},

date = {2021-06-19},

urldate = {2021-06-19},

publisher = {IEEE Conference on Computer Vision and Pattern Recognition (Oral)},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Zaeemzadeh2021,

title = {Out-of-Distribution Detection Using Union of 1-Dimensional Subspaces},

author = {Alireza Zaeemzadeh and Niccolò Bisagno and Zeno Sambugaro and Nicola Conci and Nazanin Rahnavard and Mubarak Shah},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/Out-of-Distribution-Detection-Using-Union-of-1-Dimensional-Subspaces.pdf

https://www.crcv.ucf.edu/wp-content/uploads/2018/11/Out-of-Distribution-Detection-Using-Union-of-1-Dimensional-Subspaces_Supp.pdf

https://www.crcv.ucf.edu/wp-content/uploads/2018/11/CVPR21_presentation_video.mov},

year  = {2021},

date = {2021-06-19},

urldate = {2021-06-19},

publisher = {IEEE Conference on Computer Vision and Pattern Recognition},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Khan2021b,

title = {Found a Reason for me? Weakly-supervised Grounded Visual Question Answering using Capsules},

author = {Aisha Urooj Khan and Hilde Kuehne and Kevin Duarte and Chuang Gan and Niels Da Vitoria Lobo and Mubarak Shah},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/Found-a-Reason-for-me.pdf

https://www.crcv.ucf.edu/wp-content/uploads/2018/11/Found-a-Reason-for-me_Supp.pdf

https://www.crcv.ucf.edu/wp-content/uploads/2018/11/cvpr21_poster_v2.pdf

https://www.crcv.ucf.edu/wp-content/uploads/2018/11/cvpr_2021_5min.mp4},

year  = {2021},

date = {2021-06-19},

urldate = {2021-06-19},

publisher = {IEEE Conference on Computer Vision and Pattern Recognition},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{georgescu2020anomaly,

title = {Anomaly Detection in Video via Self-Supervised and Multi-Task Learning},

author = {Mariana Iuliana Georgescu and Antonio Bărbălău and Radu Tudor Ionescu and Fahad Shahbaz Khan and Marius Popescu and Mubarak Shah},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/Publications_Anomaly-Detection-in-Video-via-Self-Supervised-and-Multi-Task-Learning.pdf

https://www.crcv.ucf.edu/wp-content/uploads/2018/11/Publications_Anomaly-Detection-in-Video-via-Self-Supervised-and-Multi-Task-Learning_Supp.pdf

https://www.crcv.ucf.edu/wp-content/uploads/2018/11/Anomaly-Detection-in-Video-via-Self-Supervised-and-Multi-Task-Learning.pptx

https://www.crcv.ucf.edu/wp-content/uploads/2018/11/Anomaly-Detection-in-Video-via-Self-Supervised-and-Multi-Task-Learning.mp4},

year  = {2021},

date = {2021-06-19},

urldate = {2021-06-19},

publisher = {IEEE Conference on Computer Vision and Pattern Recognition},

abstract = {Anomaly detection in video is a challenging computer vision problem. Due to the lack of anomalous events at training time, anomaly detection requires the design of learning methods without full supervision. In this paper, we approach anomalous event detection in video through self-supervised and multi-task learning at the object level. We first utilize a pre-trained detector to detect objects. Then, we train a 3D convolutional neural network to produce discriminative anomaly-specific information by jointly learning multiple proxy tasks: three self-supervised and one based on knowledge distillation. The self-supervised tasks are: (i) discrimination of forward/backward moving objects (arrow of time), (ii) discrimination of objects in consecutive/intermittent frames (motion irregularity) and (iii) reconstruction of object-specific appearance information. The knowledge distillation task takes into account both classification and detection information, generating large prediction discrepancies between teacher and student models when anomalies occur. To the best of our knowledge, we are the first to approach anomalous event detection in video as a multi-task learning problem, integrating multiple self-supervised and knowledge distillation proxy tasks in a single architecture. Our lightweight architecture outperforms the state-of-the-art methods on three benchmarks: Avenue, ShanghaiTech and UCSD Ped2. Additionally, we perform an ablation study demonstrating the importance of integrating self-supervised learning and normality-specific distillation in a multi-task learning setting.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Rizve2021b,

title = {Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning},

author = {Mamshad Nayeem Rizve and Salman Khan and Fahad Shahbaz Khan and Mubarak Shah},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/Exploring-Complementary-Strengths-of-Invariant-and-Equivariant.pdf

https://www.crcv.ucf.edu/wp-content/uploads/2018/11/Exploring-Complementary-Strengths-of-Invariant-and-Equivariant_Supp.pdf

https://github.com/nayeemrizve/invariance-equivariance

https://www.crcv.ucf.edu/wp-content/uploads/2018/11/FSL_CVPR2021_Video_Final.mp4},

year  = {2021},

date = {2021-06-19},

urldate = {2021-06-19},

publisher = {IEEE Conference on Computer Vision and Pattern Recognition},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Sultani2021,

title = {Dogfight: Detecting Drones from Drones Videos },

author = {Muhammad Waseem Ashraf and Waqas Sultani and Mubarak Shah},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/Dogfight.pdf

https://www.crcv.ucf.edu/wp-content/uploads/2018/11/Dogfight_Supp.mp4

https://github.com/mwaseema/Drone-Detection

http://im.itu.edu.pk/dogfight-detecting-drones-from-drones-videos/

https://docs.google.com/presentation/d/1huBSbYzyNUCs-gJHdSU2CZ0XfRlBWGOQ/edit#slide=id.p1},

year  = {2021},

date = {2021-06-19},

urldate = {2021-06-19},

publisher = {IEEE Conference on Computer Vision and Pattern Recognition},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Rizve2021,

title = {In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning},

author = {Mamshad Nayeem Rizve and Kevin Duarte and Yogesh Singh Rawat and Mubarak Shah },

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/In-Defense-Of-Pseudo-Labeling.pdf

https://github.com/nayeemrizve/ups

https://www.crcv.ucf.edu/wp-content/uploads/2018/11/UPS_ICLR2021_Slides.pdf

https://www.crcv.ucf.edu/wp-content/uploads/2018/11/UPS_ICLR2021_Slides.pptx

https://www.crcv.ucf.edu/wp-content/uploads/2018/11/UPS_Poster_ICLR2021.png},

year  = {2021},

date = {2021-05-04},

urldate = {2021-05-04},

booktitle = {Ninth International Conference on Learning Representations (ICLR)},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Khan2020b,

title = {MMFT-BERT: Multimodal Fusion Transformer with BERT Encodings for Visual Question Answering},

author = {Aisha Urooj Khan and Amir Mazaheri and Niels da Vitoria Lobo and Mubarak Shah},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/Publications_MMFT-BERT.pdf},

year  = {2020},

date = {2020-11-16},

booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Findings, EMNLP},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Vyas2020,

title = {Multi-view Action Recognition using Cross-view Video Prediction},

author = {Shruti Vyas and Yogesh Singh Rawat and Mubarak Shah},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2020/07/Projects_Multi-view-Action-Recognition-using-Cross-view-Video-Prediction.pdf

https://www.crcv.ucf.edu/wp-content/uploads/2020/07/Projects_Multi-view-Action-Recognition-using-Cross-view-Video-Prediction_Supp.pdf

https://www.crcv.ucf.edu/research/projects/multi-view-action-recognition-using-cross-view-video-prediction/},

year  = {2020},

date = {2020-08-23},

booktitle = {16th European Conference on Computer Vision},

abstract = {In this work, we address the problem of action recognition in a multi-view environment. Most of the existing approaches utilize  pose information for multi-view action recognition. We focus on RGB modality instead and propose an unsupervised representation learning framework, which encodes the scene dynamics in videos captured from multiple viewpoints via predicting actions from unseen views. The framework takes multiple short video clips from different viewpoints and time as input and learns an holistic internal representation which is used to predict a video clip from an unseen viewpoint and time. The ability of the proposed network to render unseen video frames enables it to learn a meaningful and robust representation of the scene dynamics. We evaluate the effectiveness of the learned representation for multiview video action recognition in a supervised approach. We observe a significant improvement in the performance with RGB modality on NTU-RGB+D dataset, which is the largest dataset for multi-view action recognition. The proposed framework also achieves state-of-the-art results with depth modality, which validates the generalization capability of the approach to other data modalities. The code is publicly available at https://github.com/svyas23/cross-view-action.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Sun2020,

title = {Simultaneous Detection and Tracking with Motion Modelling for Multiple Object Tracking},

author = {ShiJie Sun and Naveed Akhtar and XiangYu Song and HuanSheng Song and Ajmal Mian and Mubarak Shah},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2020/07/Publications_Simultaneous-Detection-and-Tracking-with-Motion-Modelling-for-Multiple-Object-Tracking.pdf

https://www.crcv.ucf.edu/wp-content/uploads/2020/07/Publications_Simultaneous-Detection-and-Tracking-with-Motion-Modelling-for-Multiple-Object-Tracking_Supp.pdf

https://shijies.github.io/DMMN_Page/},

year  = {2020},

date = {2020-08-23},

booktitle = {16th European Conference on Computer Vision},

abstract = {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. To resolve this issue, we introduce Deep Motion Modeling Network (DMM-Net) that can estimate multiple objects’ motion parameters to perform joint detection and association in an end-to-end manner. DMM-Net models object features over multiple frames and simultaneously infers object classes, visibility and their motion parameters. These outputs are readily used to update the tracklets for efficient MOT. DMM-Net achieves PR-MOTA score of 12.80 @ 120+ fps for the popular UA-DETRAC challenge - which is better performance and orders of magnitude faster. We also contribute a synthetic large-scale public dataset Omni-MOT for vehicle tracking that provides precise ground-truth annotations to eliminate the detector influence in MOT evaluation. This 14M+ frames dataset is extendable with our public script (Code at Dataset, Dataset Recorder, Omni-MOT Source). We demonstrate the suitability of Omni-MOT for deep learning with DMM-Net, and also make the source code of our network public.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{Xie2020,

title = {Count- and Similarity-aware R-CNN for Pedestrian Detection},

author = {Jin Xie and Hisham Cholakkal and Rao Muhammad Anwer and Fahad Shahbaz Khan and Yanwei Pang and Ling Shao and Mubarak Shah},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2020/07/Publications_Count-and-Similarity-aware-R-CNN-for-Pedestrian-Detection.pdf},

year  = {2020},

date = {2020-08-23},

booktitle = {16th European Conference on Computer Vision},

abstract = {Recent pedestrian detection methods generally rely on additional supervision, such as visible bounding-box annotations, to handle heavy occlusions. We propose an approach that leverages pedestrian count and proposal similarity information within a two-stage pedestrian detection framework. Both pedestrian count and proposal similarity are derived from standard full-body annotations commonly used to train pedestrian detectors. We introduce a count-weighted detection loss function that assigns higher weights to the detection errors occurring at highly overlapping pedestrians. The proposed loss function is utilized at both stages of the two-stage detector. We further introduce a count-andsimilarity branch within the two-stage detection framework, which predicts pedestrian count as well as proposal similarity to identify distinct proposals. Our approach requires neither part information nor visible bounding-box annotations. Experiments are performed on the CityPersons and CrowdHuman datasets. Our method sets a new state-of-the-art on both datasets. Further, it achieves an absolute gain of 2.4% over the current state-of-the-art, in terms of log-average miss rate, on the heavily occluded (HO) set of CityPersons test set, without using additional visible bounding-box supervision. Finally, we demonstrate the applicability of our approach for the problem of human instance segmentation. Code and models are available at: https://github.com/Leotju/CaSe.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}