Search

To extract robust and generalizable skeleton action recognition features, large amounts of well-curated data are typically required, which is a challenging task hindered by annotation and computation costs. Therefore, unsupervised representation learning is of prime importance to leverage unlabeled skeleton data. In this work, we investigate unsupervised representation learning for skeleton action recognition. For this purpose, we designed a lightweight convolutional transformer framework, named ReL-SAR, exploiting the complementarity of convolutional and attention layers for jointly modeling spatial and temporal cues in skeleton sequences. We also use a Selection-Permutation strategy for skeleton joints to ensure more informative descriptions from skeletal data. Finally, we capitalize on Bootstrap Your Own Latent (BYOL) to learn robust representations from unlabeled skeleton sequence data. We achieved very competitive results on limited-size datasets: MCAD, IXMAS, JHMDB, and NW-UCLA, showing the effectiveness of our proposed method against state-of-the-art methods in terms of both performance and computational efficiency. To ensure reproducibility and reusability, the source code including all implementation parameters is provided at: https://github.com/SafwenNaimi/Representation-Learning-for-Skeleton-Action-Recognition-with-Convolutional-Transformers-and-BYOL, Comment: 8 pages, 4 figures, 6 tables

We propose a novel Transformer-based module to address the data association problem for multi-object tracking. From detections obtained by a pretrained detector, this module uses only coordinates from bounding boxes to estimate an affinity score between pairs of tracks extracted from two distinct temporal windows. This module, named TWiX, is trained on sets of tracks with the objective of discriminating pairs of tracks coming from the same object from those which are not. Our module does not use the intersection over union measure, nor does it requires any motion priors or any camera motion compensation technique. By inserting TWiX within an online cascade matching pipeline, our tracker C-TWiX achieves state-of-the-art performance on the DanceTrack and KITTIMOT datasets, and gets competitive results on the MOT17 dataset. The code will be made available upon publication., Comment: Preprint submitted to Pattern Recognition

Increasing the accuracy of instance segmentation methods is often done at the expense of speed. Using coarser representations, we can reduce the number of parameters and thus obtain real-time masks. In this paper, we take inspiration from the set cover problem to predict mask approximations. Given ground-truth binary masks of objects of interest as training input, our method learns to predict the approximate coverage of these objects by disks without supervision on their location or radius. Each object is represented by a fixed number of disks with different radii. In the learning phase, we consider the radius as proportional to a standard deviation in order to compute the error to propagate on a set of two-dimensional Gaussian functions rather than disks. We trained and tested our instance segmentation method on challenging datasets showing dense urban settings with various road users. Our method achieve state-of-the art results on the IDD and KITTI dataset with an inference time of 0.040 s on a single RTX 3090 GPU.

Urban traffic environments present unique challenges for object detection, particularly with the increasing presence of micromobility vehicles like e-scooters and bikes. To address this object detection problem, this work introduces an adapted detection model that combines the accuracy and speed of single-frame object detection with the richer features offered by video object detection frameworks. This is done by applying aggregated feature maps from consecutive frames processed through motion flow to the YOLOX architecture. This fusion brings a temporal perspective to YOLOX detection abilities, allowing for a better understanding of urban mobility patterns and substantially improving detection reliability. Tested on a custom dataset curated for urban micromobility scenarios, our model showcases substantial improvement over existing state-of-the-art methods, demonstrating the need to consider spatio-temporal information for detecting such small and thin objects. Our approach enhances detection in challenging conditions, including occlusions, ensuring temporal consistency, and effectively mitigating motion blur., Comment: Accepted at the 21st Conference on Robots and Vision (CRV), 2024

Consecutive frames in a video contain redundancy, but they may also contain relevant complementary information for the detection task. The objective of our work is to leverage this complementary information to improve detection. Therefore, we propose a spatio-temporal fusion framework (STF). We first introduce multi-frame and single-frame attention modules that allow a neural network to share feature maps between nearby frames to obtain more robust object representations. Second, we introduce a dual-frame fusion module that merges feature maps in a learnable manner to improve them. Our evaluation is conducted on three different benchmarks including video sequences of moving road users. The performed experiments demonstrate that the proposed spatio-temporal fusion module leads to improved detection performance compared to baseline object detectors. Code is available at https://github.com/noreenanwar/STF-module, Comment: 8 pages,3 figures

Predicting future frames of a video is challenging because it is difficult to learn the uncertainty of the underlying factors influencing their contents. In this paper, we propose a novel video prediction model, which has infinite-dimensional latent variables over the spatio-temporal domain. Specifically, we first decompose the video motion and content information, then take a neural stochastic differential equation to predict the temporal motion information, and finally, an image diffusion model autoregressively generates the video frame by conditioning on the predicted motion feature and the previous frame. The better expressiveness and stronger stochasticity learning capability of our model lead to state-of-the-art video prediction performances. As well, our model is able to achieve temporal continuous prediction, i.e., predicting in an unsupervised way the future video frames with an arbitrarily high frame rate. Our code is available at \url{https://github.com/XiYe20/STDiffProject}.

This paper presents an efficient deep neural network model for diagnosing Parkinson's disease from gait. More specifically, we introduce a hybrid ConvNet-Transformer architecture to accurately diagnose the disease by detecting the severity stage. The proposed architecture exploits the strengths of both Convolutional Neural Networks and Transformers in a single end-to-end model, where the former is able to extract relevant local features from Vertical Ground Reaction Force (VGRF) signal, while the latter allows to capture long-term spatio-temporal dependencies in data. In this manner, our hybrid architecture achieves an improved performance compared to using either models individually. Our experimental results show that our approach is effective for detecting the different stages of Parkinson's disease from gait data, with a final accuracy of 88%, outperforming other state-of-the-art AI methods on the Physionet gait dataset. Moreover, our method can be generalized and adapted for other classification problems to jointly address the feature relevance and spatio-temporal dependency problems in 1D signals. Our source code and pre-trained models are publicly available at https://github.com/SafwenNaimi/1D-Convolutional-transformer-for-Parkinson-disease-diagnosis-from-gait., Comment: 17 pages, 5 Figures, 6 Tables. Accepted for publication in Neural Computing and Applications (NCAA) 2023

Lichens are symbiotic organisms composed of fungi, algae, and/or cyanobacteria that thrive in a variety of environments. They play important roles in carbon and nitrogen cycling, and contribute directly and indirectly to biodiversity. Ecologists typically monitor lichens by using them as indicators to assess air quality and habitat conditions. In particular, epiphytic lichens, which live on trees, are key markers of air quality and environmental health. A new method of monitoring epiphytic lichens involves using time-lapse cameras to gather images of lichen populations. These cameras are used by ecologists in Newfoundland and Labrador to subsequently analyze and manually segment the images to determine lichen thalli condition and change. These methods are time-consuming and susceptible to observer bias. In this work, we aim to automate the monitoring of lichens over extended periods and to estimate their biomass and condition to facilitate the task of ecologists. To accomplish this, our proposed framework uses semantic segmentation with an effective training approach to automate monitoring and biomass estimation of epiphytic lichens on time-lapse images. We show that our method has the potential to significantly improve the accuracy and efficiency of lichen population monitoring, making it a valuable tool for forest ecologists and environmental scientists to evaluate the impact of climate change on Canada's forests. To the best of our knowledge, this is the first time that such an approach has been used to assist ecologists in monitoring and analyzing epiphytic lichens., Comment: 6 pages, 3 Figures, 8 Tables, Accepted for publication in IEEE International Conference on Machine Learning and Applications (ICMLA), copyright IEEE

In this paper, we propose a novel deep learning method based on a new Hybrid ConvNet-Transformer architecture to detect and stage Parkinson's disease (PD) from gait data. We adopt a two-step approach by dividing the problem into two sub-problems. Our Hybrid ConvNet-Transformer model first distinguishes healthy versus parkinsonian patients. If the patient is parkinsonian, a multi-class Hybrid ConvNet-Transformer model determines the Hoehn and Yahr (H&Y) score to assess the PD severity stage. Our hybrid architecture exploits the strengths of both Convolutional Neural Networks (ConvNets) and Transformers to accurately detect PD and determine the severity stage. In particular, we take advantage of ConvNets to capture local patterns and correlations in the data, while we exploit Transformers for handling long-term dependencies in the input signal. We show that our hybrid method achieves superior performance when compared to other state-of-the-art methods, with a PD detection accuracy of 97% and a severity staging accuracy of 87%. Our source code is available at: https://github.com/SafwenNaimi, Comment: 6 pages, 6 figures, 3 tables, Accepted for publication in IEEE International Conference on Machine Learning and Applications (ICMLA), copyright IEEE

Predicting a binary mask for an object is more accurate but also more computationally expensive than a bounding box. Polygonal masks as developed in CenterPoly can be a good compromise. In this paper, we improve over CenterPoly by enhancing the classical regression L1 loss with a novel region-based loss and a novel order loss, as well as with a new training process for the vertices prediction head. Moreover, the previous methods that predict polygonal masks use different coordinate systems, but it is not clear if one is better than another, if we abstract the architecture requirement. We therefore investigate their impact on the prediction. We also use a new evaluation protocol with oracle predictions for the detection head, to further isolate the segmentation process and better compare the polygonal masks with binary masks. Our instance segmentation method is trained and tested with challenging datasets containing urban scenes, with a high density of road users. Experiments show, in particular, that using a combination of a regression loss and a region-based loss allows significant improvements on the Cityscapes and IDD test set compared to CenterPoly. Moreover the inference stage remains fast enough to reach real-time performance with an average of 0.045 s per frame for 2048$\times$1024 images on a single RTX 2070 GPU. The code is available $\href{https://github.com/KatiaJDL/CenterPoly-v2}{\text{here}}$.

This paper presents a novel approach for visible-thermal infrared stereoscopy, focusing on the estimation of disparities of human silhouettes. Visible-thermal infrared stereo poses several challenges, including occlusions and differently textured matching regions in both spectra. Finding matches between two spectra with varying colors, textures, and shapes adds further complexity to the task. To address the aforementioned challenges, this paper proposes a novel approach where a high-resolution convolutional neural network is used to better capture relationships between the two spectra. To do so, a modified HRNet backbone is used for feature extraction. This HRNet backbone is capable of capturing fine details and textures as it extracts features at multiple scales, thereby enabling the utilization of both local and global information. For matching visible and thermal infrared regions, our method extracts features on each patch using two modified HRNet streams. Features from the two streams are then combined for predicting the disparities by concatenation and correlation. Results on public datasets demonstrate the effectiveness of the proposed approach by improving the results by approximately 18 percentage points on the $\leq$ 1 pixel error, highlighting its potential for improving accuracy in this task. The code of VisiTherS is available on GitHub at the following link https://github.com/philippeDG/VisiTherS., Comment: 8 pages,3 Figures,CVPR workshop

Sketching out Graphical User Interface (GUI) layout is part of the pipeline of designing a GUI and a crucial task for the success of a software application. Arranging all components inside a GUI layout manually is a time-consuming task. In order to assist designers, we developed a method named GUILGET to automatically generate GUI layouts from positional constraints represented as GUI arrangement graphs (GUI-AGs). The goal is to support the initial step of GUI design by producing realistic and diverse GUI layouts. The existing image layout generation techniques often cannot incorporate GUI design constraints. Thus, GUILGET needs to adapt existing techniques to generate GUI layouts that obey to constraints specific to GUI designs. GUILGET is based on transformers in order to capture the semantic in relationships between elements from GUI-AG. Moreover, the model learns constraints through the minimization of losses responsible for placing each component inside its parent layout, for not letting components overlap if they are inside the same parent, and for component alignment. Our experiments, which are conducted on the CLAY dataset, reveal that our model has the best understanding of relationships from GUI-AG and has the best performances in most of evaluation metrics. Therefore, our work contributes to improved GUI layout generation by proposing a novel method that effectively accounts for the constraints on GUI elements and paves the road for a more efficient GUI design pipeline., Comment: 12 pages, 5 figures, Canadian AI Conference 2023

In recent years, the joint detection-and-tracking paradigm has been a very popular way of tackling the multi-object tracking (MOT) task. Many of the methods following this paradigm use the object center keypoint for detection. However, we argue that the center point is not optimal since it is often not visible in crowded scenarios, which results in many missed detections when the objects are partially occluded. We propose TopTrack, a joint detection-and-tracking method that uses the top of the object as a keypoint for detection instead of the center because it is more often visible. Furthermore, TopTrack processes consecutive frames in separate streams in order to facilitate training. We performed experiments to show that using the object top as a keypoint for detection can reduce the amount of missed detections, which in turn leads to more complete trajectories and less lost trajectories. TopTrack manages to achieve competitive results with other state-of-the-art trackers on two MOT benchmarks., Comment: 14 pages, 7 figures, submitted to Machine Vision and Applications

Video prediction is a challenging computer vision task that has a wide range of applications. In this work, we present a new family of Transformer-based models for video prediction. Firstly, an efficient local spatial-temporal separation attention mechanism is proposed to reduce the complexity of standard Transformers. Then, a full autoregressive model, a partial autoregressive model and a non-autoregressive model are developed based on the new efficient Transformer. The partial autoregressive model has a similar performance with the full autoregressive model but a faster inference speed. The non-autoregressive model not only achieves a faster inference speed but also mitigates the quality degradation problem of the autoregressive counterparts, but it requires additional parameters and loss function for learning. Given the same attention mechanism, we conducted a comprehensive study to compare the proposed three video prediction variants. Experiments show that the proposed video prediction models are competitive with more complex state-of-the-art convolutional-LSTM based models. The source code is available at https://github.com/XiYe20/VPTR., Comment: Accepted by Image and Vision Computing. arXiv admin note: text overlap with arXiv:2203.15836

Different conditional video prediction tasks, like video future frame prediction and video frame interpolation, are normally solved by task-related models even though they share many common underlying characteristics. Furthermore, almost all conditional video prediction models can only achieve discrete prediction. In this paper, we propose a unified model that addresses these two issues at the same time. We show that conditional video prediction can be formulated as a neural process, which maps input spatio-temporal coordinates to target pixel values given context spatio-temporal coordinates and context pixel values. Specifically, we feed the implicit neural representation of coordinates and context pixel features into a Transformer-based non-autoregressive conditional video prediction model. Our task-specific models outperform previous work for video future frame prediction and video interpolation on multiple datasets. Importantly, the model is able to interpolate or predict with an arbitrary high frame rate, i.e., continuous prediction. Our source code is available at \url{https://npvp.github.io}., Comment: Accepted by CVPR2023 Workshop

Multiple object tracking (MOT) is a task in computer vision that aims to detect the position of various objects in videos and to associate them to a unique identity. We propose an approach based on Constraint Programming (CP) whose goal is to be grafted to any existing tracker in order to improve its object association results. We developed a modular algorithm divided into three independent phases. The first phase consists in recovering the tracklets provided by a base tracker and to cut them at the places where uncertain associations are spotted, for example, when tracklets overlap, which may cause identity switches. In the second phase, we associate the previously constructed tracklets using a Belief Propagation Constraint Programming algorithm, where we propose various constraints that assign scores to each of the tracklets based on multiple characteristics, such as their dynamics or the distance between them in time and space. Finally, the third phase is a rudimentary interpolation model to fill in the remaining holes in the trajectories we built. Experiments show that our model leads to improvements in the results for all three of the state-of-the-art trackers on which we tested it (3 to 4 points gained on HOTA and IDF1)., Comment: 8 pages, 6 figures, CRV 2022

Multispectral stereoscopy is an emerging field. A lot of work has been done in classical stereoscopy, but multispectral stereoscopy is not studied as frequently. This type of stereoscopy can be used in autonomous vehicles to complete the information given by RGB cameras. It helps to identify objects in the surroundings when the conditions are more difficult, such as in night scenes. This paper focuses on the RGB-LWIR spectrum. RGB-LWIR stereoscopy has the same challenges as classical stereoscopy, that is occlusions, textureless surfaces and repetitive patterns, plus specific ones related to the different modalities. Finding matches between two spectrums adds another layer of complexity. Color, texture and shapes are more likely to vary from a spectrum to another. To address this additional challenge, this paper focuses on estimating the disparity of people present in a scene. Given the fact that people's shape is captured in both RGB and LWIR, we propose a novel method that uses segmentation masks of the human in both spectrum and than concatenate them to the original images before the first layer of a Siamese Network. This method helps to improve the accuracy, particularly within the one pixel error range., Comment: 6 pages, 2 figures

Human action recognition (HAR) in videos is one of the core tasks of video understanding. Based on video sequences, the goal is to recognize actions performed by humans. While HAR has received much attention in the visible spectrum, action recognition in infrared videos is little studied. Accurate recognition of human actions in the infrared domain is a highly challenging task because of the redundant and indistinguishable texture features present in the sequence. Furthermore, in some cases, challenges arise from the irrelevant information induced by the presence of multiple active persons not contributing to the actual action of interest. Therefore, most existing methods consider a standard paradigm that does not take into account these challenges, which is in some part due to the ambiguous definition of the recognition task in some cases. In this paper, we propose a new method that simultaneously learns to recognize efficiently human actions in the infrared spectrum, while automatically identifying the key-actors performing the action without using any prior knowledge or explicit annotations. Our method is composed of three stages. In the first stage, optical flow-based key-actor identification is performed. Then for each key-actor, we estimate key-poses that will guide the frame selection process. A scale-invariant encoding process along with embedded pose filtering are performed in order to enhance the quality of action representations. Experimental results on InfAR dataset show that our proposed model achieves promising recognition performance and learns useful action representations.

This paper focuses on the detection of Parkinson's disease based on the analysis of a patient's gait. The growing popularity and success of Transformer networks in natural language processing and image recognition motivated us to develop a novel method for this problem based on an automatic features extraction via Transformers. The use of Transformers in 1D signal is not really widespread yet, but we show in this paper that they are effective in extracting relevant features from 1D signals. As Transformers require a lot of memory, we decoupled temporal and spatial information to make the model smaller. Our architecture used temporal Transformers, dimension reduction layers to reduce the dimension of the data, a spatial Transformer, two fully connected layers and an output layer for the final prediction. Our model outperforms the current state-of-the-art algorithm with 95.2\% accuracy in distinguishing a Parkinsonian patient from a healthy one on the Physionet dataset. A key learning from this work is that Transformers allow for greater stability in results. The source code and pre-trained models are released in https://github.com/DucMinhDimitriNguyen/Transformers-for-1D-signals-in-Parkinson-s-disease-detection-from-gait.git, Comment: International Conference on Pattern Recognition (ICPR 2022)

In this paper, we propose a new Transformer block for video future frames prediction based on an efficient local spatial-temporal separation attention mechanism. Based on this new Transformer block, a fully autoregressive video future frames prediction Transformer is proposed. In addition, a non-autoregressive video prediction Transformer is also proposed to increase the inference speed and reduce the accumulated inference errors of its autoregressive counterpart. In order to avoid the prediction of very similar future frames, a contrastive feature loss is applied to maximize the mutual information between predicted and ground-truth future frame features. This work is the first that makes a formal comparison of the two types of attention-based video future frames prediction models over different scenarios. The proposed models reach a performance competitive with more complex state-of-the-art models. The source code is available at \emph{https://github.com/XiYe20/VPTR}.

Identifying and understanding underlying sentiment or emotions in text is a key component of multiple natural language processing applications. While simple polarity sentiment analysis is a well-studied subject, fewer advances have been made in identifying more complex, finer-grained emotions using only textual data. In this paper, we present a Transformer-based model with a Fusion of Adapter layers which leverages knowledge from more simple sentiment analysis tasks to improve the emotion detection task on large scale dataset, such as CMU-MOSEI, using the textual modality only. Results show that our proposed method is competitive with other approaches. We obtained state-of-the-art results for emotion recognition on CMU-MOSEI even while using only the textual modality.

In this paper, we present a novel method called PolyTrack for fast multi-object tracking and segmentation using bounding polygons. Polytrack detects objects by producing heatmaps of their center keypoint. For each of them, a rough segmentation is done by computing a bounding polygon over each instance instead of the traditional bounding box. Tracking is done by taking two consecutive frames as input and computing a center offset for each object detected in the first frame to predict its location in the second frame. A Kalman filter is also applied to reduce the number of ID switches. Since our target application is automated driving systems, we apply our method on urban environment videos. We trained and evaluated PolyTrack on the MOTS and KITTIMOTS datasets. Results show that tracking polygons can be a good alternative to bounding box and mask tracking. The code of PolyTrack is available at https://github.com/gafaua/PolyTrack., Comment: NeurIPS 2021 Machine Learning for Autonomous Driving Workshop

We propose a method for multi-object tracking and segmentation based on a novel memory-based mechanism to associate tracklets. The proposed tracker, MeNToS, addresses particularly the long-term data association problem, when objects are not observable for long time intervals. Indeed, the recently introduced HOTA metric (High Order Tracking Accuracy), which has a better alignment than the formerly established MOTA (Multiple Object Tracking Accuracy) with the human visual assessment of tracking, has shown that improvements are still needed for data association, despite the recent improvement in object detection. In MeNToS, after creating tracklets using instance segmentation and optical flow, the proposed method relies on a space-time memory network originally developed for one-shot video object segmentation to improve the association of sequence of detections (tracklets) with temporal gaps. We evaluate our tracker on KITTIMOTS and MOTSChallenge and we show the benefit of our data association strategy with the HOTA metric. Additional ablation studies demonstrate that our approach using a space-time memory network gives better and more robust long-term association than those based on a re-identification network. Our project page is at \url{www.mehdimiah.com/mentos+}., Comment: arXiv admin note: text overlap with arXiv:2107.07067 Accepted at CRV 2023 (Conference on Robots and Vision)

Detecting and tracking vehicles in urban scenes is a crucial step in many traffic-related applications as it helps to improve road user safety among other benefits. Various challenges remain unresolved in multi-object tracking (MOT) including target information description, long-term occlusions and fast motion. We propose a multi-vehicle detection and tracking system following the tracking-by-detection paradigm that tackles the previously mentioned challenges. Our MOT method extends an Intersection-over-Union (IOU)-based tracker with vehicle re-identification features. This allows us to utilize appearance information to better match objects after long occlusion phases and/or when object location is significantly shifted due to fast motion. We outperform our baseline MOT method on the UA-DETRAC benchmark while maintaining a total processing speed suitable for online use cases.

A significant amount of redundancy exists between consecutive frames of a video. Object detectors typically produce detections for one image at a time, without any capabilities for taking advantage of this redundancy. Meanwhile, many applications for object detection work with videos, including intelligent transportation systems, advanced driver assistance systems and video surveillance. Our work aims at taking advantage of the similarity between video frames to produce better detections. We propose FFAVOD, standing for feature fusion architecture for video object detection. We first introduce a novel video object detection architecture that allows a network to share feature maps between nearby frames. Second, we propose a feature fusion module that learns to merge feature maps to enhance them. We show that using the proposed architecture and the fusion module can improve the performance of three base object detectors on two object detection benchmarks containing sequences of moving road users. Additionally, to further increase performance, we propose an improvement to the SpotNet attention module. Using our architecture on the improved SpotNet detector, we obtain the state-of-the-art performance on the UA-DETRAC public benchmark as well as on the UAVDT dataset. Code is available at https://github.com/hu64/FFAVOD., Comment: Accepted for publication in Pattern Recognition Letters

We present a novel method, called CenterPoly, for real-time instance segmentation using bounding polygons. We apply it to detect road users in dense urban environments, making it suitable for applications in intelligent transportation systems like automated vehicles. CenterPoly detects objects by their center keypoint while predicting a fixed number of polygon vertices for each object, thus performing detection and segmentation in parallel. Most of the network parameters are shared by the network heads, making it fast and lightweight enough to run at real-time speed. To properly convert mask ground-truth to polygon ground-truth, we designed a vertex selection strategy to facilitate the learning of the polygons. Additionally, to better segment overlapping objects in dense urban scenes, we also train a relative depth branch to determine which instances are closer and which are further, using available weak annotations. We propose several models with different backbones to show the possible speed / accuracy trade-offs. The models were trained and evaluated on Cityscapes, KITTI and IDD and the results are reported on their public benchmark, which are state-of-the-art at real-time speeds. Code is available at https://github.com/hu64/CenterPoly, Comment: Accepted to the 2nd Autonomous Vehicle Vision Workshop (AVVision)

We propose a method for multi-object tracking and segmentation (MOTS) that does not require fine-tuning or per benchmark hyperparameter selection. The proposed method addresses particularly the data association problem. Indeed, the recently introduced HOTA metric, that has a better alignment with the human visual assessment by evenly balancing detections and associations quality, has shown that improvements are still needed for data association. After creating tracklets using instance segmentation and optical flow, the proposed method relies on a space-time memory network (STM) developed for one-shot video object segmentation to improve the association of tracklets with temporal gaps. To the best of our knowledge, our method, named MeNToS, is the first to use the STM network to track object masks for MOTS. We took the 4th place in the RobMOTS challenge. The project page is https://mehdimiah.com/mentos.html., Comment: Presented at the "Robust Video Scene Understanding: Tracking and Video Segmentation" workshop (CVPR-W 2021)

We present a local anomaly detection method in videos. As opposed to most existing methods that are computationally expensive and are not very generalizable across different video scenes, we propose an adversarial framework that learns the temporal local appearance variations by predicting the appearance of a normally behaving object in the next frame of a scene by only relying on its current and past appearances. In the presence of an abnormally behaving object, the reconstruction error between the real and the predicted next appearance of that object indicates the likelihood of an anomaly. Our method is competitive with the existing state-of-the-art while being significantly faster for both training and inference and being better at generalizing to unseen video scenes., Comment: Accepted as an oral presentation for MVA'2021

Siamese trackers demonstrated high performance in object tracking due to their balance between accuracy and speed. Unlike classification-based CNNs, deep similarity networks are specifically designed to address the image similarity problem, and thus are inherently more appropriate for the tracking task. However, Siamese trackers mainly use the last convolutional layers for similarity analysis and target search, which restricts their performance. In this paper, we argue that using a single convolutional layer as feature representation is not an optimal choice in a deep similarity framework. We present a Multiple Features-Siamese Tracker (MFST), a novel tracking algorithm exploiting several hierarchical feature maps for robust tracking. Since convolutional layers provide several abstraction levels in characterizing an object, fusing hierarchical features allows to obtain a richer and more efficient representation of the target. Moreover, we handle the target appearance variations by calibrating the deep features extracted from two different CNN models. Based on this advanced feature representation, our method achieves high tracking accuracy, while outperforming the standard siamese tracker on object tracking benchmarks. The source code and trained models are available at https://github.com/zhenxili96/MFST., Comment: Accepted for Machine Vision and Applications, 2021. arXiv admin note: substantial text overlap with arXiv:2103.00810

Siamese trackers have recently achieved interesting results due to their balance between accuracy and speed. This success is mainly due to the fact that deep similarity networks were specifically designed to address the image similarity problem. Therefore, they are inherently more appropriate than classical CNNs for the tracking task. However, Siamese trackers rely on the last convolutional layers for similarity analysis and target search, which restricts their performance. In this paper, we argue that using a single convolutional layer as feature representation is not the optimal choice within the deep similarity framework, as multiple convolutional layers provide several abstraction levels in characterizing an object. Starting from this motivation, we present the Multi-Features Siamese Tracker (MFST), a novel tracking algorithm exploiting several hierarchical feature maps for robust deep similarity tracking. MFST proceeds by fusing hierarchical features to ensure a richer and more efficient representation. Moreover, we handle appearance variation by calibrating deep features extracted from two different CNN models. Based on this advanced feature representation, our algorithm achieves high tracking accuracy, while outperforming several state-of-the-art trackers, including standard Siamese trackers. The code and trained models are available at https://github.com/zhenxili96/MFST., Comment: ICPR 2021, Oral

We propose a novel unsupervised approach based on a two-stage object-centric adversarial framework that only needs object regions for detecting frame-level local anomalies in videos. The first stage consists in learning the correspondence between the current appearance and past gradient images of objects in scenes deemed normal, allowing us to either generate the past gradient from current appearance or the reverse. The second stage extracts the partial reconstruction errors between real and generated images (appearance and past gradient) with normal object behaviour, and trains a discriminator in an adversarial fashion. In inference mode, we employ the trained image generators with the adversarially learned binary classifier for outputting region-level anomaly detection scores. We tested our method on four public benchmarks, UMN, UCSD, Avenue and ShanghaiTech and our proposed object-centric adversarial approach yields competitive or even superior results compared to state-of-the-art methods., Comment: Accepted for The First International Workshop on Deep Learning for Human-Centric Activity Understanding (ICPR2020 workshop)

Human action recognition (HAR) in videos is a fundamental research topic in computer vision. It consists mainly in understanding actions performed by humans based on a sequence of visual observations. In recent years, HAR have witnessed significant progress, especially with the emergence of deep learning models. However, most of existing approaches for action recognition rely on information that is not always relevant for this task, and are limited in the way they fuse the temporal information. In this paper, we propose a novel method for human action recognition that encodes efficiently the most discriminative appearance information of an action with explicit attention on representative pose features, into a new compact grid representation. Our GRAR (Grid-based Representation for Action Recognition) method is tested on several benchmark datasets demonstrating that our model can accurately recognize human actions, despite intra-class appearance variations and occlusion challenges., Comment: Accepted on 25th International Conference on Pattern Recognition (ICPR 2020)

This paper addresses the problem of selecting appearance features for multiple object tracking (MOT) in urban scenes. Over the years, a large number of features has been used for MOT. However, it is not clear whether some of them are better than others. Commonly used features are color histograms, histograms of oriented gradients, deep features from convolutional neural networks and re-identification (ReID) features. In this study, we assess how good these features are at discriminating objects enclosed by a bounding box in urban scene tracking scenarios. Several affinity measures, namely the $\mathrm{L}_1$, $\mathrm{L}_2$ and the Bhattacharyya distances, Rank-1 counts and the cosine similarity, are also assessed for their impact on the discriminative power of the features. Results on several datasets show that features from ReID networks are the best for discriminating instances from one another regardless of the quality of the detector. If a ReID model is not available, color histograms may be selected if the detector has a good recall and there are few occlusions; otherwise, deep features are more robust to detectors with lower recall. The project page is http://www.mehdimiah.com/visual_features., Comment: Accepted on 25th International Conference on Pattern Recognition (ICPR 2020)

While recent person re-identification (ReID) methods achieve high accuracy in a supervised setting, their generalization to an unlabelled domain is still an open problem. In this paper, we introduce a novel unsupervised disentanglement generative adversarial network (UD-GAN) to address the domain adaptation issue of supervised person ReID. Our framework jointly trains a ReID network for discriminative features extraction in a source labelled domain using identity annotation, and adapts the ReID model to an unlabelled target domain by learning disentangled latent representations on the domain. Identity-unrelated features in the target domain are distilled from the latent features. As a result, the ReID features better encompass the identity of a person in the unsupervised domain. We conducted experiments on the Market1501, DukeMTMC and MSMT17 datasets. Results show that the unsupervised domain adaptation problem in ReID is very challenging. Nevertheless, our method shows improvement in half of the domain transfers and achieve state-of-the-art performance for one of them., Comment: 8 pages, 5 figures, submitted to ICPR 2020

Multispectral disparity estimation is a difficult task for many reasons: it has all the same challenges as traditional visible-visible disparity estimation (occlusions, repetitive patterns, textureless surfaces), in addition of having very few common visual information between images (e.g. color information vs. thermal information). In this paper, we propose a new CNN architecture able to do disparity estimation between images from different spectrum, namely thermal and visible in our case. Our proposed model takes two patches as input and proceeds to do domain feature extraction for each of them. Features from both domains are then merged with two fusion operations, namely correlation and concatenation. These merged vectors are then forwarded to their respective classification heads, which are responsible for classifying the inputs as being same or not. Using two merging operations gives more robustness to our feature extraction process, which leads to more precise disparity estimation. Our method was tested using the publicly available LITIV 2014 and LITIV 2018 datasets, and showed best results when compared to other state of the art methods.

In this paper, we propose a multiple object tracker, called MF-Tracker, that integrates multiple classical features (spatial distances and colours) and modern features (detection labels and re-identification features) in its tracking framework. Since our tracker can work with detections coming either from unsupervised and supervised object detectors, we also investigated the impact of supervised and unsupervised detection inputs in our method and for tracking road users in general. We also compared our results with existing methods that were applied on the UA-Detrac and the UrbanTracker datasets. Results show that our proposed method is performing very well in both datasets with different inputs (MOTA ranging from 0:3491 to 0:5805 for unsupervised inputs on the UrbanTracker dataset and an average MOTA of 0:7638 for supervised inputs on the UA Detrac dataset) under different circumstances. A well-trained supervised object detector can give better results in challenging scenarios. However, in simpler scenarios, if good training data is not available, unsupervised method can perform well and can be a good alternative., Comment: Accepted for ICIAR 2020

Consecutive frames in a video are highly redundant. Therefore, to perform the task of video object detection, executing single frame detectors on every frame without reusing any information is quite wasteful. It is with this idea in mind that we propose RN-VID (standing for RetinaNet-VIDeo), a novel approach to video object detection. Our contributions are twofold. First, we propose a new architecture that allows the usage of information from nearby frames to enhance feature maps. Second, we propose a novel module to merge feature maps of same dimensions using re-ordering of channels and 1 x 1 convolutions. We then demonstrate that RN-VID achieves better mean average precision (mAP) than corresponding single frame detectors with little additional cost during inference.

In this paper, we aim at improving the tracking of road users in urban scenes. We present a constraint programming (CP) approach for the data association phase found in the tracking-by-detection paradigm of the multiple object tracking (MOT) problem. Such an approach can solve the data association problem more efficiently than graph-based methods and can handle better the combinatorial explosion occurring when multiple frames are analyzed. Because our focus is on the data association problem, our MOT method only uses simple image features, which are the center position and color of detections for each frame. Constraints are defined on these two features and on the general MOT problem. For example, we enforce color appearance preservation over trajectories and constrain the extent of motion between frames. Filtering layers are used in order to eliminate detection candidates before using CP and to remove dummy trajectories produced by the CP solver. Our proposed method was tested on a motorized vehicles tracking dataset and produces results that outperform the top methods of the UA-DETRAC benchmark.

Humans are very good at directing their visual attention toward relevant areas when they search for different types of objects. For instance, when we search for cars, we will look at the streets, not at the top of buildings. The motivation of this paper is to train a network to do the same via a multi-task learning approach. To train visual attention, we produce foreground/background segmentation labels in a semi-supervised way, using background subtraction or optical flow. Using these labels, we train an object detection model to produce foreground/background segmentation maps as well as bounding boxes while sharing most model parameters. We use those segmentation maps inside the network as a self-attention mechanism to weight the feature map used to produce the bounding boxes, decreasing the signal of non-relevant areas. We show that by using this method, we obtain a significant mAP improvement on two traffic surveillance datasets, with state-of-the-art results on both UA-DETRAC and UAVDT.