BREMOND , Francois

Depth information improves skeleton detection, thus skeleton based methods are the most popular methods in RGB-D action recognition. But skeleton detection working range is limited in terms of distance and viewpoint. Most of the skeleton based action recognition methods ignore fact that skeleton may be missing. Local points-of-interest (POIs)...

This paper introduces a new channel descriptor for pedestrian detection. This type of descriptor usually selects a set of one-valued filters within the enormous set of all possible filters for improved efficiency. The main claim underpinning this paper is that the recent works on channel-based features restrict the filter space search,...

This paper addresses the person re-identification task applied in a real-world scenario. Finding people in a network of cameras is challenging due to significant variations in lighting conditions, different colour responses and different camera viewpoints. State of the art algorithms are likely to fail due to serious perspective and pose...

In this paper, we focus on the important topic of violence recognition and detection in surveillance videos. Our goal is to determine if a violence occurs in a video (recognition) and when it happens (detection). Firstly, we propose an extension of the Improved Fisher Vectors (IFV) for videos, which allows to represent a video using both local...

Appearance based person re-identification is a challenging task, specially due to difficulty in capturing high intra-person appearance variance across cameras when inter-person similarity is also high. Metric learning is often used to address deficiency of low-level features by learning view specific re-identification models. The models are...

This paper tackles data selection for training set generation in the context of nearreal-time pedestrian detection through the introduction of a training methodology: FairTrain.After highlighting the impact of poorly chosen data on detector performance, we will introduce anew data selection technique utilizing the expectation-maximization...

In this paper, we propose a new local spatio-temporal descriptor for videos and we propose a new approach for action recognition in videos based on the introduced descriptor. The new descriptor is called the Video Covariance Matrix Logarithm (VCML). The VCML descriptor is based on a covariance matrix representation, and it models relationships...

This paper presents a novel way to transfer model weights from one domain to another using residual learning framework instead of direct fine-tuning. It also argues for hybrid models that use learned (deep) features and statistical metric learning for multi-shot person re-identification when training sets are small. This is in contrast...

Appearance based person re-identification in real-world video surveillance systems is a challenging problem for many reasons, including ineptness of existing low level features under significant viewpoint, illumination, or camera characteristic changes to robustly describe a person's appearance. One approach to handle appearance variability is...

Multi-object tracking algorithms reach impressive performance on the benchmark datasets that they are trained and evaluated on, especially with their object detector parts tuned. When these algorithms are exposed to new videos though, the performance of the detection and tracking becomes poor, making them not usable. This paper tries to...

3D gaze estimation is about predicting the line of sight of a person in 3D space. Person-independent models for the same lack precision due to anatomical differences of subjects, whereas person-specific calibrated techniques add strict constraints on scalability. To overcome these issues, we propose a novel technique, Facial Landmark Heatmap...

The objective of unsupervised person re-identification (Re-ID) is to learn discriminative features without laborintensive identity annotations. State-of-the-art unsupervised Re-ID methods assign pseudo labels to unlabeled images in the target domain and learn from these noisy pseudo labels. Recently introduced Mean Teacher Model is a promising...

Most action recognition models treat human activities as unitary events. However, human activities often follow a certain hierarchy. In fact, many human activities are compositional. Also, these actions are mostly human-object interactions. In this paper we propose to recognize human action by leveraging the set of interactions that define an...

Expression recognition remains challenging, predominantly due to (a) lack of sufficient data, (b) subtle emotion intensity, (c) subjective and inconsistent annotation, as well as due to (d) in-the-wild data containing variations in pose, intensity, and occlusion. To address such challenges in a unified framework, we propose a self-training...

Action detection is an essential and challenging task, especially for densely labelled datasets of untrimmed videos. There are many real-world challenges in those datasets, such as composite action, co-occurring action, and high temporal variation of instance duration. For handling these challenges, we propose to explore both the class and...

In Person Re-Identification (Re-ID) task, combining local and global features is a common strategy to overcome missing key parts and misalignment on models based only on global features. Using this combination, neural networks yield impressive performance in Re-ID task. Previous part-based models mainly focus on spatial partition strategies....

Recent studies have demonstrated the effectiveness of warping in transferring unique textures to the output of the pose transfer networks. However, due to the mutual dependencies of image features and pixel locations, joint estimation of flow map and output image is very likely to get stuck in local minima. Current solution is limited to...

In this paper, we introduce a new approach for Activities of Daily Living (ADL) recognition. In order to discriminate between activities with similar appearance and motion, we focus on their temporal structure. Actions with subtle and similar motion are hard to disambiguate since long-range temporal information is hard to encode. So, we propose...

The smart city vision raises the prospect that cities will become more intelligent in various fields, such as more sustainable environment and a better quality of life for residents. As a key component of smart cities, intelligent transportation system highlights the importance of vehicle re-identification (Re-ID). However, as compared to the...

Facial attributes are instrumental in semantically characterizing faces. Automated classification of such attributes (i.e., age, gender, ethnicity) has been a well studied topic. We here seek to explore the inverse problem, namely given attribute-labels the generation of attribute-associated faces. The interest in this topic is fueled by...

This work explores joint classification of gender, age and race. Specifically, we here propose a Multi-Task Convolution Neural Network (MTCNN) employing joint dynamic loss weight adjustment towards classification of named soft biometrics, as well as towards mitigation of soft biometrics related bias. The proposed algorithm achieves promising...

Recent advances in computer vision have aimed at extracting and classifying auxiliary biometric information such as age, gender, as well as health attributes, referred to as soft biometrics or attributes. We here seek to explore the inverse problem, namely face generation based on attribute labels, which is of interest due to related...

Unsupervised person re-identification (ReID) aims at learning discriminative identity features without annotations. Recently, self-supervised contrastive learning has gained increasing attention for its effectiveness in unsupervised representation learning. The main idea of instance contrastive learning is to match a same instance in different...

In video understanding, most cross-modal knowledge distillation (KD) methods are tailored for classification tasks, focusing on the discriminative representation of the trimmed videos. However, action detection requires not only categorizing actions, but also localizing them in untrimmed videos. Therefore, transferring knowledge pertaining to...