arXiv subjects

Alberto Del Bimbo

Publications and source records attributed to Alberto Del Bimbo.

At least 73 records · Page 4Linked to original sources

arXiv2021

AdaVQA: Overcoming Language Priors with Adapted Margin Cosine Loss

A number of studies point out that current Visual Question Answering (VQA) models are severely affected by the language prior problem, which refers to blindly making predictions based on the language shortcut. Some efforts have been devoted to overcoming this issue with delicate models. However, there is no research to address it from the angle of the answer feature space learning, despite of the fact that existing VQA methods all cast VQA as a classification task. Inspired by this, in this work, we attempt to tackle the language prior problem from the viewpoint of the feature space learning. To this end, an adapted margin cosine loss is designed to discriminate the frequent and the sparse answer feature space under each question type properly. As a result, the limited patterns within the language modality are largely reduced, thereby less language priors would be introduced by our method. We apply this loss function to several baseline models and evaluate its effectiveness on two VQA-CP benchmarks. Experimental results demonstrate that our adapted margin cosine loss can greatly enhance the baseline models with an absolute performance gain of 15\% on average, strongly verifying the potential of tackling the language prior problem in VQA from the angle of the answer feature space learning.

cs.CV↗

arXiv2021

Regular Polytope Networks

Neural networks are widely used as a model for classification in a large variety of tasks. Typically, a learnable transformation (i.e. the classifier) is placed at the end of such models returning a value for each class used for classification. This transformation plays an important role in determining how the generated features change during the learning process. In this work, we argue that this transformation not only can be fixed (i.e. set as non-trainable) with no loss of accuracy and with a reduction in memory usage, but it can also be used to learn stationary and maximally separated embeddings. We show that the stationarity of the embedding and its maximal separated representation can be theoretically justified by setting the weights of the fixed classifier to values taken from the coordinate vertices of the three regular polytopes available in $\mathbb{R}^d$, namely: the $d$-Simplex, the $d$-Cube and the $d$-Orthoplex. These regular polytopes have the maximal amount of symmetry that can be exploited to generate stationary features angularly centered around their corresponding fixed weights. Our approach improves and broadens the concept of a fixed classifier, recently proposed in \cite{hoffer2018fix}, to a larger class of fixed classifier models. Experimental results confirm the theoretical analysis, the generalization capability, the faster convergence and the improved performance of the proposed method. Code will be publicly available.

cs.LG↗

arXiv2021

Robust pedestrian detection in thermal imagery using synthesized images

In this paper we propose a method for improving pedestrian detection in the thermal domain using two stages: first, a generative data augmentation approach is used, then a domain adaptation method using generated data adapts an RGB pedestrian detector. Our model, based on the Least-Squares Generative Adversarial Network, is trained to synthesize realistic thermal versions of input RGB images which are then used to augment the limited amount of labeled thermal pedestrian images available for training. We apply our generative data augmentation strategy in order to adapt a pretrained YOLOv3 pedestrian detector to detection in the thermal-only domain. Experimental results demonstrate the effectiveness of our approach: using less than 50\% of available real thermal training data, and relying on synthesized data generated by our model in the domain adaptation phase, our detector achieves state-of-the-art results on the KAIST Multispectral Pedestrian Detection Benchmark; even if more real thermal data is available adding GAN generated images to the training data results in improved performance, thus showing that these images act as an effective form of data augmentation. To the best of our knowledge, our detector achieves the best single-modality detection results on KAIST with respect to the state-of-the-art.

cs.CV↗

arXiv2020

Garment Recommendation with Memory Augmented Neural Networks

Fashion plays a pivotal role in society. Combining garments appropriately is essential for people to communicate their personality and style. Also different events require outfits to be thoroughly chosen to comply with underlying social clothing rules. Therefore, combining garments appropriately might not be trivial. The fashion industry has turned this into a massive source of income, relying on complex recommendation systems to retrieve and suggest appropriate clothing items for customers. To perform better recommendations, personalized suggestions can be performed, taking into account user preferences or purchase histories. In this paper, we propose a garment recommendation system to pair different clothing items, namely tops and bottoms, exploiting a Memory Augmented Neural Network (MANN). By training a memory writing controller, we are able to store a non-redundant subset of samples, which is then used to retrieve a ranked list of suitable bottoms to complement a given top. In particular, we aim at retrieving a variety of modalities in which a certain garment can be combined. To refine our recommendations, we then include user preferences via Matrix Factorization. We experiment on IQON3000, a dataset collected from an online fashion community, reporting state of the art results.

cs.CV↗

arXiv2020

Temporal Binary Representation for Event-Based Action Recognition

In this paper we present an event aggregation strategy to convert the output of an event camera into frames processable by traditional Computer Vision algorithms. The proposed method first generates sequences of intermediate binary representations, which are then losslessly transformed into a compact format by simply applying a binary-to-decimal conversion. This strategy allows us to encode temporal information directly into pixel values, which are then interpreted by deep learning models. We apply our strategy, called Temporal Binary Representation, to the task of Gesture Recognition, obtaining state of the art results on the popular DVS128 Gesture Dataset. To underline the effectiveness of the proposed method compared to existing ones, we also collect an extension of the dataset under more challenging conditions on which to perform experiments.

cs.CV↗

arXiv2020

Multiple Future Prediction Leveraging Synthetic Trajectories

Trajectory prediction is an important task, especially in autonomous driving. The ability to forecast the position of other moving agents can yield to an effective planning, ensuring safety for the autonomous vehicle as well for the observed entities. In this work we propose a data driven approach based on Markov Chains to generate synthetic trajectories, which are useful for training a multiple future trajectory predictor. The advantages are twofold: on the one hand synthetic samples can be used to augment existing datasets and train more effective predictors; on the other hand, it allows to generate samples with multiple ground truths, corresponding to diverse equally likely outcomes of the observed trajectory. We define a trajectory prediction model and a loss that explicitly address the multimodality of the problem and we show that combining synthetic and real data leads to prediction improvements, obtaining state of the art results.

cs.CV↗

arXiv2020

Inner Eye Canthus Localization for Human Body Temperature Screening

In this paper, we propose an automatic approach for localizing the inner eye canthus in thermal face images. We first coarsely detect 5 facial keypoints corresponding to the center of the eyes, the nosetip and the ears. Then we compute a sparse 2D-3D points correspondence using a 3D Morphable Face Model (3DMM). This correspondence is used to project the entire 3D face onto the image, and subsequently locate the inner eye canthus. Detecting this location allows to obtain the most precise body temperature measurement for a person using a thermal camera. We evaluated the approach on a thermal face dataset provided with manually annotated landmarks. However, such manual annotations are normally conceived to identify facial parts such as eyes, nose and mouth, and are not specifically tailored for localizing the eye canthus region. As additional contribution, we enrich the original dataset by using the annotated landmarks to deform and project the 3DMM onto the images. Then, by manually selecting a small region corresponding to the eye canthus, we enrich the dataset with additional annotations. By using the manual landmarks, we ensure the correctness of the 3DMM projection, which can be used as ground-truth for future evaluations. Moreover, we supply the dataset with the 3D head poses and per-point visibility masks for detecting self-occlusions. The data will be publicly released.

cs.CV↗

arXiv2020

Automatic Estimation of Self-Reported Pain by Interpretable Representations of Motion Dynamics

We propose an automatic method for pain intensity measurement from video. For each video, pain intensity was measured using the dynamics of facial movement using 66 facial points. Gram matrices formulation was used for facial points trajectory representations on the Riemannian manifold of symmetric positive semi-definite matrices of fixed rank. Curve fitting and temporal alignment were then used to smooth the extracted trajectories. A Support Vector Regression model was then trained to encode the extracted trajectories into ten pain intensity levels consistent with the Visual Analogue Scale for pain intensity measurement. The proposed approach was evaluated using the UNBC McMaster Shoulder Pain Archive and was compared to the state-of-the-art on the same data. Using both 5-fold cross-validation and leave-one-subject-out cross-validation, our results are competitive with respect to state-of-the-art methods.

cs.CV↗

arXiv2020

Modelling the Statistics of Cyclic Activities by Trajectory Analysis on the Manifold of Positive-Semi-Definite Matrices

In this paper, a model is presented to extract statistical summaries to characterize the repetition of a cyclic body action, for instance a gym exercise, for the purpose of checking the compliance of the observed action to a template one and highlighting the parts of the action that are not correctly executed (if any). The proposed system relies on a Riemannian metric to compute the distance between two poses in such a way that the geometry of the manifold where the pose descriptors lie is preserved; a model to detect the begin and end of each cycle; a model to temporally align the poses of different cycles so as to accurately estimate the \emph{cross-sectional} mean and variance of poses across different cycles. The proposed model is demonstrated using gym videos taken from the Internet.

cs.CV↗

arXiv2020

Explaining Autonomous Driving by Learning End-to-End Visual Attention

Current deep learning based autonomous driving approaches yield impressive results also leading to in-production deployment in certain controlled scenarios. One of the most popular and fascinating approaches relies on learning vehicle controls directly from data perceived by sensors. This end-to-end learning paradigm can be applied both in classical supervised settings and using reinforcement learning. Nonetheless the main drawback of this approach as also in other learning problems is the lack of explainability. Indeed, a deep network will act as a black-box outputting predictions depending on previously seen driving patterns without giving any feedback on why such decisions were taken. While to obtain optimal performance it is not critical to obtain explainable outputs from a learned agent, especially in such a safety critical field, it is of paramount importance to understand how the network behaves. This is particularly relevant to interpret failures of such systems. In this work we propose to train an imitation learning based agent equipped with an attention model. The attention model allows us to understand what part of the image has been deemed most important. Interestingly, the use of attention also leads to superior performance in a standard benchmark using the CARLA driving simulator.

cs.CV↗

arXiv2020

Image Retrieval using Multi-scale CNN Features Pooling

In this paper, we address the problem of image retrieval by learning images representation based on the activations of a Convolutional Neural Network. We present an end-to-end trainable network architecture that exploits a novel multi-scale local pooling based on NetVLAD and a triplet mining procedure based on samples difficulty to obtain an effective image representation. Extensive experiments show that our approach is able to reach state-of-the-art results on three standard datasets.

cs.CV↗

arXiv2020

Visual Question Answering for Cultural Heritage

Technology and the fruition of cultural heritage are becoming increasingly more entwined, especially with the advent of smart audio guides, virtual and augmented reality, and interactive installations. Machine learning and computer vision are important components of this ongoing integration, enabling new interaction modalities between user and museum. Nonetheless, the most frequent way of interacting with paintings and statues still remains taking pictures. Yet images alone can only convey the aesthetics of the artwork, lacking is information which is often required to fully understand and appreciate it. Usually this additional knowledge comes both from the artwork itself (and therefore the image depicting it) and from an external source of knowledge, such as an information sheet. While the former can be inferred by computer vision algorithms, the latter needs more structured data to pair visual content with relevant information. Regardless of its source, this information still must be be effectively transmitted to the user. A popular emerging trend in computer vision is Visual Question Answering (VQA), in which users can interact with a neural network by posing questions in natural language and receiving answers about the visual content. We believe that this will be the evolution of smart audio guides for museum visits and simple image browsing on personal smartphones. This will turn the classic audio guide into a smart personal instructor with which the visitor can interact by asking for explanations focused on specific interests. The advantages are twofold: on the one hand the cognitive burden of the visitor will decrease, limiting the flow of information to what the user actually wants to hear; and on the other hand it proposes the most natural way of interacting with a guide, favoring engagement.

cs.CV↗

arXiv2020

Am I Done? Predicting Action Progress in Videos

In this paper we deal with the problem of predicting action progress in videos. We argue that this is an extremely important task since it can be valuable for a wide range of interaction applications. To this end we introduce a novel approach, named ProgressNet, capable of predicting when an action takes place in a video, where it is located within the frames, and how far it has progressed during its execution. To provide a general definition of action progress, we ground our work in the linguistics literature, borrowing terms and concepts to understand which actions can be the subject of progress estimation. As a result, we define a categorization of actions and their phases. Motivated by the recent success obtained from the interaction of Convolutional and Recurrent Neural Networks, our model is based on a combination of the Faster R-CNN framework, to make frame-wise predictions, and LSTM networks, to estimate action progress through time. After introducing two evaluation protocols for the task at hand, we demonstrate the capability of our model to effectively predict action progress on the UCF-101 and J-HMDB datasets.

cs.CV↗

arXiv2019

Text-to-Image Synthesis Based on Machine Generated Captions

Text to Image Synthesis refers to the process of automatic generation of a photo-realistic image starting from a given text and is revolutionizing many real-world applications. In order to perform such process it is necessary to exploit datasets containing captioned images, meaning that each image is associated with one (or more) captions describing it. Despite the abundance of uncaptioned images datasets, the number of captioned datasets is limited. To address this issue, in this paper we propose an approach capable of generating images starting from a given text using conditional GANs trained on uncaptioned images dataset. In particular, uncaptioned images are fed to an Image Captioning Module to generate the descriptions. Then, the GAN Module is trained on both the input image and the machine-generated caption. To evaluate the results, the performance of our solution is compared with the results obtained by the unconditional GAN. For the experiments, we chose to use the uncaptioned dataset LSUN bedroom. The results obtained in our study are preliminary but still promising.

cs.LG↗

arXiv2019

Fitting, Comparison, and Alignment of Trajectories on Positive Semi-Definite Matrices with Application to Action Recognition

In this paper, we tackle the problem of action recognition using body skeletons extracted from video sequences. Our approach lies in the continuity of recent works representing video frames by Gramian matrices that describe a trajectory on the Riemannian manifold of positive-semidefinite matrices of fixed rank. In comparison with previous works, the manifold of fixed-rank positive-semidefinite matrices is here endowed with a different metric, and we resort to different algorithms for the curve fitting and temporal alignment steps. We evaluated our approach on three publicly available datasets (UTKinect-Action3D, KTH-Action and UAV-Gesture). The results of the proposed approach are competitive with respect to state-of-the-art methods, while only involving body skeletons.

cs.CV↗

arXiv2019

Fix Your Features: Stationary and Maximally Discriminative Embeddings using Regular Polytope (Fixed Classifier) Networks

Neural networks are widely used as a model for classification in a large variety of tasks. Typically, a learnable transformation (i.e. the classifier) is placed at the end of such models returning a value for each class used for classification. This transformation plays an important role in determining how the generated features change during the learning process. In this work we argue that this transformation not only can be fixed (i.e. set as non trainable) with no loss of accuracy, but it can also be used to learn stationary and maximally discriminative embeddings. We show that the stationarity of the embedding and its maximal discriminative representation can be theoretically justified by setting the weights of the fixed classifier to values taken from the coordinate vertices of three regular polytopes available in $\mathbb{R}^d$, namely: the $d$-Simplex, the $d$-Cube and the $d$-Orthoplex. These regular polytopes have the maximal amount of symmetry that can be exploited to generate stationary features angularly centered around their corresponding fixed weights. Our approach improves and broadens the concept of a fixed classifier, recently proposed in \cite{hoffer2018fix}, to a larger class of fixed classifier models. Experimental results confirm both the theoretical analysis and the generalization capability of the proposed method.

cs.CV↗

arXiv2019

Additional Baseline Metrics for the paper "Extended YouTube Faces: a Dataset for Heterogeneous Open-Set Face Identification"

In this report, we provide additional and corrected results for the paper "Extended YouTube Faces: a Dataset for Heterogeneous Open-Set Face Identification". After further investigations, we discovered and corrected wrongly labeled images and incorrect identities. This forced us to re-generate the evaluation protocol for the new data; in doing so, we also reproduced and extended the experimental results with other standard metrics and measures used in the literature. The reader can refer to the original paper for additional details regarding the data collection procedure and recognition pipeline.

cs.CV↗

arXiv2018

Semantic Road Layout Understanding by Generative Adversarial Inpainting

Autonomous driving is becoming a reality, yet vehicles still need to rely on complex sensor fusion to understand the scene they act in. The ability to discern static environment and dynamic entities provides a comprehension of the road layout that poses constraints to the reasoning process about moving objects. We pursue this through a GAN-based semantic segmentation inpainting model to remove all dynamic objects from the scene and focus on understanding its static components such as streets, sidewalks and buildings. We evaluate this task on the Cityscapes dataset and on a novel synthetically generated dataset obtained with the CARLA simulator and specifically designed to quantitatively evaluate semantic segmentation inpaintings. We compare our methods with a variety of baselines working both in the RGB and segmentation domains.

cs.CV↗