Javier Selva, Anders S. Johansen, Sergio Escalera, Kamal Nasrollahi, Thomas B. Moeslund, & Albert Clapes. (2023). Video transformers: A survey. TPAMI - IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(11), 12922–12943.
Abstract: Transformer models have shown great success handling long-range interactions, making them a promising tool for modeling video. However, they lack inductive biases and scale quadratically with input length. These limitations are further exacerbated when dealing with the high dimensionality introduced by the temporal dimension. While there are surveys analyzing the advances of Transformers for vision, none focus on an in-depth analysis of video-specific designs. In this survey, we analyze the main contributions and trends of works leveraging Transformers to model video. Specifically, we delve into how videos are handled at the input level first. Then, we study the architectural changes made to deal with video more efficiently, reduce redundancy, re-introduce useful inductive biases, and capture long-term temporal dynamics. In addition, we provide an overview of different training regimes and explore effective self-supervised learning strategies for video. Finally, we conduct a performance comparison on the most common benchmark for Video Transformers (i.e., action classification), finding them to outperform 3D ConvNets even with less computational complexity.
Keywords: Artificial Intelligence; Computer Vision; Self-Attention; Transformers; Video Representations
|
Akhil Gurram, Ahmet Faruk Tuna, Fengyi Shen, Onay Urfalioglu, & Antonio Lopez. (2021). Monocular Depth Estimation through Virtual-world Supervision and Real-world SfM Self-Supervision. TITS - IEEE Transactions on Intelligent Transportation Systems, 23(8), 12738–12751.
Abstract: Depth information is essential for on-board perception in autonomous driving and driver assistance. Monocular depth estimation (MDE) is very appealing since it allows for appearance and depth being on direct pixelwise correspondence without further calibration. Best MDE models are based on Convolutional Neural Networks (CNNs) trained in a supervised manner, i.e., assuming pixelwise ground truth (GT). Usually, this GT is acquired at training time through a calibrated multi-modal suite of sensors. However, also using only a monocular system at training time is cheaper and more scalable. This is possible by relying on structure-from-motion (SfM) principles to generate self-supervision. Nevertheless, problems of camouflaged objects, visibility changes, static-camera intervals, textureless areas, and scale ambiguity, diminish the usefulness of such self-supervision. In this paper, we perform monocular depth estimation by virtual-world supervision (MonoDEVS) and real-world SfM self-supervision. We compensate the SfM self-supervision limitations by leveraging virtual-world images with accurate semantic and depth supervision and addressing the virtual-to-real domain gap. Our MonoDEVSNet outperforms previous MDE CNNs trained on monocular and even stereo sequences.
|
Cristhian Aguilera, Fernando Barrera, Felipe Lumbreras, Angel Sappa, & Ricardo Toledo. (2012). Multispectral Image Feature Points. SENS - Sensors, 12(9), 12661–12672.
Abstract: Far-Infrared and Visible Spectrum images. It allows matching interest points on images of the same scene but acquired in different spectral bands. Initially, points of interest are detected on both images through a SIFT-like based scale space representation. Then, these points are characterized using an Edge Oriented Histogram (EOH) descriptor. Finally, points of interest from multispectral images are matched by finding nearest couples using the information from the descriptor. The provided experimental results and comparisons with similar methods show both the validity of the proposed approach as well as the improvements it offers with respect to the current state-of-the-art.
Keywords: multispectral image descriptor; color and infrared images; feature point descriptor
|
Senmao Li, Joost Van de Weijer, Yaxing Wang, Fahad Shahbaz Khan, Meiqin Liu, & Jian Yang. (2023). 3D-Aware Multi-Class Image-to-Image Translation with NeRFs. In 36th IEEE Conference on Computer Vision and Pattern Recognition (pp. 12652–12662).
Abstract: Recent advances in 3D-aware generative models (3D-aware GANs) combined with Neural Radiance Fields (NeRF) have achieved impressive results. However no prior works investigate 3D-aware GANs for 3D consistent multiclass image-to-image (3D-aware 121) translation. Naively using 2D-121 translation methods suffers from unrealistic shape/identity change. To perform 3D-aware multiclass 121 translation, we decouple this learning process into a multiclass 3D-aware GAN step and a 3D-aware 121 translation step. In the first step, we propose two novel techniques: a new conditional architecture and an effective training strategy. In the second step, based on the well-trained multiclass 3D-aware GAN architecture, that preserves view-consistency, we construct a 3D-aware 121 translation system. To further reduce the view-consistency problems, we propose several new techniques, including a U-net-like adaptor network design, a hierarchical representation constrain and a relative regularization loss. In exten-sive experiments on two datasets, quantitative and qualitative results demonstrate that we successfully perform 3D-aware 121 translation with multi-view consistency. Code is available in 3DI2I.
|
Victor M. Campello, Carlos Martin-Isla, Cristian Izquierdo, Andrea Guala, Jose F. Rodriguez Palomares, David Vilades, et al. (2022). Minimising multi-centre radiomics variability through image normalisation: a pilot study. ScR - Scientific Reports, 12(1), 12532.
Abstract: Radiomics is an emerging technique for the quantification of imaging data that has recently shown great promise for deeper phenotyping of cardiovascular disease. Thus far, the technique has been mostly applied in single-centre studies. However, one of the main difficulties in multi-centre imaging studies is the inherent variability of image characteristics due to centre differences. In this paper, a comprehensive analysis of radiomics variability under several image- and feature-based normalisation techniques was conducted using a multi-centre cardiovascular magnetic resonance dataset. 218 subjects divided into healthy (n = 112) and hypertrophic cardiomyopathy (n = 106, HCM) groups from five different centres were considered. First and second order texture radiomic features were extracted from three regions of interest, namely the left and right ventricular cavities and the left ventricular myocardium. Two methods were used to assess features’ variability. First, feature distributions were compared across centres to obtain a distribution similarity index. Second, two classification tasks were proposed to assess: (1) the amount of centre-related information encoded in normalised features (centre identification) and (2) the generalisation ability for a classification model when trained on these features (healthy versus HCM classification). The results showed that the feature-based harmonisation technique ComBat is able to remove the variability introduced by centre information from radiomic features, at the expense of slightly degrading classification performance. Piecewise linear histogram matching normalisation gave features with greater generalisation ability for classification ( balanced accuracy in between 0.78 ± 0.08 and 0.79 ± 0.09). Models trained with features from images without normalisation showed the worst performance overall ( balanced accuracy in between 0.45 ± 0.28 and 0.60 ± 0.22). In conclusion, centre-related information removal did not imply good generalisation ability for classification.
|
Ali Furkan Biten, Lluis Gomez, Marçal Rusiñol, & Dimosthenis Karatzas. (2019). Good News, Everyone! Context driven entity-aware captioning for news images. In 32nd IEEE Conference on Computer Vision and Pattern Recognition (pp. 12458–12467).
Abstract: Current image captioning systems perform at a merely descriptive level, essentially enumerating the objects in the scene and their relations. Humans, on the contrary, interpret images by integrating several sources of prior knowledge of the world. In this work, we aim to take a step closer to producing captions that offer a plausible interpretation of the scene, by integrating such contextual information into the captioning pipeline. For this we focus on the captioning of images used to illustrate news articles. We propose a novel captioning method that is able to leverage contextual information provided by the text of news articles associated with an image. Our model is able to selectively draw information from the article guided by visual cues, and to dynamically extend the output dictionary to out-of-vocabulary named entities that appear in the context source. Furthermore we introduce“ GoodNews”, the largest news image captioning dataset in the literature and demonstrate state-of-the-art results.
|
Anjan Dutta, Pau Riba, Josep Llados, & Alicia Fornes. (2020). Hierarchical Stochastic Graphlet Embedding for Graph-based Pattern Recognition. NEUCOMA - Neural Computing and Applications, 32, 11579–11596.
Abstract: Despite being very successful within the pattern recognition and machine learning community, graph-based methods are often unusable because of the lack of mathematical operations defined in graph domain. Graph embedding, which maps graphs to a vectorial space, has been proposed as a way to tackle these difficulties enabling the use of standard machine learning techniques. However, it is well known that graph embedding functions usually suffer from the loss of structural information. In this paper, we consider the hierarchical structure of a graph as a way to mitigate this loss of information. The hierarchical structure is constructed by topologically clustering the graph nodes and considering each cluster as a node in the upper hierarchical level. Once this hierarchical structure is constructed, we consider several configurations to define the mapping into a vector space given a classical graph embedding, in particular, we propose to make use of the stochastic graphlet embedding (SGE). Broadly speaking, SGE produces a distribution of uniformly sampled low-to-high-order graphlets as a way to embed graphs into the vector space. In what follows, the coarse-to-fine structure of a graph hierarchy and the statistics fetched by the SGE complements each other and includes important structural information with varied contexts. Altogether, these two techniques substantially cope with the usual information loss involved in graph embedding techniques, obtaining a more robust graph representation. This fact has been corroborated through a detailed experimental evaluation on various benchmark graph datasets, where we outperform the state-of-the-art methods.
|
Armin Mehri, Parichehr Behjati, & Angel Sappa. (2023). TnTViT-G: Transformer in Transformer Network for Guidance Super Resolution. ACCESS - IEEE Access, 11, 11529–11540.
Abstract: Image Super Resolution is a potential approach that can improve the image quality of low-resolution optical sensors, leading to improved performance in various industrial applications. It is important to emphasize that most state-of-the-art super resolution algorithms often use a single channel of input data for training and inference. However, this practice ignores the fact that the cost of acquiring high-resolution images in various spectral domains can differ a lot from one another. In this paper, we attempt to exploit complementary information from a low-cost channel (visible image) to increase the image quality of an expensive channel (infrared image). We propose a dual stream Transformer-based super resolution approach that uses the visible image as a guide to super-resolve another spectral band image. To this end, we introduce Transformer in Transformer network for Guidance super resolution, named TnTViT-G, an efficient and effective method that extracts the features of input images via different streams and fuses them together at various stages. In addition, unlike other guidance super resolution approaches, TnTViT-G is not limited to a fixed upsample size and it can generate super-resolved images of any size. Extensive experiments on various datasets show that the proposed model outperforms other state-of-the-art super resolution approaches. TnTViT-G surpasses state-of-the-art methods by up to 0.19∼2.3dB , while it is memory efficient.
|
Yuyang Liu, Yang Cong, Dipam Goswami, Xialei Liu, & Joost Van de Weijer. (2023). Augmented Box Replay: Overcoming Foreground Shift for Incremental Object Detection. In 20th IEEE International Conference on Computer Vision (pp. 11367–11377).
Abstract: In incremental learning, replaying stored samples from previous tasks together with current task samples is one of the most efficient approaches to address catastrophic forgetting. However, unlike incremental classification, image replay has not been successfully applied to incremental object detection (IOD). In this paper, we identify the overlooked problem of foreground shift as the main reason for this. Foreground shift only occurs when replaying images of previous tasks and refers to the fact that their background might contain foreground objects of the current task. To overcome this problem, a novel and efficient Augmented Box Replay (ABR) method is developed that only stores and replays foreground objects and thereby circumvents the foreground shift problem. In addition, we propose an innovative Attentive RoI Distillation loss that uses spatial attention from region-of-interest (RoI) features to constrain current model to focus on the most important information from old model. ABR significantly reduces forgetting of previous classes while maintaining high plasticity in current classes. Moreover, it considerably reduces the storage requirements when compared to standard image replay. Comprehensive experiments on Pascal-VOC and COCO datasets support the state-of-the-art performance of our model.
|
Iban Berganzo-Besga, Hector A. Orengo, Felipe Lumbreras, Aftab Alam, Rosie Campbell, Petrus J Gerrits, et al. (2023). Curriculum learning-based strategy for low-density archaeological mound detection from historical maps in India and Pakistan. ScR - Scientific Reports, 13, 11257.
Abstract: This paper presents two algorithms for the large-scale automatic detection and instance segmentation of potential archaeological mounds on historical maps. Historical maps present a unique source of information for the reconstruction of ancient landscapes. The last 100 years have seen unprecedented landscape modifications with the introduction and large-scale implementation of mechanised agriculture, channel-based irrigation schemes, and urban expansion to name but a few. Historical maps offer a window onto disappearing landscapes where many historical and archaeological elements that no longer exist today are depicted. The algorithms focus on the detection and shape extraction of mound features with high probability of being archaeological settlements, mounds being one of the most commonly documented archaeological features to be found in the Survey of India historical map series, although not necessarily recognised as such at the time of surveying. Mound features with high archaeological potential are most commonly depicted through hachures or contour-equivalent form-lines, therefore, an algorithm has been designed to detect each of those features. Our proposed approach addresses two of the most common issues in archaeological automated survey, the low-density of archaeological features to be detected, and the small amount of training data available. It has been applied to all types of maps available of the historic 1″ to 1-mile series, thus increasing the complexity of the detection. Moreover, the inclusion of synthetic data, along with a Curriculum Learning strategy, has allowed the algorithm to better understand what the mound features look like. Likewise, a series of filters based on topographic setting, form, and size have been applied to improve the accuracy of the models. The resulting algorithms have a recall value of 52.61% and a precision of 82.31% for the hachure mounds, and a recall value of 70.80% and a precision of 70.29% for the form-line mounds, which allowed the detection of nearly 6000 mound features over an area of 470,500 km2, the largest such approach to have ever been applied. If we restrict our focus to the maps most similar to those used in the algorithm training, we reach recall values greater than 60% and precision values greater than 90%. This approach has shown the potential to implement an adaptive algorithm that allows, after a small amount of retraining with data detected from a new map, a better general mound feature detection in the same map.
|
Domicele Jonauskaite, Lucia Camenzind, C. Alejandro Parraga, Cecile N Diouf, Mathieu Mercapide Ducommun, Lauriane Müller, et al. (2021). Colour-emotion associations in individuals with red-green colour blindness. PeerJ, 9, e11180.
Abstract: Colours and emotions are associated in languages and traditions. Some of us may convey sadness by saying feeling blue or by wearing black clothes at funerals. The first example is a conceptual experience of colour and the second example is an immediate perceptual experience of colour. To investigate whether one or the other type of experience more strongly drives colour-emotion associations, we tested 64 congenitally red-green colour-blind men and 66 non-colour-blind men. All participants associated 12 colours, presented as terms or patches, with 20 emotion concepts, and rated intensities of the associated emotions. We found that colour-blind and non-colour-blind men associated similar emotions with colours, irrespective of whether colours were conveyed via terms (r = .82) or patches (r = .80). The colour-emotion associations and the emotion intensities were not modulated by participants' severity of colour blindness. Hinting at some additional, although minor, role of actual colour perception, the consistencies in associations for colour terms and patches were higher in non-colour-blind than colour-blind men. Together, these results suggest that colour-emotion associations in adults do not require immediate perceptual colour experiences, as conceptual experiences are sufficient.
Keywords: Affect; Chromotherapy; Colour cognition; Colour vision deficiency; Cross-modal correspondences; Daltonism; Deuteranopia; Dichromatic; Emotion; Protanopia.
|
Swathikiran Sudhakaran, Sergio Escalera, & Oswald Lanz. (2023). Gate-Shift-Fuse for Video Action Recognition. TPAMI - IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(9), 10913–10928.
Abstract: Convolutional Neural Networks are the de facto models for image recognition. However 3D CNNs, the straight forward extension of 2D CNNs for video recognition, have not achieved the same success on standard action recognition benchmarks. One of the main reasons for this reduced performance of 3D CNNs is the increased computational complexity requiring large scale annotated datasets to train them in scale. 3D kernel factorization approaches have been proposed to reduce the complexity of 3D CNNs. Existing kernel factorization approaches follow hand-designed and hard-wired techniques. In this paper we propose Gate-Shift-Fuse (GSF), a novel spatio-temporal feature extraction module which controls interactions in spatio-temporal decomposition and learns to adaptively route features through time and combine them in a data dependent manner. GSF leverages grouped spatial gating to decompose input tensor and channel weighting to fuse the decomposed tensors. GSF can be inserted into existing 2D CNNs to convert them into an efficient and high performing spatio-temporal feature extractor, with negligible parameter and compute overhead. We perform an extensive analysis of GSF using two popular 2D CNN families and achieve state-of-the-art or competitive performance on five standard action recognition benchmarks.
Keywords: Action Recognition; Video Classification; Spatial Gating; Channel Fusion
|
Alejandro Cartas, Petia Radeva, & Mariella Dimiccoli. (2021). Modeling long-term interactions to enhance action recognition. In 25th International Conference on Pattern Recognition (pp. 10351–10358).
Abstract: In this paper, we propose a new approach to under-stand actions in egocentric videos that exploits the semantics of object interactions at both frame and temporal levels. At the frame level, we use a region-based approach that takes as input a primary region roughly corresponding to the user hands and a set of secondary regions potentially corresponding to the interacting objects and calculates the action score through a CNN formulation. This information is then fed to a Hierarchical LongShort-Term Memory Network (HLSTM) that captures temporal dependencies between actions within and across shots. Ablation studies thoroughly validate the proposed approach, showing in particular that both levels of the HLSTM architecture contribute to performance improvement. Furthermore, quantitative comparisons show that the proposed approach outperforms the state-of-the-art in terms of action recognition on standard benchmarks,without relying on motion information
|
Swathikiran Sudhakaran, Sergio Escalera, & Oswald Lanz. (2019). LSTA: Long Short-Term Attention for Egocentric Action Recognition. In 32nd IEEE Conference on Computer Vision and Pattern Recognition (pp. 9946–9955).
Abstract: Egocentric activity recognition is one of the most challenging tasks in video analysis. It requires a fine-grained discrimination of small objects and their manipulation. While some methods base on strong supervision and attention mechanisms, they are either annotation consuming or do not take spatio-temporal patterns into account. In this paper we propose LSTA as a mechanism to focus on features from spatial relevant parts while attention is being tracked smoothly across the video sequence. We demonstrate the effectiveness of LSTA on egocentric activity recognition with an end-to-end trainable two-stream architecture, achieving state-of-the-art performance on four standard benchmarks.
|
Siyang Song, Micol Spitale, Cheng Luo, German Barquero, Cristina Palmero, Sergio Escalera, et al. (2023). REACT2023: The First Multiple Appropriate Facial Reaction Generation Challenge. In Proceedings of the 31st ACM International Conference on Multimedia (9620–9624).
Abstract: The Multiple Appropriate Facial Reaction Generation Challenge (REACT2023) is the first competition event focused on evaluating multimedia processing and machine learning techniques for generating human-appropriate facial reactions in various dyadic interaction scenarios, with all participants competing strictly under the same conditions. The goal of the challenge is to provide the first benchmark test set for multi-modal information processing and to foster collaboration among the audio, visual, and audio-visual behaviour analysis and behaviour generation (a.k.a generative AI) communities, to compare the relative merits of the approaches to automatic appropriate facial reaction generation under different spontaneous dyadic interaction conditions. This paper presents: (i) the novelties, contributions and guidelines of the REACT2023 challenge; (ii) the dataset utilized in the challenge; and (iii) the performance of the baseline systems on the two proposed sub-challenges: Offline Multiple Appropriate Facial Reaction Generation and Online Multiple Appropriate Facial Reaction Generation, respectively. The challenge baseline code is publicly available at https://github.com/reactmultimodalchallenge/baseline_react2023.
|