Abstract: The recognition of food image is an interesting research topic, in which its applicability in the creation of nutritional diaries stands out with the aim of improving the quality of life of people with a chronic disease (e.g. diabetes, heart disease) or prone to acquire it (e.g. people with overweight or obese). For a food recognition system to be useful in real applications, it is necessary to recognize a huge number of different foods. We argue that for very large scale classification, a traditional flat classifier is not enough to acquire an acceptable result. To address this, we propose a method that performs prediction with local classifiers, based on a class hierarchy, or with flat classifier. We decide which approach to use, depending on the analysis of both the Epistemic Uncertainty obtained for the image in the children classifiers and the prediction of the parent classifier. When our criterion is met, the final prediction is obtained with the respective local classifier; otherwise, with the flat classifier. From the results, we can see that the proposed method improves the classification performance compared to the use of a single flat classifier.

Abstract: One interesting publicity application for Smart City environments is recognizing brand information contained in urban advertising panels. For such a purpose, a previous stage is to accurately detect and locate the position of these panels in images. This work presents an effective solution to this problem using a Single Shot Detector (SSD) based on a deep neural network architecture that minimizes the number of false detections under multiple variable conditions regarding the panels and the scene. Achieved experimental results using the Intersection over Union (IoU) accuracy metric make this proposal applicable in real complex urban images.

Abstract: Action recognition pipelines that use Recurrent Neural Networks (RNN) are currently 5–10% less accurate than Convolutional Neural Networks (CNN). While most works that use RNNs employ a 2D CNN on each frame to extract descriptors for action recognition, we extract spatiotemporal features from a 3D CNN and then learn the temporal relationship of these descriptors through a stacked residual recurrent neural network (Res-RNN). We introduce for the first time residual learning to counter the degradation problem in multi-layer RNNs, which have been successful for temporal aggregation in two-stream action recognition pipelines. Finally, we use a late fusion strategy to combine RGB and optical flow data of the two-stream Res-RNN. Experimental results show that the proposed pipeline achieves competitive results on UCF-101 and state of-the-art results for RNN-like architectures on the challenging HMDB-51 dataset.

Abstract: Future video prediction is an ill-posed Computer Vision problem that recently received much attention. Its main challenges are the high variability in video content, the propagation of errors through time, and the non-specificity of the future frames: given a sequence of past frames there is a continuous distribution of possible futures. This work introduces bijective Gated Recurrent Units, a double mapping between the input and output of a GRU layer. This allows for recurrent auto-encoders with state sharing between encoder and decoder, stratifying the sequence representation and helping to prevent capacity problems. We show how with this topology only the encoder or decoder needs to be applied for input encoding and prediction, respectively. This reduces the computational cost and avoids re-encoding the predictions when generating a sequence of frames, mitigating the propagation of errors. Furthermore, it is possible to remove layers from an already trained model, giving an insight to the role performed by each layer and making the model more explainable. We evaluate our approach on three video datasets, outperforming state of the art prediction results on MMNIST and UCF101, and obtaining competitive results on KTH with 2 and 3 times less memory usage and computational cost than the best scored approach.

Abstract: Facial expressions are combinations of basic components called Action Units (AU). Recognizing AUs is key for general facial expression analysis. Recently, efforts in automatic AU recognition have been dedicated to learning combinations of local features and to exploiting correlations between AUs. We propose a deep neural architecture that tackles both problems by combining learned local and global features in its initial stages and replicating a message passing algorithm between classes similar to a graphical model inference approach in later stages. We show that by training the model end-to-end with increased supervision we improve state-of-the-art by 5.3% and 8.2% performance on BP4D and DISFA datasets, respectively.

Abstract: ransferring knowledge of pre-trained networks to new domains by means of fine-tuning is a widely used practice for applications based on discriminative models. To the best of our knowledge this practice has not been studied within the context of generative deep networks. Therefore, we study domain adaptation applied to image generation with generative adversarial networks. We evaluate several aspects of domain adaptation, including the impact of target domain size, the relative distance between source and target domain, and the initialization of conditional GANs. Our results show that using knowledge from pre-trained networks can shorten the convergence time and can significantly improve the quality of the generated images, especially when target data is limited. We show that these conclusions can also be drawn for conditional GANs even when the pre-trained model was trained without conditioning. Our results also suggest that density is more important than diversity and a dataset with one or few densely sampled classes is a better source model than more diverse datasets such as ImageNet or Places.

Abstract: Recognizing visual categories from semantic descriptions is a promising way to extend the capability of a visual classifier beyond the concepts represented in the training data (i.e. seen categories). This problem is addressed by (generalized) zero-shot learning methods (GZSL), which leverage semantic descriptions that connect them to seen categories (e.g. label embedding, attributes). Conventional GZSL are designed mostly for object recognition. In this paper we focus on zero-shot scene recognition, a more challenging setting with hundreds of categories where their differences can be subtle and often localized in certain objects or regions. Conventional GZSL representations are not rich enough to capture these local discriminative differences. Addressing these limitations, we propose a feature generation framework with two novel components: 1) multiple sources of semantic information (i.e. attributes, word embeddings and descriptions), 2) region descriptions that can enhance scene discrimination. To generate synthetic visual features we propose a two-step generative approach, where local descriptions are sampled and used as conditions to generate visual features. The generated features are then aggregated and used together with real features to train a joint classifier. In order to evaluate the proposed method, we introduce a new dataset for zero-shot scene recognition with multi-semantic annotations. Experimental results on the proposed dataset and SUN Attribute dataset illustrate the effectiveness of the proposed method.

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.