Enabling machines to solve computer vision tasks with natural language components can greatly improve human interaction with computers. In this thesis, we address vision and language tasks with deep learning methods that explicitly localize relevant visual evidence. Spatial evidence localization in images enhances the interpretability of the model, while temporal localization in video is necessary to remove irrelevant content. We apply our methods to various vision and language tasks, including visual question answering, temporal activity detection, dense video captioning and cross-modal retrieval. First, we tackle the problem of image question answering, which requires the model to predict answers to questions posed about images. We design a memory network with a question-guided spatial attention mechanism which assigns higher weights to regions that are more relevant to the question. The visual evidence used to derive the answer can be shown by visualizing the attention weights in images. We then address the problem of localizing temporal evidence in videos. For most language/vision tasks, only part of the video is relevant to the linguistic component, so we need to detect these relevant events in videos. We propose an end-to-end model for temporal activity detection, which can detect arbitrary length activities by coordinate regression with respect to anchors and contains a proposal stage to filter out background segments, saving computation time. We further extend activity category detection to event captioning, which can express richer semantic meaning compared to a class label. This derives the problem of dense video captioning, which involves two sub-problems: localizing distinct events in long video and generating captions for the localized events. We propose an end-to-end hierarchical captioning model with vision and language context modeling in which the captioning training affects the activity localization. Lastly, the task of text-to-clip video retrieval requires one to localize the specified query instead of detecting and captioning all events. We propose a model based on the early fusion of words and visual features, outperforming standard approaches which embed the whole sentence before performing late feature fusion. Furthermore, we use queries to regulate the proposal network to generate query related proposals. In conclusion, our proposed visual localization mechanism applies across a variety of vision and language tasks and achieves state-of-the-art results. Together with the inference module, our work can contribute to solving other tasks such as video question answering in future research.

Modern deep learning methods have boosted research progress in visual recognition and text understanding but it is a non-trivial task to unite these advances from both disciplines. In this thesis, we develop models and techniques that allow us to connect natural language and visual content enabling automatic video subtitling, visual grounding, and text-based image search. Such models could be useful in a wide range of applications in robotics and human-computer interaction bridging the gap in vision and language understanding. First, we develop a model that generates natural language descriptions of the main activities and scenes depicted in short videos. While previous methods were constrained to a predefined list of objects, actions, or attributes, our model learns to generate descriptions directly from raw pixels. The model exploits available audio information and the video’s category (e.g., cooking, movie, education) to generate more relevant and coherent sentences. Then, we introduce a technique for visual grounding of generated sentences using the same video description model. Our approach allows for explaining the model’s prediction by localizing salient video regions for corresponding words in the generated sentence. Lastly, we address the problem of image retrieval. Existing cross-modal retrieval methods work by learning a common embedding space for different modalities using parallel data such as images and their accompanying descriptions. Instead, we focus on the case when images are connected by relative annotations: given the context set as an image and its metadata, the user can specify desired semantic changes using natural language instructions. The model needs to capture distinctive visual differences between image pairs as described by the user. Our approach enables interactive image search such that the natural language feedback significantly improves the efficacy of image retrieval. We show that the proposed methods advance the state-of-the-art for video captioning and image retrieval tasks in terms of both accuracy and interpretability.

No description available.

No description available.

Ces dernières années, le domaine de l’apprentissage profond a connu des progrès énormes dans des applications allant de la génération d’images, détection d’objets, modélisation du langage à la réponse aux questions visuelles. Les approches classiques telles que l’apprentissage supervisé nécessitent de grandes quantités de données étiquetées et spécifiques à la tâches. Cependant, celles-ci sont parfois coûteuses, peu pratiques, ou trop longues à collecter. La modélisation efficace en données, qui comprend des techniques comme l’apprentissage few-shot (à partir de peu d’exemples) et l’apprentissage self-supervised (auto-supervisé), tentent de remédier au manque de données spécifiques à la tâche en exploitant de grandes quantités de données plus “générales”. Les progrès de l’apprentissage profond, et en particulier de l’apprentissage few-shot, s’appuient sur les benchmarks (suites d’évaluation), les métriques d’évaluation et les jeux de données, car ceux-ci sont utilisés pour tester et départager différentes méthodes sur des tâches précises, et identifier l’état de l’art. Cependant, du fait qu’il s’agit de versions idéalisées de la tâche à résoudre, les benchmarks sont rarement équivalents à la tâche originelle, et peuvent avoir plusieurs limitations qui entravent leur rôle de sélection des directions de recherche les plus prometteuses. De plus, la définition de métriques d’évaluation pertinentes peut être difficile, en particulier dans le cas de sorties structurées et en haute dimension, telles que des images, de l’audio, de la parole ou encore du texte. Cette thèse discute des limites et des perspectives des benchmarks existants, des fonctions de coût (training losses) et des métriques d’évaluation (evaluation metrics), en mettant l’accent sur la modélisation générative - les Réseaux Antagonistes Génératifs (GANs) en particulier - et la modélisation efficace des données, qui comprend l’apprentissage few-shot et self-supervised. La première contribution est une discussion de la tâche de modélisation générative, suivie d’une exploration des propriétés théoriques et empiriques des fonctions de coût des GANs. La deuxième contribution est une discussion sur la limitation des few-shot classification benchmarks, certains ne nécessitant pas de généralisation à de nouvelles sémantiques de classe pour être résolus, et la proposition d’une méthode de base pour les résoudre sans étiquettes en phase de testing. La troisième contribution est une revue sur les méthodes few-shot et self-supervised de détection d’objets , qui souligne les limites et directions de recherche prometteuses. Enfin, la quatrième contribution est une méthode efficace en données pour la description de vidéo qui exploite des jeux de données texte et vidéo non supervisés. / In recent years, the field of deep learning has seen tremendous progress for applications ranging from image generation, object detection, language modeling, to visual question answering. Classic approaches such as supervised learning require large amounts of task-specific and labeled data, which may be too expensive, time-consuming, or impractical to collect. Data-efficient methods, such as few-shot and self-supervised learning, attempt to deal with the limited availability of task-specific data by leveraging large amounts of general data. Progress in deep learning, and in particular, few-shot learning, is largely driven by the relevant benchmarks, evaluation metrics, and datasets. They are used to test and compare different methods on a given task, and determine the state-of-the-art. However, due to being idealized versions of the task to solve, benchmarks are rarely equivalent to the original task, and can have several limitations which hinder their role of identifying the most promising research directions. Moreover, defining meaningful evaluation metrics can be challenging, especially in the case of high-dimensional and structured outputs, such as images, audio, speech, or text. This thesis discusses the limitations and perspectives of existing benchmarks, training losses, and evaluation metrics, with a focus on generative modeling—Generative Adversarial Networks (GANs) in particular—and data-efficient modeling, which includes few-shot and self-supervised learning. The first contribution is a discussion of the generative modeling task, followed by an exploration of theoretical and empirical properties of the GAN loss. The second contribution is a discussion of a limitation of few-shot classification benchmarks, which is that they may not require class semantic generalization to be solved, and the proposal of a baseline method for solving them without test-time labels. The third contribution is a survey of few-shot and self-supervised object detection, which points out the limitations and promising future research for the field. Finally, the fourth contribution is a data-efficient method for video captioning, which leverages unsupervised text and video datasets, and explores several multimodal pretraining strategies.