We introduce SaltiNet, a deep neural network for scanpath prediction trained on 360-degree images. The model is based on a temporal-aware novel representation of saliency information named the saliency volume. The first part of the network consists of a model trained to generate saliency volumes, whose parameters are fit by back-propagation computed from a binary cross entropy (BCE) loss over downsampled versions of the saliency volumes. Sampling strategies over these volumes are used to generate scanpaths over the 360-degree images. Our experiments show the advantages of using saliency volumes, and how they can be used for related tasks. Our source code and trained models available at https://github.com/massens/saliency-360salient-2017.
This paper introduces an unsupervised framework to extract semantically rich features for video representation. Inspired by how the human visual system groups objects based on motion cues, we propose a deep convolutional neural network that disentangles motion, foreground and background information. The proposed architecture consists of a 3D convolutional feature encoder for blocks of 16 frames, which is trained for reconstruction tasks over the first and last frames of the sequence. A preliminary supervised experiment was conducted to verify the feasibility of proposed method by training the model with a fraction of videos from the UCF-101 dataset taking as ground truth the bounding boxes around the activity regions. Qualitative results indicate that the network can successfully segment foreground and background in videos as well as update the foreground appearance based on disentangled motion features. The benefits of these learned features are shown in a discriminative classification task, where initializing the network with the proposed pretraining method outperforms both random initialization and autoencoder pretraining. Our model and source code are publicly available at https://imatge-upc.github.io/unsupervised-2017-cvprw/ .
Image retrieval in realistic scenarios targets large dynamic datasets of unlabeled images. In these cases, training or fine-tuning a model every time new images are added to the database is neither efficient nor scalable. Convolutional neural networks trained for image classification over large datasets have been proven effective feature extractors for image retrieval. The most successful approaches are based on encoding the activations of convolutional layers, as they convey the image spatial information. In this paper, we go beyond this spatial information and propose a local-aware encoding of convolutional features based on semantic information predicted in the target image. To this end, we obtain the most discriminative regions of an image using Class Activation Maps (CAMs). CAMs are based on the knowledge contained in the network and therefore, our approach, has the additional advantage of not requiring external information. In addition, we use CAMs to generate object proposals during an unsupervised re-ranking stage after a first fast search. Our experiments on two public available datasets for instance retrieval, Oxford5k and Paris6k, demonstrate the competitiveness of our approach outperforming the current state-of-the-art when using off-the-shelf models trained on ImageNet. The source code and model used in this paper are publicly available at http://imatge-upc.github.io/retrieval-2017-cam/.
This work presents a retrieval pipeline and evaluation scheme for the problem of finding the last appearance of personal objects in a large dataset of images captured from a wearable camera. Each personal object is modelled by a small set of images that define a query for a visual search engine.The retrieved results are reranked considering the temporal timestamps of the images to increase the relevance of the later detections. Finally, a temporal interleaving of the results is introduced for robustness against false detections. The Mean Reciprocal Rank is proposed as a metric to evaluate this problem. This application could help into developing personal assistants capable of helping users when they do not remember where they left their personal belongings.
This thesis explore different approaches using Convolutional and Recurrent Neural Networks to classify and temporally localize activities on videos, furthermore an implementation to achieve it has been proposed. As the first step, features have been extracted from video frames using an state of the art 3D Convolutional Neural Network. This features are fed in a recurrent neural network that solves the activity classification and temporally location tasks in a simple and flexible way. Different architectures and configurations have been tested in order to achieve the best performance and learning of the video dataset provided. In addition it has been studied different kind of post processing over the trained network's output to achieve a better results on the temporally localization of activities on the videos. The results provided by the neural network developed in this thesis have been submitted to the ActivityNet Challenge 2016 of the CVPR, achieving competitive results using a simple and flexible architecture.
Visual multimedia have become an inseparable part of our digital social lives, and they often capture moments tied with deep affections. Automated visual sentiment analysis tools can provide a means of extracting the rich feelings and latent dispositions embedded in these media. In this work, we explore how Convolutional Neural Networks (CNNs), a now de facto computational machine learning tool particularly in the area of Computer Vision, can be specifically applied to the task of visual sentiment prediction. We accomplish this through fine-tuning experiments using a state-of-the-art CNN and via rigorous architecture analysis, we present several modifications that lead to accuracy improvements over prior art on a dataset of images from a popular social media platform. We additionally present visualizations of local patterns that the network learned to associate with image sentiment for insight into how visual positivity (or negativity) is perceived by the model.
We present a method for performing hierarchical object detection in images guided by a deep reinforcement learning agent. The key idea is to focus on those parts of the image that contain richer information and zoom on them. We train an intelligent agent that, given an image window, is capable of deciding where to focus the attention among five different predefined region candidates (smaller windows). This procedure is iterated providing a hierarchical image analysis.We compare two different candidate proposal strategies to guide the object search: with and without overlap. Moreover, our work compares two different strategies to extract features from a convolutional neural network for each region proposal: a first one that computes new feature maps for each region proposal, and a second one that computes the feature maps for the whole image to later generate crops for each region proposal. Experiments indicate better results for the overlapping candidate proposal strategy and a loss of performance for the cropped image features due to the loss of spatial resolution. We argue that, while this loss seems unavoidable when working with large amounts of object candidates, the much more reduced amount of region proposals generated by our reinforcement learning agent allows considering to extract features for each location without sharing convolutional computation among regions.
This thesis report studies methods to solve Visual Question-Answering (VQA) tasks with a Deep Learning framework. As a preliminary step, we explore Long Short-Term Memory (LSTM) networks used in Natural Language Processing (NLP) to tackle Question-Answering (text based). We then modify the previous model to accept an image as an input in addition to the question. For this purpose, we explore the VGG-16 and K-CNN convolutional neural networks to extract visual features from the image. These are merged with the word embedding or with a sentence embedding of the question to predict the answer. This work was successfully submitted to the Visual Question Answering Challenge 2016, where it achieved a 53,62% of accuracy in the test dataset. The developed software has followed the best programming practices and Python code style, providing a consistent baseline in Keras for different configurations.
Image representations derived from pre-trained Convolutional Neural Networks (CNNs) have become the new state of the art in computer vision tasks such as instance retrieval. This work explores the suitability for instance retrieval of image- and region-wise representations pooled from an object detection CNN such as Faster R-CNN. We take advantage of the object proposals learned by a Region Proposal Network (RPN) and their associated CNN features to build an instance search pipeline composed of a first filtering stage followed by a spatial reranking. We further investigate the suitability of Faster R-CNN features when the network is fine-tuned for the same objects one wants to retrieve. We assess the performance of our proposed system with the Oxford Buildings 5k, Paris Buildings 6k and a subset of TRECVid Instance Search 2013, achieving competitive results.
This work proposes a simple instance retrieval pipeline based on encoding the convolutional features of CNN using the bag of words aggregation scheme (BoW). Assigning each local array of activations in a convolutional layer to a visual word produces an \textit{assignment map}, a compact representation that relates regions of an image with a visual word. We use the assignment map for fast spatial reranking, obtaining object localizations that are used for query expansion. We demonstrate the suitability of the BoW representation based on local CNN features for instance retrieval, achieving competitive performance on the Oxford and Paris buildings benchmarks. We show that our proposed system for CNN feature aggregation with BoW outperforms state-of-the-art techniques using sum pooling at a subset of the challenging TRECVid INS benchmark.