No abstract

No abstract

Some images that are difficult to recognize on their own may become more clear in the context of a neighborhood of related images with similar social-network metadata. We build on this intuition to improve multilabel image annotation. Our model uses image metadata nonparametrically to generate neighborhoods of related images using Jaccard similarities, then uses a deep neural network to blend visual information from the image and its neighbors. Prior work typically models image metadata parametrically; in contrast, our nonparametric treatment allows our model to perform well even when the vocabulary of metadata changes between training and testing. We perform comprehensive experiments on the NUS-WIDE dataset, where we show that our model outperforms state-of-the-art methods for multilabel image annotation even when our model is forced to generalize to new types of metadata.

Human motion and behaviour in crowded spaces is influenced by several factors, such as the dynamics of other moving agents in the scene, as well as the static elements that might be perceived as points of attraction or obstacles. In this work, we present a new model for human trajectory prediction which is able to take advantage of both humanhuman and human-space interactions. The future trajectory of humans, are generated by observing their past positions and interactions with the surroundings. To this end, we propose a "context-aware" recurrent neural network LSTM model, which can learn and predict human motion in crowded spaces such as a sidewalk, a museum or a shopping mall. We evaluate our model on a public pedestrian datasets, and we contribute a new challenging dataset that collects videos of humans that navigate in a (real) crowded space such as a big museum. Results show that our approach can predict human trajectories better when compared to previous state-of-the-art forecasting models.

When given a single frame of the video, humans can not only interpret the content of the scene, but also they are able to forecast the near future. This ability is mostly driven by their rich prior knowledge about the visual world, both in terms of (i) the dynamics of moving agents, as well as (ii) the semantic of the scene. In this work we exploit the interplay between these two key elements to predict scenespecific motion patterns. First, we extract patch descriptors encoding the probability of moving to the adjacent patches, and the probability of being in that particular patch or changing behavior. Then, we introduce a Dynamic Bayesian Network which exploits this scene specific knowledge for trajectory prediction. Experimental results demonstrate that our method is able to accurately predict trajectories and transfer predictions to a novel scene characterized by similar elements.

Research on methods for detection and recognition of events and actions in videos is receiving an increasing attention from the scientific community, because of its relevance for many applications, from semantic video indexing to intelligent video surveillance systems and advanced human-computer interaction interfaces. Event detection and recognition requires to consider the temporal aspect of video, either at the low-level with appropriate features, or at a higher-level with models and classifiers than can represent time. In this paper we survey the field of event recognition, from interest point detectors and descriptors, to event modelling techniques and knowledge management technologies. We provide an overview of the methods, categorising them according to video production methods and video domains, and according to types of events and actions that are typical of these domains

When an attacker wants to falsify an image, in most of cases she/he will perform a JPEG recompression. Different techniques have been developed based on diverse theoretical assumptions but very effective solutions have not been developed yet. Recently, machine learning based approaches have been started to appear in the field of image forensics to solve diverse tasks such as acquisition source identification and forgery detection. In this last case, the aim ahead would be to get a trained neural network able, given a to-be-checked image, to reliably localize the forged areas. With this in mind, our paper proposes a step forward in this direction by analyzing how a single or double JPEG compression can be revealed and localized using convolutional neural networks (CNNs). Different kinds of input to the CNN have been taken into consideration, and various experiments have been carried out trying also to evidence potential issues to be further investigated

Automatic image annotation is among the fundamental problems in computer vision and pattern recognition, and it is becoming increasingly important in order to develop algorithms that are able to search and browse large-scale image collections. In this paper, we propose a label propagation framework based on Kernel Canonical Correlation Analysis (KCCA), which builds a latent semantic space where correlation of visual and textual features are well preserved into a semantic embedding. The proposed approach is robust and can work either when the training set is well annotated by experts, as well as when it is noisy such as in the case of user-generated tags in social media. We report extensive results on four popular datasets. Our results show that our KCCA-based framework can be applied to several state-of-the-art label transfer methods to obtain significant improvements. Our approach works even with the noisy tags of social users, provided that appropriate denoising is performed. Experiments on a large scale setting show that our method can provide some benefits even when the semantic space is estimated on a subset of training images.