Though impressive results have been achieved in visual captioning, the task of generating abstract stories from photo streams is still a little-tapped problem. Different from captions, stories have more expressive language styles and contain many imaginary concepts that do not appear in the images. Thus it poses challenges to behavioral cloning algorithms. Furthermore, due to the limitations of automatic metrics on evaluating story quality, reinforcement learning methods with hand-crafted rewards also face difficulties in gaining an overall performance boost. Therefore, we propose an Adversarial REward Learning (AREL) framework to learn an implicit reward function from human demonstrations, and then optimize policy search with the learned reward function. Though automatic evaluation indicates slight performance boost over state-of-the-art (SOTA) methods in cloning expert behaviors, human evaluation shows that our approach achieves significant improvement in generating more human-like stories than SOTA systems.

Impressive image captioning results (i.e., an objective description for an image) are achieved with plenty of training pairs. In this paper, we take one step further to investigate the creation of narrative paragraph for a photo stream. This task is even more challenging due to the difficulty in modeling an ordered photo sequence and in generating a relevant paragraph with expressive language style for storytelling. The difficulty can even be exacerbated by the limited training data, so that existing approaches almost focus on search-based solutions. To deal with these challenges, we propose a sequence-to-sequence modeling approach with reinforcement learning and adversarial training. First, to model the ordered photo stream, we propose a hierarchical recurrent neural network as story generator, which is optimized by reinforcement learning with rewards. Second, to generate relevant and story-style paragraphs, we design the rewards with two critic networks, including a multi-modal and a language-style discriminator. Third, we further consider the story generator and reward critics as adversaries. The generator aims to create indistinguishable paragraphs to human-level stories, whereas the critics aim at distinguishing them and further improving the generator by policy gradient. Experiments on three widely-used datasets show the effectiveness, against state-of-the-art methods with relative increase of 20.2% by METEOR. We also show the subjective preference for the proposed approach over the baselines through a user study with 30 human subjects.

Automatic generation of natural language description for individual images (a.k.a. image captioning) has attracted extensive research attention. In this paper, we take one step further to investigate the generation of a paragraph to describe a photo stream for the purpose of storytelling. This task is even more challenging than individual image description due to the difficulty in modeling the large visual variance in an ordered photo collection and in preserving the long-term language coherence among multiple sentences. To deal with these challenges, we formulate the task as a sequence-to-sequence learning problem and propose a novel joint learning model by leveraging the semantic coherence in a photo stream. Specifically, to reduce visual variance, we learn a semantic space by jointly embedding each photo with its corresponding contextual sentence, so that the semantically related photos and their correlations are discovered. Then, to preserve language coherence in the paragraph, we learn a novel Bidirectional Attention-based Recurrent Neural Network (BARNN) model, which can attend on the discovered semantic relation to produce a sentence sequence and maintain its consistence with the photo stream. We integrate the two-step learning components into one single optimization formulation and train the network in an end-to-end manner. Experiments on three widely-used datasets (NYC/Disney/SIND) show that the proposed approach outperforms state-of-the-art methods with large margins for both retrieval and paragraph generation tasks. We also show the subjective preference of the machine-generated stories by the proposed approach over the baselines through a user study with 40 human subjects.

While wearable cameras are becoming increasingly popular, locating relevant information in large unstructured collections of egocentric images is still a tedious and time consuming process. This paper addresses the problem of organizing egocentric photo streams acquired by a wearable camera into semantically meaningful segments, hence making an important step towards the goal of automatically annotating these photos for browsing and retrieval. In the proposed method, first, contextual and semantic information is extracted for each image by employing a Convolutional Neural Networks approach. Later, a vocabulary of concepts is defined in a semantic space by relying on linguistic information. Finally, by exploiting the temporal coherence of concepts in photo streams, images which share contextual and semantic attributes are grouped together. The resulting temporal segmentation is particularly suited for further analysis, ranging from event recognition to semantic indexing and summarization. Experimental results over egocentric set of nearly 31,000 images, show the prominence of the proposed approach over state-of-the-art methods. Keywords: temporal segmentation, egocentric vision, photo streams clustering 1. Introduction Among the advances in wearable technology during the last few years, wearable cameras specifically have gained more popularity [5].

The new social media sites - blogs, wikis, del.icio.us and Flickr, among others - underscore the transformation of the Web to a participatory medium in which users are actively creating, evaluating and distributing information. The photo-sharing site Flickr, for example, allows users to upload photographs, view photos created by others, comment on those photos, etc. As is common to other social media sites, Flickr allows users to designate others as ``contacts'' and to track their activities in real time. The contacts (or friends) lists form the social network backbone of social media sites. We claim that these social networks facilitate new ways of interacting with information, e.g., through what we call social browsing. The contacts interface on Flickr enables users to see latest images submitted by their friends. Through an extensive analysis of Flickr data, we show that social browsing through the contacts' photo streams is one of the primary methods by which users find new images on Flickr. This finding has implications for creating personalized recommendation systems based on the user's declared contacts lists.