Common image-text joint understanding techniques presume that images and the associated text can universally be characterized by a single implicit model. However, co-occurring images and text can be related in qualitatively different ways, and explicitly modeling it could improve the performance of current joint understanding models. In this paper, we train a Cross-Modal Coherence Modelfor text-to-image retrieval task. Our analysis shows that models trained with image--text coherence relations can retrieve images originally paired with target text more often than coherence-agnostic models. We also show via human evaluation that images retrieved by the proposed coherence-aware model are preferred over a coherence-agnostic baseline by a huge margin. Our findings provide insights into the ways that different modalities communicate and the role of coherence relations in capturing commonsense inferences in text and imagery.
This paper considers the problem of spatiotemporal object-centric reasoning in videos. Central to our approach is the notion of object permanence, i.e., the ability to reason about the location of objects as they move through the video while being occluded, contained or carried by other objects. Existing deep learning based approaches often suffer from spatiotemporal biases when applied to video reasoning problems. We propose Hopper, which uses a Multi-hop Transformer for reasoning object permanence in videos. Given a video and a localization query, Hopper reasons over image and object tracks to automatically hop over critical frames in an iterative fashion to predict the final position of the object of interest. We demonstrate the effectiveness of using a contrastive loss to reduce spatiotemporal biases. We evaluate over CATER dataset and find that Hopper achieves 73.2% Top-1 accuracy using just 1 FPS by hopping through just a few critical frames. We also demonstrate Hopper can perform long-term reasoning by building a CATER-h dataset that requires multi-step reasoning to localize objects of interest correctly.
Floorplans are commonly used to represent the layout of buildings. In computer aided-design (CAD) floorplans are usually represented in the form of hierarchical graph structures. Research works towards computational techniques that facilitate the design process, such as automated analysis and optimization, often use simple floorplan representations that ignore the semantics of the space and do not take into account usage related analytics. We present a floorplan embedding technique that uses an attributed graph to represent the geometric information as well as design semantics and behavioral features of the inhabitants as node and edge attributes. A Long Short-Term Memory (LSTM) Variational Autoencoder (VAE) architecture is proposed and trained to embed attributed graphs as vectors in a continuous space. A user study is conducted to evaluate the coupling of similar floorplans retrieved from the embedding space with respect to a given input (e.g., design layout). The qualitative, quantitative and user-study evaluations show that our embedding framework produces meaningful and accurate vector representations for floorplans. In addition, our proposed model is a generative model. We studied and showcased its effectiveness for generating new floorplans. We also release the dataset that we have constructed and which, for each floorplan, includes the design semantics attributes as well as simulation generated human behavioral features for further study in the community.
Software development is becoming increasingly open and collaborative with the advent of platforms such as GitHub. Given its crucial role, there is a need to better understand and model the dynamics of GitHub as a social platform. Previous work has mostly considered the dynamics of traditional social networking sites like Twitter and Facebook. We propose GitEvolve, a system to predict the evolution of GitHub repositories and the different ways by which users interact with them. To this end, we develop an end-to-end multi-task sequential deep neural network that given some seed events, simultaneously predicts which user-group is next going to interact with a given repository, what the type of the interaction is, and when it happens. To facilitate learning, we use graph based representation learning to encode relationship between repositories. We map users to groups by modelling common interests to better predict popularity and to generalize to unseen users during inference. We introduce an artificial event type to better model varying levels of activity of repositories in the dataset. The proposed multi-task architecture is generic and can be extended to model information diffusion in other social networks. In a series of experiments, we demonstrate the effectiveness of the proposed model, using multiple metrics and baselines. Qualitative analysis of the model's ability to predict popularity and forecast trends proves its applicability.
Cross-modal knowledge distillation deals with transferring knowledge from a model trained with superior modalities (Teacher) to another model trained with weak modalities (Student). Existing approaches require paired training examples exist in both modalities. However, accessing the data from superior modalities may not always be feasible. For example, in the case of 3D hand pose estimation, depth maps, point clouds, or stereo images usually capture better hand structures than RGB images, but most of them are expensive to be collected. In this paper, we propose a novel scheme to train the Student in a Target dataset where the Teacher is unavailable. Our key idea is to generalize the distilled cross-modal knowledge learned from a Source dataset, which contains paired examples from both modalities, to the Target dataset by modeling knowledge as priors on parameters of the Student. We name our method "Cross-Modal Knowledge Generalization" and demonstrate that our scheme results in competitive performance for 3D hand pose estimation on standard benchmark datasets.
Predicting the behavior of crowds in complex environments is a key requirement in a multitude of application areas, including crowd and disaster management, architectural design, and urban planning. Given a crowd's immediate state, current approaches simulate crowd movement to arrive at a future state. However, most applications require the ability to predict hundreds of possible simulation outcomes (e.g., under different environment and crowd situations) at real-time rates, for which these approaches are prohibitively expensive. In this paper, we propose an approach to instantly predict the long-term flow of crowds in arbitrarily large, realistic environments. Central to our approach is a novel CAGE representation consisting of Capacity, Agent, Goal, and Environment-oriented information, which efficiently encodes and decodes crowd scenarios into compact, fixed-size representations that are environmentally lossless. We present a framework to facilitate the accurate and efficient prediction of crowd flow in never-before-seen crowd scenarios. We conduct a series of experiments to evaluate the efficacy of our approach and showcase positive results.
In the event of a disaster, saving human lives is of utmost importance. For developing proper evacuation procedures and guidance systems, behavioural data on how people respond during panic and stress is crucial. In the absence of real human data on building evacuation, there is a need for a crowd simulator to model egress and decision-making under uncertainty. In this paper, we propose an agent-based simulation tool, which is grounded in human cognition and decision-making, for evaluating and improving the effectiveness of building evacuation procedures and guidance systems during a disaster. Specifically, we propose a predictive agent-wayfinding framework based on information theory that is applied at intersections with variable route choices where it fuses N dynamic information sources. The proposed framework can be used to visualize trajectories and prediction results (i.e., total evacuation time, number of people evacuated) for different combinations of reinforcing or contradicting information sources (i.e., signage, crowd flow, familiarity, and spatial layout). This tool can enable designers to recreate various disaster scenarios and generate simulation data for improving the evacuation procedures and existing guidance systems.
Automatically generating animation from natural language text finds application in a number of areas e.g. movie script writing, instructional videos, and public safety. However, translating natural language text into animation is a challenging task. Existing text-to-animation systems can handle only very simple sentences, which limits their applications. In this paper, we develop a text-to-animation system which is capable of handling complex sentences. We achieve this by introducing a text simplification step into the process. Building on an existing animation generation system for screenwriting, we create a robust NLP pipeline to extract information from screenplays and map them to the system's knowledge base. We develop a set of linguistic transformation rules that simplify complex sentences. Information extracted from the simplified sentences is used to generate a rough storyboard and video depicting the text. Our sentence simplification module outperforms existing systems in terms of BLEU and SARI metrics.We further evaluated our system via a user study: 68 % participants believe that our system generates reasonable animation from input screenplays.
In this paper, we study the problem of learning Graph Convolutional Networks (GCNs) for regression. Current architectures of GCNs are limited to the small receptive field of convolution filters and shared transformation matrix for each node. To address these limitations, we propose Semantic Graph Convolutional Networks (SemGCN), a novel neural network architecture that operates on regression tasks with graph-structured data. SemGCN learns to capture semantic information such as local and global node relationships, which is not explicitly represented in the graph. These semantic relationships can be learned through end-to-end training from the ground truth without additional supervision or hand-crafted rules. We further investigate applying SemGCN to 3D human pose regression. Our formulation is intuitive and sufficient since both 2D and 3D human poses can be represented as a structured graph encoding the relationships between joints in the skeleton of a human body. We carry out comprehensive studies to validate our method. The results prove that SemGCN outperforms state of the art while using 90% fewer parameters.
Developing intelligent virtual characters has attracted a lot of attention in the recent years. The process of creating such characters often involves a team of creative authors who describe different aspects of the characters in natural language, and planning experts that translate this description into a planning domain. This can be quite challenging as the team of creative authors should diligently define every aspect of the character especially if it contains complex human-like behavior. Also a team of engineers has to manually translate the natural language description of a character's personality into the planning domain knowledge. This can be extremely time and resource demanding and can be an obstacle to author's creativity. The goal of this paper is to introduce an authoring assistant tool to automate the process of domain generation from natural language description of virtual characters, thus bridging between the creative authoring team and the planning domain experts. Moreover, the proposed tool also identifies possible missing information in the domain description and iteratively makes suggestions to the author.